Management treatment of insulin therapy using reinforcement learning and therapy upgrade approach

Abstract

A method of therapy upgrade for a diabetic patient includes: receiving glucose data of a user from an in vivo glucose monitoring device; receiving first therapy information for a first therapy, wherein the first therapy includes basal insulin; calculating one or more glucose metrics based on the received glucose data; titrating a dose of basal insulin based on the one or more glucose metrics; and determining a basal insulin excess based on one or more of the glucose data and the first therapy information. Advantageously, the system is capable of regularly monitoring a user's glucose control, detecting basal insulin excess, providing frequent therapy intervention and adjustments, reducing the duration of intervention, and improving user adherence, efficacy, and satisfaction.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 494,865, filed April 7, 2023, and also claims the benefit of U.S. Provisional Application No. 63 / 560,371, filed March 1, 2024, each of which is incorporated herein by reference in its entirety. Technical Field

[0003] This disclosure relates to therapy management devices, systems, and methods, such as management processes for insulin therapy using reinforcement learning, and software application devices, systems, and methods for detecting the effectiveness of current therapy, detecting basal insulin overdose, and escalating to one or more therapy pathways. Background Technology

[0004] Detecting and / or monitoring glucose levels can be crucial to the health of individuals with diabetes. People with diabetes (PWD) generally require monitoring of their glucose levels to ensure they remain within a clinically safe range, and this information can also be used to determine whether and / or when insulin is needed to lower their glucose levels, or when additional glucose is needed to raise them. Several systems allow individuals to monitor their glucose, such as using a continuous glucose monitor (CGM) to measure interstitial fluid glucose levels. Some of these systems include electrochemical biosensors, including systems that use glucose sensors adapted for placement within the body, such as those inserted fully or partially subcutaneously or percutaneously, to continuously monitor glucose levels in body fluids (e.g., interstitial fluid) at that site.

[0005] Diabetes is a chronic metabolic disorder caused by the pancreas's inability to produce enough insulin, resulting in an inability to properly absorb sugars and starches. This dysfunction leads to hyperglycemia, for example, the presence of excess glucose. Persistent hyperglycemia is associated with a variety of serious symptoms and life-threatening long-term complications, such as dehydration, ketoacidosis, diabetic coma, cardiovascular disease, chronic kidney failure, retinal damage, and nerve damage, and even the risk of amputation.

[0006] To maintain glucose levels within acceptable limits, a permanent therapy providing sustained glucose control is needed. This blood glucose control can be achieved by periodically administering topical medications to the PWD, thereby lowering elevated glucose levels. Topical bioactive drugs (e.g., insulin or its analogues) are typically administered via daily injections. In some cases, multiple daily injections of a mixture of rapid-acting (RA) and long-acting (LA) insulin are administered via reusable transdermal liquid delivery devices.

[0007] Glycated hemoglobin HbAlc (A1C) is a form of hemoglobin that has chemically linked to it sugar. The formation of sugar-hemoglobin linkages can indicate the presence of excess sugar in the bloodstream, often suggesting high concentrations of diabetes. A1C is measured primarily to determine the average blood glucose level over a 3-month period, and can be used as a diagnostic test for diabetes and as an assessment test for glycemic control of PWDs. Generally, normal A1C levels are below 5.7%, levels of 5.7% to 6.4% indicate prediabetes, and levels of 6.5% or above indicate diabetes. Within the prediabetes range of 5.7% to 6.4%, the higher the A1C level for a PWD, the greater the risk of developing type 2 diabetes.

[0008] Currently, the method of monitoring A1C levels is limited to every 3-6 months, depending on a variety of factors. This method of measuring patient progress and follow-up, which is limited to quarterly or semi-annual visits, results in significant therapeutic inertia throughout the course of treatment for PWDs, leading to suboptimal efficacy and creating a method of “treat-to-failure” for diabetes therapy. Additionally, limited human resources continue to delay advancing therapy according to standards of care. SUMMARY

[0009] Accordingly, there is a need to develop a therapy management system that can regularly monitor glucose control of a user, provide frequent therapy interventions and adjustments (e.g., on a daily or weekly basis rather than every 3-6 months), reduce the duration of interventions, and improve user adherence, efficacy, and satisfaction.

[0010] In one aspect, a non-transitory computer-readable storage medium having instructions stored thereon that, when executed by a processor, cause the processor to perform operations for management processing of insulin therapy, the operations comprising: performing a survey on a person with diabetes (PWD) and receiving survey information in response to the survey; performing a high-touch interaction phase on the PWD, the high-touch interaction phase comprising repeatedly adjusting insulin therapy based on collected data and publicly available guidelines on insulin therapy, the high-touch interaction phase establishing at least a basal dose setting, a meal dose setting, and a correction dose setting for the PWD; and performing an ongoing phase on the PWD after termination of the high-touch interaction phase, the ongoing phase comprising collecting performance metrics for the PWD, applying reinforcement learning to the performance metrics, and automatically performing actions on the PWD based on the reinforcement learning.

[0011] Implementations can include any or all of the following features. The high-touch interaction phase is executed for a predetermined length of time. The high-touch interaction phase has a target-based duration. The target-based duration depends on a determination that the PWD’s blood glucose level is within a target range and that the PWD is taking insulin as prescribed in an insulin therapy. The operations further include evaluating each insight of a plurality of insights and determining whether the insight is triggered in view of at least a performance metric and collected data, wherein the action is selected based on at least one of the insights being triggered. The insights are evaluated according to a priority with respect to the PWD. The evaluated insight is selected from the set of insights based on having the highest priority. Evaluating at least one of the insights includes a multi-modal evaluation. The operations further include performing an observation of a state of the PWD after automatically performing the action. The reinforcement learning includes providing positive or negative feedback on the selection of the action. The operations further include performing a cool down after termination of the observation. The operations further include evaluating each insight of a plurality of insights and determining whether the insight is triggered in view of at least a performance metric and collected data, wherein the action is selected based on at least one of the insights being triggered. The operations further include checking, prior to selecting the action, whether a cool down involves the action. If the cool down involves the action, then the operations instead evaluate a next insight of the plurality of insights. The operations further include evaluating each insight of a plurality of insights and determining whether the insight is triggered in view of at least a performance metric and collected data, wherein the action is selected based on at least one of the insights being triggered. The operations further include checking, prior to selecting the action, whether an observation involves the insight. If the observation involves the insight, then the operations evaluate an improvement criterion with respect to the insight in view of at least a performance metric and collected data. Evaluating the improvement criterion includes a multi-modal evaluation. For any insight that is not triggered in the evaluation, the operations further include determining whether the insight has not been triggered for at least a predetermined time, and performing a continuous action in view of the determination. Automatically performing the action includes selecting one or more targets for the PWD and presenting the one or more targets to the PWD. The operations further include receiving a PWD opt-in input or an opt-out input.

[0012] In some aspects, a method for therapy escalation for a PWD can include receiving glucose data of a user from an in vivo glucose monitoring device. In some aspects, the method can further include receiving first therapy information of a first therapy. In some aspects, the first therapy can include basal insulin. In some aspects, the method can further include calculating one or more glucose metrics based on the received glucose data. In some aspects, the method can further include titrating a dose of the basal insulin based on the one or more glucose metrics. In some aspects, the method can further include determining a basal insulin excess based on one or more of the glucose data and the first therapy information.

[0013] In some aspects, the method can further include outputting a recommendation to add a second therapy when the basal insulin excess is determined.

[0014] In some aspects, outputting the recommendation can include displaying the recommendation. In some aspects, displaying the recommendation can include displaying the recommendation on a display device, a remote device (e.g., a receiver, a smart phone, a computer, etc.), a medication delivery device, a pen cap, or a combination thereof.

[0015] In some aspects, outputting the recommendation can include outputting the recommended therapy. In some aspects, outputting the recommended therapy can include communicating the recommended therapy to a display device, a remote device (e.g., a receiver, a smart phone, a computer, etc.), a medication delivery device, a pen cap, or a combination thereof.

[0016] In some aspects, the method can further include administering the recommended dose and / or the recommended therapy via a medication delivery device. In some aspects, the recommended dose and / or the recommended therapy can be administered automatically or upon user confirmation.

[0017] In some aspects, the first therapy information can include information about a recommended dose amount of basal insulin, an actual basal insulin dose amount, a timing of basal insulin administration, or a combination thereof.

[0018] In some aspects, alternatively, the method can further include outputting an indication that titration has stopped when the basal insulin excess is determined, and / or outputting an indication that the patient should consult their doctor when the basal insulin excess is determined, instead of outputting a recommendation to add a second therapy. For example, the indication can provide a notification to the user (e.g., “Titration has stopped due to inability to optimize your basal insulin. Please consult your doctor.”, “Please consult your doctor regarding basal insulin excess.”).

[0019] In some aspects, the one or more glucose metrics can include a mean glucose, a median glucose, a time in range (TIR), a time below range (TBR), a time above range (TAR), a time very low (TVL), a glucose management indicator (GMI), a minimum morning glucose (MMG), a minimum post-dose glucose (MPDG), a post-prandial glucose (PPG), a bedtime to morning glucose (BeAM), a time in tight range (TITR), a time in very tight range (TIVTR), or a combination thereof.

[0020] In some aspects, the MMG can be configured to estimate fasting glucose with continuous glucose monitoring (CGM) data. In some aspects, the MMG can be calculated based on the lowest glucose value during the morning hours, e.g., between approximately 4:30 AM to 10:00 AM, at least approximately 30 minutes before the projected wake-up time. In some aspects, the MMG can be calculated based on the median MMG, with days having nocturnal activity (e.g., treating hypoglycemia, ingesting a RA dose, missing a LA dose, etc.) ignored from the calculation, thereby providing a more robust estimate of nocturnal glucose. In some aspects, the MMG can be used as an effective metric for identifying patients needing adjustment of LA insulin therapy (e.g., MMG 14 days prior to increasing and / or decreasing LA insulin therapy settings). In some aspects, the MMG can be used as a sensitive indicator of nocturnal hypoglycemia compared to more traditional fasting glucose estimates (e.g., pre-breakfast glucose). In some aspects, a change in the median MMG can indicate a change (e.g., increase or decrease) in LA insulin therapy. In some aspects, an increase in the median MMG (e.g., 110 mg / dL to 155 mg / dL) can indicate an increase in LA insulin therapy. In some aspects, a decrease in the median MMG (e.g., 155 mg / dL to 110 mg / dL) can indicate a decrease in LA insulin therapy.

[0021] In some aspects, the first therapy information can be manually entered via an input of the computing device. In some aspects, the first therapy information can be collected by a drug delivery device and can be transmitted to the computing device. In some aspects, the first therapy information can be collected by a dose detection device for a drug delivery device, such as an add-on module or smart cap, etc. In some aspects, the drug delivery device can include an infusion pump, a patch pump, or an injection pen, etc. In some aspects, the initial dose can also be calculated from data collected from one or more smart scales, other glucose measurement devices, or combinations thereof.

[0022] In some aspects, the basal insulin excess can be determined based on a ratio of insulin total daily dose (TDD) to weight of the user. In some aspects, the basal insulin excess can be determined based on glucose variability. In some aspects, the basal insulin excess can be determined based on a hypoglycemia metric. In some aspects, the basal insulin excess can be determined based on a change in glucose levels in a meal period or a nocturnal period.

[0023] In some aspects, the method can further include decreasing the basal insulin dose upon adding the second therapy.

[0024] In some aspects, the second therapy can include a glucagon-like peptide-1 (GLP-1) receptor agonist. In some aspects, the method can further include titrating a dose of the GLP-1 receptor agonist. In some aspects, titrating the dose can include receiving user input regarding side effects of the second therapy. In some aspects, titrating the dose can include recommending an increased dose when the user input is associated with no side effects. In some aspects, titrating the dose can include receiving a body weight measurement of the user. In some aspects, titrating the dose can include recommending an increased dose when the body weight measurement is above a target body weight.

[0025] In some aspects, the one or more glucose metrics can include a postprandial glucose rise for each meal of a plurality of meals. In some aspects, the method can further include recommending initiating a prandial insulin dose for a first meal when the postprandial glucose rise for the meal exceeds a threshold. In some aspects, the threshold can be defined by a total change in glucose levels (difference between minimum and maximum) from a pre-meal period to a post-meal period, a rate of change in glucose levels (slope), a post- pre-meal difference, or a combination thereof. In some aspects, the method can further include recommending initiating a prandial insulin dose for a plurality of meals when the postprandial glucose rise for each meal of the plurality of meals exceeds a threshold. In some aspects, the threshold can be defined by a total change in glucose levels (difference between minimum and maximum) from a pre-meal period to a post-meal period for a plurality of meals, a rate of change in glucose levels (slope) for each meal of the plurality of meals, a post- pre-meal difference for each meal of the plurality of meals, or a combination thereof.

[0026] In some aspects, a system for therapy escalation for a diabetes patient can include an in vivo glucose monitoring device, a remote device, a drug delivery device, and a processor. In some aspects, the in vivo glucose monitoring device can be configured to measure glucose data of a user. In some aspects, the remote device can be in communication with the in vivo glucose monitoring device. In some aspects, the remote device can be configured to receive or retrieve glucose data from the in vivo glucose monitoring device. In some aspects, the drug delivery device can be in communication with the in vivo glucose monitoring device and the remote device. In some aspects, the drug delivery device can be configured to administer one or more dosing regimens. In some aspects, the processor can be in communication with an analyte measurement system, the remote device, and the drug delivery device. In some aspects, the processor can be coupled to a memory storing instructions that, when executed, cause the processor to perform operations comprising receiving glucose data of a user from an in vivo glucose monitoring device. In some aspects, the operations can further comprise receiving first therapy information of a first therapy from the remote device, the drug delivery device, or both. In some aspects, the first therapy can comprise basal insulin. In some aspects, the operations can further comprise calculating one or more glucose metrics based on the received glucose data. In some aspects, the operations can further comprise titrating a dose of basal insulin based on the one or more glucose metrics. In some aspects, the operations can further comprise determining a basal insulin excess based on one or more of the glucose data and the first therapy information.

[0027] In some aspects, the operations can further comprise outputting a recommendation to add a second therapy to the remote device when the basal insulin excess is determined.

[0028] In some aspects, outputting the recommendation can comprise displaying the recommendation on the remote device (e.g., receiver, smart phone, computer, etc.). In some aspects, displaying the recommendation can comprise displaying the recommendation on a display device, the remote device, the drug delivery device, a pen cap, or a combination thereof.

[0029] In some aspects, outputting the recommendation can comprise outputting the recommended therapy. In some aspects, outputting the recommended therapy can comprise communicating the recommended therapy to a display device, a remote device (e.g., receiver, smart phone, computer, etc.), a drug delivery device, a pen cap, or a combination thereof.

[0030] In some aspects, the operations can further comprise administering the recommended dose and / or the recommended therapy via the drug delivery device. In some aspects, the recommended dose and / or the recommended therapy can be administered automatically or upon user confirmation.

[0031] In some aspects, a system for managing therapy to maintain one or more user metrics within one or more targets or ranges thereof can include an analyte measurement system, a remote device, a drug delivery device, and a software application. In some aspects, the analyte measurement system can be configured to measure an analyte (e.g., glucose) of a user. In some aspects, the analyte measurement system can include an analyte sensor. In some aspects, the remote device can be in communication with the analyte measurement system. In some aspects, the remote device can be configured to receive or retrieve sensor data from the analyte sensor. In some aspects, the drug delivery device can be in communication with the analyte measurement system and the remote device. In some aspects, the drug delivery device can be configured to administer one or more dosing regimens. In some aspects, the software application can be in communication with the analyte measurement system, the remote device, and the drug delivery device.

[0032] In some aspects, the software application can be running on a processor coupled to a memory storing instructions that, when executed, cause the processor to perform operations including recommending a first dosing regimen (e.g., basal insulin) if one or more user metrics are outside of one or more targets. In some aspects, the operations can further include determining a basal insulin excess for the first dosing regimen. In some aspects, the operations can further include adding a second dosing regimen (e.g., GLP-1, single mealtime bolus, mealtime bolus per meal) if the one or more user metrics are maintained outside of the one or more targets or if the basal insulin excess is determined. In some aspects, the operations can further include determining a basal insulin excess for the second dosing regimen. In some aspects, the user can be performing an initial dosing regimen (e.g., GLP-1, etc.) prior to performing the first dosing regimen (e.g., basal insulin).

[0033] In some aspects, the one or more user metrics can include mean glucose, median glucose, time in range (TIR) of glucose, time in tight range (TITR) of glucose, time in very tight range (TIVTR) of glucose, time below range (TBR) of glucose, time above range (TAR) of glucose, time very low (TVL) of glucose, coefficient of variation of glucose (CV), glucose management indicator (GMI), minimum morning glucose (MMG), minimum post-dose glucose (MPDG), post-prandial glucose (PPG), basal bolus ratio (BBR), bedtime to morning glucose (BeAM), insulin sensitivity factor (ISF), post rapid-acting dose correction glucose (PRA-CG), weight, BMI, total daily dose (TDD) (e.g., of insulin), ratio of TDD to weight, A1C level (e.g., percentage of glycated hemoglobin, mmol / mol), heart rate, blood pressure, or combinations thereof.

[0034] In some aspects, the one or more targets can include a target glucose level (e.g., about 110 mg / dL), a target glucose level range (e.g., about 110 mg / dL to about 155 mg / dL), a target basal state (e.g., MMG about 100 mg / dL to about 130 mg / dL), a target meal state (e.g., MPDG about 100 mg / dL to about 120 mg / dL), a target correction ISF state (e.g., PRA-CG about 70 mg / dL to about 180 mg / dL), a target weight, a target A1C level (e.g., 5.7%), a target heart rate, a target blood pressure, a target body mass, or a combination thereof. In some aspects, the one or more targets can be based at least in part on a body mass index (BMI) of the user and a mean glucose level of the user.

[0035] In some aspects, in the second dosing regimen, the operations can further include monitoring one or more user adherence metrics for a first time period. In some aspects, the one or more user adherence metrics can include correct wear and use of the CGM, correct and consistent administration of the medication, or a combination thereof. In some aspects, in the second dosing regimen, the operations can further include rapid titration of the basal analog, the GLP-1 class drug, or the prandial RA insulin for a second time period. In some aspects, the rapid titration can include recommending an adjusted dose at a first interval (e.g., daily) based on the one or more user metrics for the first interval until no changes are made for a predetermined time period (e.g., 3 days). In some aspects, in the second dosing regimen, the operations can further include monitoring whether the dosing output state is unchanged for a third time period. In some aspects, in the second dosing regimen, the operations can further include maintaining titration of the basal analog, the GLP-1 class drug, or the prandial RA insulin for a fourth time period. In some aspects, the maintaining titration can include recommending an adjusted dose at a second interval (e.g., days, weeks) based on the one or more user metrics for the second interval until a new issue is identified (e.g., a new medication regimen, a new exercise habit, a new diet, etc.).

[0036] In some aspects, the software application can be configured to determine a basal insulin excess based at least in part on the medication delivery information. In some aspects, the basal insulin excess can be determined based at least in part on a ratio of TDD of insulin to weight of the user exceeding a predetermined threshold. In some aspects, for example, the predetermined threshold can be about 0.5 units (U) / kg / day. In some aspects, the software application can be configured to determine a basal insulin excess based at least in part on the glucose metrics. In some aspects, the basal insulin excess can be determined based at least in part on an increase in the morning (AM)-bedtime (PM) difference and / or the postprandial-preprandial difference. In some aspects, the software application can be configured to determine a basal insulin excess based at least in part on the hypoglycemia metrics being below a predetermined threshold. In some aspects, for example, the predetermined threshold can be a glucose concentration of about 70 mg / dL. In some aspects, the software application can be configured to determine a basal insulin excess based at least in part on the glucose variability exceeding a predetermined threshold. In some aspects, for example, the predetermined threshold can include a preprandial rise of less than about 30 mg / dL, a postprandial spike of less than about 110 mg / dL, a total change in glucose level from a preprandial period to a postprandial period (difference between minimum and maximum), or a combination thereof. In some aspects, the software application can be configured to determine a basal insulin excess based at least in part on a ratio of TDD of insulin to weight of the user exceeding a predetermined threshold (e.g., basal insulin dose greater than 0.5 U / kg / day), an increase in the morning (AM)-bedtime (PM) difference and / or the postprandial-preprandial difference, the hypoglycemia metrics being below a predetermined threshold (e.g., glucose concentration of about 70 mg / dL), an increase in variability of sensor data, or a combination thereof.

[0037] In some aspects, the operations can further include recommending a second dosing regimen of a glucagon-like peptide- 1 (GLP-1) receptor agonist or a gastric inhibitory peptide (GIP) / GLP-1 receptor agonist if the one or more user metrics remain outside of the one or more targets. In some aspects, the operations can further include recommending the second dosing regimen of the GLP-1 receptor agonist or the GIP / GLP-1 receptor agonist if the basal insulin excess is determined to exist.

[0038] In some aspects, the operations can further include recommending a third dosing regimen of prandial insulin at a meal if the one or more user metrics remain outside of the one or more targets. In some aspects, the operations can further include recommending the third dosing regimen of prandial insulin at a meal if the basal insulin excess is determined to exist.

[0039] In some aspects, the operations can further include recommending a fourth dosing regimen of a daily multiple injection (MDI) of bolus insulin if the one or more user metrics remain outside of the one or more targets. In some aspects, the operations can further include recommending the fourth dosing regimen of the MDI of bolus insulin if an excess of basal insulin is determined.

[0040] In some aspects, the operations can further include recommending a fifth dosing regimen of basal insulin and meal bolus insulin if the one or more user metrics remain outside of the one or more targets. In some aspects, the operations can further include recommending the fifth dosing regimen of basal insulin and meal bolus (push) insulin if an excess of basal insulin is determined.

[0041] In some aspects, for any of the dosing regimens described above, the operations can further include performing a monitoring phase, a rapid titration phase, and a maintenance phase for the current dosing regimen. In some aspects, the monitoring phase can include monitoring one or more user adherence metrics for the current dosing regimen for a predetermined period of time (e.g., 3 days) to determine whether the user is correctly wearing and using the CGM, and whether the medication is being administered correctly and consistently. In some aspects, the one or more user adherence metrics can include a frequency of glucose data (scans), an interval in the glucose data, a time of medication, a size of the dose (e.g., corresponding to a recommended dose), a receipt of user input, or a combination thereof. In some aspects, once the user adherence metrics are met, the rapid titration phase can include recommending an adjusted dose at a first interval (e.g., every night) based on one or more user metrics at the first interval until no changes are made for a predetermined period of time (e.g., 3 days). In some aspects, the dose adjustments can be made at a fixed interval (e.g., an increase of 0.25 U, an increase of 10%, etc.), or can be proportional to the degree of glucose dysfunction (e.g., a higher dose change is made if the glucose is significantly outside of the target value). In some aspects, the maintenance dose titration phase can include recommending an adjusted dose at a second interval (e.g., every few days, every week) based on one or more user metrics at the second interval until a new issue is identified (e.g., a new medication regimen, a new exercise habit, a new diet, etc.).

[0042] In some aspects, the software application can be configured to adjust a dose amount of one or more dosing regimens based at least in part on one or more metrics of the user. In some aspects, the one or more metrics can include mean glucose, glucose TIR, glucose TBR, glucose TVL, GMI, MMG, PPG, BBR, BeAM, ISF, or a combination thereof.

[0043] In some aspects, the system can further include an external scale in communication with the software application. In some aspects, the external scale can be configured to measure a weight of the user. In some aspects, the external scale can be configured to provide a weight of the user to the software application to determine an excess of basal insulin based at least in part on a ratio of the TDD of insulin to the measured weight of the user exceeding a predetermined threshold (e.g., basal insulin dose greater than 0.5 U / kg / day). In some aspects, the remote device can prompt the user to enter a weight measurement, or weigh the user using the external scale.

[0044] In some aspects, the system can further include an external sensor in communication with the software application. In some aspects, the external sensor can be configured to measure one or more user parameters. In some aspects, the one or more user parameters can include a meal parameter, an exercise-related parameter, an activity parameter, a respiration parameter, a heart rate, a heart rate variability, a temperature, a blood pressure, a sleep-related parameter, a nausea parameter, or a combination thereof. In some aspects, the external sensor can include an accelerometer, a gyroscope, a microelectromechanical system (MEMS) device, a location sensor, a sound sensor, a smart device, a smart phone, a smart ring, a bed sensor, a smart pill bottle, a smart injection pen cap, or a combination thereof.

[0045] In some aspects, the operations can further include receiving an input signal from a user or a third party. In some aspects, the operations can further include sending a control signal to the software application to recommend an adjustment to one or more dosing regimens based at least in part on the input signal. In some aspects, the input signal can include feedback, a clinician guideline, a user adherence, a verbal indication, a therapy pathway, a therapy escalation, a therapy regimen, a historical therapy regimen analysis, or a combination thereof. In some aspects, the third party can include a medical professional, such as a clinician, a primary care physician (PCP), a healthcare professional (HCP), or the like.

[0046] In some aspects, the operations can further include performing an analysis on the sensor data and the user data to generate a predictive model. In some aspects, the predictive model can be based on a regression, a model-based parameter adaptation, a supervised machine learning, an unsupervised machine learning, a neural network, a classification model, or a combination thereof.

[0047] In some aspects, the software application can be configured to receive one or more parameters of the user measured over time from a remote server. In some aspects, the software application can be configured to recommend an adjustment of one or more dosing regimens based at least in part on an algorithm or function incorporating the one or more parameters of the user measured over time. In some aspects, the software application can be configured to receive a constructed user profile. In some aspects, the constructed user profile can be generated using an artificial intelligence (AI) module trained with analytical data from a remote server. In some aspects, the software application can be configured to recommend an adjustment of one or more dosing regimens based at least in part on the constructed user profile.

[0048] In some aspects, the processor can be part of an analyte measurement system, a remote device, or a drug delivery device. In some aspects, the software application can be part of an external device, a remote server, or a cloud server. In some aspects, the software application (e.g., one or more algorithms) can be executed by a combination of devices.

[0049] In some aspects, the communication between the analyte measurement system and the remote device can include wireless communication, near field communication (NFC), Bluetooth, Bluetooth low energy (BLE), or a combination thereof.

[0050] In some aspects, a method for a diabetes patient to detect therapy escalation for non-adherence to basal insulin recommendations can include receiving glucose data of the user from an in-vivo glucose monitoring device. In some aspects, the method can further include recommending a first dose of basal insulin to the user. In some aspects, the method can further include calculating one or more glucose metrics based on the received glucose data. In some aspects, the one or more glucose metrics can include a lowest glucose metric. In some aspects, the method can further include titrating the recommended dose of basal insulin based on the one or more glucose metrics. In some aspects, the method can further include recommending a second dose of basal insulin to the user. In some aspects, the second dose can be different from the first dose, e.g., due to titrating the recommended dose. In some aspects, the method can further include calculating a change in the lowest glucose metric from a first time period before the second dose is recommended to a second time period after the second dose is recommended. In some aspects, the method can further include determining whether the change in the lowest glucose metric is outside of a predetermined metric. In some aspects, the method can further include outputting an indication to cease titration of the basal insulin if the change in the lowest glucose metric is outside of the predetermined metric.

[0051] In some aspects, the minimum glucose metric can include fasting glucose, daily minimum glucose (DMG), minimum morning glucose (MMG), average glucose for a predetermined time period, daily minimum hourly average glucose (DMHAG), or a combination thereof. In some aspects, for example, the minimum glucose metric can include DMHAG.

[0052] In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than a predetermined percentage of an expected change in the minimum glucose metric. In some aspects, for example, the change in the minimum glucose metric can be less than 50% of the expected change in the minimum glucose metric. In some aspects, the expected change in the minimum glucose metric is based on one or more user metrics. In some aspects, the one or more user metrics can include weight, BMI, age, insulin sensitivity factor (ISF), total daily dose (TDD), a ratio of TDD to weight, A1C level, heart rate, blood pressure, or a combination thereof. In some aspects, for example, the one or more user metrics can include ISF. In some aspects, the expected change in the minimum glucose metric can be based on historical glucose data for the user. In some aspects, the expected change in the minimum glucose metric can be proportional to a change between the first dose and the second dose.

[0053] In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than a predetermined change in the glucose level. In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than 5 mg / dL. In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than 15 mg / dL. In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than 10 mg / dL. In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than 3 mg / dL. In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than 1 mg / dL. In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than 0.1 mg / dL. In some aspects, the predetermined metric can include a change in the minimum glucose metric that is less than a range of about 0.1 mg / dL to about 15 mg / dL.

[0054] In some aspects, the predetermined metric can include determining a change in the minimum glucose metric based on a statistical method. In some aspects, the predetermined metric can include a statistical test of the minimum glucose metric that does not support a hypothesis that the minimum glucose metric has changed. In some aspects, the statistical test can include an insulin sensitivity test (IST), an insulin tolerance test (ITT), an oral glucose tolerance test (OGTT), a fasting plasma glucose (FPG) test, a random plasma glucose test, or a combination thereof.

[0055] In some aspects, the method can further include prompting the user to confirm administration of the second dose. In some aspects, the method can further include resuming titration if the user confirms administration of the second dose. In some aspects, the method can further include recommending a third dose based on titrating the second dose if the user does not confirm administration of the second dose.

[0056] In some aspects, the method can further include recommending a limit on the change in the amount of the basal insulin dose if the minimum glucose metric does not change after titrating the recommended dose for a predetermined period of time. In some aspects, limiting the change in the amount of the dose can include limiting the change in the amount of the dose to no more than a predetermined percentage of the previous amount of the dose, e.g., no more than 1%, 2%, 5%, 10%, etc. In some aspects, limiting the change in the amount of the dose can include stopping any change in the amount of the dose. In some aspects, the predetermined period of time can include at least 3 days.

[0057] In some aspects, the method can further include stopping upward titration of the basal insulin if the minimum glucose metric does not decrease after titrating the recommended dose for a predetermined period of time. In some aspects, the method can further include stopping downward titration of the basal insulin if the minimum glucose metric does not increase after titrating the recommended dose for a predetermined period of time.

[0058] In some aspects, the method can further include activating a blind mode such that glucose data is not displayed to the user.

[0059] In some aspects, the method can further include initiating a counter configured to monitor a number of titration cycles if the change in the minimum glucose metric is outside of a predetermined metric. In some aspects, the method can further include stopping titration of the basal insulin if the change in the minimum glucose metric remains outside of the predetermined metric after a predetermined number of titration cycles of increasing or decreasing the dose of the basal insulin.

[0060] In some aspects, the method can further include receiving basal insulin dose administration time data. In some aspects, titrating the recommended dose is not based on the basal insulin dose amount data.

[0061] In some aspects, the method can further include outputting a prompt to the user to confirm that the user followed the recommended dose. In some aspects, the method can further include outputting a prompt to the user to seek guidance from a healthcare professional. In some aspects, the method can further include outputting a quiz to the user to verify that the user followed the recommended dose.

[0062] In some aspects, a method of detecting non-compliance with a dose recommendation can include receiving glucose data of a user over a first time period from an in vivo glucose monitoring device. In some aspects, the method can further include determining a first lowest glucose metric for the first time period. In some aspects, the method can further include providing a dose recommendation to the user based on the glucose data over the first time period. In some aspects, the method can further include receiving glucose data of the user over a second time period after the dose recommendation. In some aspects, the method can further include determining a second lowest glucose metric for the second time period. In some aspects, the method can further include determining non-compliance with the dose recommendation based on a comparison of the first lowest glucose metric and the second lowest glucose metric. In some aspects, the method can further include outputting an indication of non-compliance.

[0063] In some aspects, the first and second lowest glucose metrics can include daily minimum hourly average glucose (DMHAG).

[0064] In some aspects, the comparison can include a change between the first and second lowest glucose metrics. In some aspects, determining non-compliance includes comparing the change between the first lowest glucose metric and the second lowest glucose metric to a predetermined percentage change threshold. In some aspects, determining non-compliance includes comparing the change between the first lowest glucose metric and the second lowest glucose metric to a predetermined change in glucose level.

[0065] In some aspects, the comparison can include a direction of the first and second lowest glucose metrics. In some aspects, the direction is inversely proportional to the dose recommendation. In some aspects, for example, non-compliance of the user can be determined by a direction (e.g., trend) of the first and second lowest glucose metrics increasing (rather than decreasing) in response to the dose recommendation. In some aspects, for example, non-compliance of the user can be determined by a direction (e.g., trend) of the first and second lowest glucose metrics decreasing (rather than increasing) in response to the dose recommendation.

[0066] Embodiments of any of the techniques described above can include systems, methods, processes, devices, and / or apparatuses. Details of one or more implementations are set forth in the accompanying drawings and description below. Other features will be apparent from the description and drawings, and from the claims.

[0067] Further features and exemplary aspects of the disclosure are described below with reference to the accompanying drawings, and various aspects are set forth in the description and claims. Note that the aspects are not limited to the specific aspects described herein. These aspects are presented only to provide illustrative examples of the aspects. Additional aspects will be apparent to those of ordinary skill in the art based on the teachings herein. BRIEF DESCRIPTION OF DRAWINGS

[0068] The accompanying drawings, which are incorporated herein and form part of the specification, illustrate the aspects and, together with this specification, serve to further explain the principles of the aspects and enable those skilled in the art(s) to make and use the aspects.

[0069] FIG. 1 An example of treatment used to guide PWD in managing their insulin therapy is shown.

[0070] FIG. 2 It shows FIG. 1 An example of a pre-training survey for processing.

[0071] FIG. 3 It shows that it can be used FIG. 1 An example of a patient messaging profile created during the processing.

[0072] FIG. 4 An example of a system for diabetes management is shown.

[0073] FIG. 5 An example of a system for guiding PWD in managing their insulin therapy is shown.

[0074] FIG. 6 It shows that it can be made by FIG. 5 An example of the state graph used by the insight generation engine.

[0075] FIG. 7 It schematically shows that it can be made by FIG. 5 The insight generation engine prioritizes the insights it generates.

[0076] FIG. 8A-FIG. 8B It shows that it can be made by FIG. 5 An example of the processing performed by the insight generation engine.

[0077] FIG. 9 An example of multimodal insight triggering is shown.

[0078] FIG. 10 An example of a multimodal insight satisfaction assessment is shown.

[0079] FIG. 11 Examples of actions related to insight are shown.

[0080] FIG. 12 An example of a computing device that can be used to implement the techniques described herein is shown.

[0081] FIG. 13 This is a schematic diagram of a therapy management system based on an exemplary aspect.

[0082] FIG. 14A It is an illustrative control diagram for a therapeutic escalation pathway based on exemplary aspects.

[0083] FIG. 14B is a schematic therapy assessment for a therapy escalation pathway according to exemplary aspects.

[0084] FIG. 14C is a schematic control chart for a therapy escalation pathway according to exemplary aspects.

[0085] FIG. 15 is a schematic control chart for a first dosing regimen according to exemplary aspects.

[0086] FIG. 16 is a schematic control chart for a second dosing regimen according to exemplary aspects.

[0087] FIG. 17 is a schematic control chart for a third dosing regimen according to exemplary aspects.

[0088] FIG. 18 is a schematic control chart for a fourth dosing regimen according to exemplary aspects.

[0089] FIG. 19A is a schematic illustration of a basal state according to exemplary aspects.

[0090] FIG. 19B is a schematic illustration of a meal state according to exemplary aspects.

[0091] FIG. 19C is a schematic illustration of a correction insulin sensitivity factor (ISF) state according to exemplary aspects.

[0092] FIG. 20 illustrates a flowchart for therapy escalation for a diabetes patient according to exemplary aspects.

[0093] FIG. 21 illustrates a flowchart for detecting non-adherence to a dose recommendation according to exemplary aspects.

[0094] FIG. 22 illustrates a flowchart for detecting non-adherence to a dose recommendation according to exemplary aspects.

[0095] FIG. 23 is a schematic illustration of a computing device that can be used to implement the operations described herein according to exemplary aspects.

[0096] The features and example aspects of the present disclosure will become more apparent from the detailed description set forth below and from the drawings, in which like reference numerals identify corresponding elements throughout the several views. In the drawings, like reference numerals identify identical, similar, or corresponding elements throughout the several views. In addition, generally, the left-most digit(s) of the reference numerals identify the drawings in which the reference numerals first appear. The drawings provided herein are not to be construed as being to scale with one another. The drawings are schematic illustrations of idealized embodiments of the present disclosure. DETAILED DESCRIPTION

[0097] Described herein are examples of systems and techniques that use reinforcement learning as a way to apply machine learning techniques to the management of PWDs' insulin therapy and benefit from it. Generally, reinforcement learning can be applied to aspects of the insulin therapy management process where algorithms do not have pre-specified actions to perform, so that indirect feedback can be considered when planning action(s). Systems according to the present disclosure better communicate with PWDs during the course of insulin therapy because it broadly considers the PWD's current physiological and psychological state (sometimes also referred to as considering the PWD's complete state).

[0098] Provided herein are system, device, apparatus, method, and / or computer program product aspects, and / or combinations and sub-combinations thereof, for a therapy escalation pathway to manage diabetes and maintain normal glycemia, such as by maintaining one or more glucose metrics within a target level or target range.

[0099] A system as described below can continuously monitor a user's glucose level, determine one or more glucose metrics, implement one or more dosing regimens, confirm user adherence to therapy, determine whether any basal insulin excess exists in the therapy, monitor the therapy over discrete time periods, and adjust and / or escalate the therapy in response to one or more dosing regimens according to one or more measured user metrics.

[0100] The present specification discloses one or more aspects that incorporate features of the present disclosure.

[0101] The described aspect(s) and the description herein of “one aspect”, “an aspect”, “an example aspect”, “an exemplary aspect” and the like refers to a particular described aspect, but not necessarily to the only aspect having the specific feature(s) described, and for purposes of the description here, the use of “the” and “of the” describes only one of a possible myriad of aspects, but is not used to exclude individual aspects from the scope of the description. Further, features illustrated for one aspect can apply to any other aspect, unless specifically noted otherwise.

[0102] The terms“about,”“substantially,” or“approximately” as used herein indicate that a value of a given quantity can vary based on a particular technology. Based on a particular technology, the terms“about,”“substantially,” or“approximately” can indicate that a value of a given quantity varies within, for example, 1-15% of the value (e.g., ±1%, ±2%, ±5%, ±10%, or ±15% of the value). In some aspects, the terms“substantially” and“about” as used herein are used to describe and account for small fluctuations, such as those resulting from variations in processing. For example, these terms can refer to less than or equal to ±5%, such as less than or equal to ±2%, such as less than or equal to ±1%, such as less than or equal to ±0.5%, such as less than or equal to ±0.2%, such as less than or equal to ±0.1%, such as less than or equal to ±0.05%. Also, the indefinite articles“a” and“an,” as used herein in a context involving at least one, can refer to“at least one” and / or“one or more.”

[0103] Values (including the endpoints of ranges) expressed as approximations can be expressed as a quantity plus or minus a value associated with the quantity. For example, the expression“about 100” can mean the quantity 100 plus or minus 10%. Values expressed as a range of values can be expressed as an approximation by using the term“about” with respect to one or both of the values and / or using language such as“between” or“from.” For example, the expression“between 100 and 200” can mean from 100 to 200, or from 100 to 200 plus or minus 10%. Similarly, the expression“from 100 to 200” can mean from 100 to 200, or from 100 to 200 plus or minus 10%.

[0104] Aspects of the present disclosure can be implemented in hardware, firmware, software, or any combination thereof. Aspects of the present disclosure can also be implemented as instructions stored on a machine-readable medium, which can be read and executed by one or more processors. A machine-readable medium can include any mechanism for storing or transmitting information in a form readable by a machine (e.g., a computing device). For example, a machine-readable medium can include read only memory (ROM); random access memory (RAM); magnetic disk storage media; optical storage media; flash memory devices; electrical, optical, acoustical or other form of propagated signals (e.g., carrier waves, infrared signals, digital signals, etc.), and others. Further, firmware, software, routines, and / or instructions can be described herein as performing certain actions. However, it should be appreciated that such descriptions are merely for convenience and that such actions in fact result from execution of the firmware, software, routines, instructions, etc. by the computing device, processor, controller, or other device under the control of the firmware, software, routines, instructions, etc.

[0105] As used herein, the term“basal insulin overshoot” indicates that basal insulin is titrated beyond an appropriate dose in an attempt to achieve a glucose target. In some aspects, an appropriate dose refers to a dose that allows a user to reach a glucose target.

[0106] As used herein, the terms “long-acting (LA) insulin” and “basal insulin” are interchangeable terms and indicate a dose of insulin associated with non-meal times and nighttime.

[0107] As used herein, the terms “rapid-acting (RA) insulin,” “mealtime insulin,” and “bolus insulin” are interchangeable terms and indicate a dose of insulin associated with a meal.

[0108] As used herein, the term “therapy intervention” can refer to initiating or modifying a therapy regimen or recommending initiation or modification of therapy (e.g., adjusting a dose amount, adjusting a type of dose, etc.) over a period of time (e.g., adjusted daily and / or weekly).

[0109] The term “duration of intervention” can refer to a time between therapy interventions. For example, the duration of intervention can be a predetermined period of time (e.g., every day, every two days, every week, every two weeks, etc.).

[0110] The term “monitoring phase” can refer to monitoring one or more user adherence metrics of a current therapy over a predetermined period of time (e.g., every day, every two days, every three days, etc.).

[0111] As used herein, the term “titration dose” can refer to determining a maintenance or adjustment of a dose amount (e.g., an increase or decrease) to improve glucose control.

[0112] As used herein, the term “titration up” refers to increasing a dose amount.

[0113] As used herein, the term “titration down” refers to decreasing a dose amount.

[0114] As used herein, the term “titration cycle” can refer to a cycle of recommending a first dose amount, calculating one or more glucose metrics, and maintaining or adjusting the administered first dose amount based on the one or more glucose metrics.

[0115] As used herein, the term “adding a second therapy” can refer to a pharmaceutical therapy regimen including one or more therapies, and a second therapy can be added or incorporated into the pharmaceutical therapy regimen such that the pharmaceutical therapy regimen includes the first and second therapies (e.g., a basal insulin therapy and a GLP-1 therapy, a basal insulin therapy and a mealtime insulin therapy, etc.).

[0116] As used herein, the term “inverse” can refer to two quantities whose behaviors are opposite, such that a decrease in a first quantity increases relative to a second quantity, and vice versa. For example, a direction (e.g., a trend) of a first and second lowest glucose metric decreases in response to an increase in a dose recommendation, and vice versa.

[0117] Exemplary management processes for insulin therapy

[0118] As discussed above, reinforcement learning can be applied to aspects of insulin therapy management processing where the algorithm does not have pre-specified actions to perform, and thus can consider indirect feedback when planning action(s). The system according to the present disclosure better communicates with the PWD during the course of insulin therapy because it broadly considers the PWD’s current physiological and psychological state (sometimes also referred to as considering the PWD’s full state).

[0119] In some implementations, a reinforcement learning driven insight engine can be provided that seeks to guide the PWD through their insulin injection journey in an optimal manner. The insight engine can use PWD preferences, guidance from healthcare providers, physiological data, behavioral data, medication dosing data, and measures of efficacy for the PWD and other similar PWDs to select coaching messages and therapy adjustments. For example, coaching messages can instruct the PWD how to change their behavior to benefit their diabetes journey. As another example, therapy adjustments can include any change to insulin therapy such as improving glucose performance (e.g., changing the type of insulin, changing the timing of insulin injections, changing the psychological model of dosing for one type of insulin (e.g., long-acting insulin), changing the dose of insulin (e.g., long-acting or fast-acting insulin), or changing the correction table for insulin. The primary goal of the insight engine can be to understand each patient and determine how best to help them achieve control of their diabetes. To meet the PWD’s goals in their treatment journey, the system can leverage different methods to assess their current state and provide clinically relevant recommendations, whether they are initiating a new therapy, optimizing an existing therapy, or driving recommendations for changes to therapy. The insight engine can use generalized reinforcement learning to guide the PWD to achieve better therapy, including but not limited to, with respect to insulin settings, measuring blood glucose levels, making injections, and / or controlling the timing of injections. System components can include, but are not limited to, a blood glucose meter or monitor, an insulin pump, a smart cap on an injection pen, an insulin therapy application, and / or a cloud infrastructure.

[0120] The present disclosure can provide a management process for insulin therapy that includes an initial interaction with the PWD, asking the PWD and / or healthcare provider questions to obtain preferences, training the PWD, subjecting the PWD to a high-touch interaction phase in which insulin settings for the PWD can be quickly adjusted based on standard guidelines, and finally an ongoing phase that attempts to optimize insulin therapy using reinforcement learning. The high-touch interaction phase and one or more other initial phases can prepare the way for later optimization. In this management process, the system or technology can take into account the overall situation of the PWD's general state, not just specific measurements. From this state, the system / technology can probabilistically determine the action(s) to perform next (e.g., increase, decrease, or maintain a dose, and / or ask another recommendation or perform coaching). After performing the action(s), the system / technology can observe one or more aspects about the PWD to assess whether they took the correct action(s), thereby obtaining feedback as part of reinforcement learning. In the future, if / when a similar situation occurs, the system / technology can take this feedback into account. For example, the feedback can make it more likely (or less likely) to perform the same action(s) again.

[0121] Insulin delivery devices include, but are not limited to, insulin injection pens, insulin inhalers, insulin pumps, and insulin syringes. Improper administration of insulin, whether due to human error, malfunction of the insulin pen, missed doses, repeated dosing, or incorrect dosing, is always a cause for concern. The methods, devices, and systems provided herein are described with respect to delivery of insulin, collection of blood glucose data, and / or treatment of diabetes. Moreover, the methods, devices, and systems provided herein can be applicable to delivery of other medications, collection of other analyte data, and / or treatment of other diseases. The methods, devices, and systems provided herein are described by way of exemplifying features and functionality of a number of illustrative embodiments. Other implementations are possible.

[0122] Some examples herein relate to insulin injection pens. Insulin injection pens include at least one container holding insulin (e.g., an insulin cartridge), a dial or other mechanism for specifying a dose, and a pen needle for percutaneously delivering insulin into the tissue or vasculature of a person with diabetes. In reusable insulin injection pens, the insulin container (e.g., cartridge) is replaceable or refillable. Pre-filled insulin injection pens are intended for use during a limited time period. The dose specifying mechanism can include a rotatable wheel coupled to mechanical and / or electronic components for limiting the amount of insulin administered to within a volume of a specified dose (e.g., in terms of number of units of insulin). The dose specifying mechanism can have a mechanical and / or electronic display reflecting the current setting of the mechanism. The pen needle can be permanently attached to the housing of the insulin injection pen (e.g., like a disposable pen), or can be removable (e.g., so that a new needle can be installed when needed). For example, a replaceable pen needle can include a hollow needle fixed to a fitting that is configured for removably attaching to one end of an insulin injection pen.

[0123] Some examples herein relate to mobile communication devices. As used herein, a mobile communication device includes, but is not limited to, a mobile phone, a smartphone, a wearable electronic device (e.g., a smartwatch), a tablet computer, a laptop computer, a portable computer, and similar devices. A mobile communication device includes one or more processors, a non-transitory storage device (e.g., a memory and / or a hard drive) holding executable instructions for operating the mobile communication device, a wireless communication component, and one or more input and / or output devices (e.g., a touchscreen, a display, or a keyboard). A mobile communication device can operate according to one or more applications stored locally on the mobile communication device, remotely stored (e.g., when using cloud computing), or a combination thereof. A mobile communication device can execute at least one operating system in order to perform functions and services.

[0124] Some examples herein relate to blood glucose meters (BGMs). A BGM is an electronic device configured to receive a sample (e.g., a blood sample) from a PWD and analyze the sample to estimate the blood glucose level of a person with diabetes. A BGM can be configured to have a new test strip partially inserted inside the BGM for each sample, and then a person will drop a drop of blood onto the end of the test strip that extends out of the BGM. The BGM performs a test on the drop of blood through the test strip.

[0125] Some examples herein relate to continuous glucose monitors (CGMs). A CGM is an electronic device configured to take readings of glucose values at regular intervals or continuously in order to estimate the blood glucose level of a PWD. A CGM can have an electrode placed under the skin that transmits its output to a receiver (e.g., via a transmitter), such as a handheld device. Another type of CGM can be fully implantable under the skin of a PWD. Yet another type of CGM can be non-invasive and avoid pricking the skin, such as by analyzing the breath of a PWD or by shining light onto the skin of a PWD. Some CGMs determine blood glucose values periodically (e.g., after a certain number of seconds or minutes) and output information automatically or upon receiving a prompt. A CGM can include wireless communication components for one or more types of signaling, including but not limited to near field communication (NFC) and / or Bluetooth communication.

[0126] In some embodiments, the systems, devices, and / or methods provided herein can recommend insulin doses (e.g., doses of long-acting and / or rapid-acting insulin) using any suitable technique. In some embodiments, the recommended insulin doses can be based on blood glucose data (e.g., current estimated glucose values (EGVs) from a CGM, a flash glucose monitor, a blood glucose meter, or any other sensor, blood glucose trend data, etc.), insulin administration data (bolus dose amounts of rapid-acting insulin, doses of long-acting insulin, dosing times, calculations of insulin on board (IOB) and / or active insulin, etc.), meal data (meal times, user-estimated carbohydrates, user-estimated meal categories, user-estimated effects of meals on blood glucose, user meal history, user meal trends, etc.), and / or one or more insulin delivery parameters (e.g., total daily doses of basal or long-acting insulin, carbohydrate-to-insulin ratios (CRs), insulin sensitivity factors (ISFs), etc.). In some embodiments, the methods, devices, and systems provided herein can adjust insulin delivery parameters over time based on glucose data and / or insulin administration data.

[0127] Some examples herein relate to long-acting insulin and fast-acting insulin, or in some cases more generally to first and second types of insulin. Insulin for treatment is often synthetic human insulin. Also, different insulins are characterized by the speed at which they typically begin to take effect in a person with diabetes after administration, and / or the time for which they typically remain active in a person with diabetes. Fast-acting insulin can be used for dosing in response to a meal or to correct high blood glucose. There is more than one type of insulin that can be considered fast-acting insulin. Many, but not necessarily all, fast-acting insulins begin to take effect within about an hour after administration. Similarly, there is more than one type of insulin that can be considered long-acting insulin, and many, but not necessarily all, long-acting insulins begin to take effect about an hour or more after administration. Long-acting insulin is often referred to as basal insulin (e.g., insulin used to support basal metabolic needs). Generally, long-acting insulin has a longer active time (i.e., length of time in which it remains active in a person with diabetes after administration) than fast-acting insulin. Thus, long-acting insulin is an example of a type of insulin that has a longer active time than a type of insulin such as fast-acting insulin.

[0128] FIG. 1 An example of a process 100 for guiding a PWD in managing their insulin therapy is shown. The process 100 can be used in combination with one or more other examples described elsewhere herein. The process 100 is shown schematically as a number of blocks. In some implementations, more or fewer operations than shown can be performed.

[0129] The pre-training survey phase 102 involves collecting data from and / or about the PWD. The data can be collected by administering one or more surveys to the PWD. For example, the survey can be administered to the person and / or presented on a display, or using a speaker of a computer system (e.g., on a mobile electronic device). The survey can ask the PWD about goals in managing insulin therapy, as well as other aspects of the PWD’s personal or lifestyle. For example, the survey can explore how to communicate with the PWD during insulin therapy. The pre-training survey phase 102 can collect information from a healthcare provider (HCP) of the PWD. For example, the HCP can be a doctor, a nurse, other medical professional, a family member, or other caregiver. The information collected from the HCP can include information about the health of the PWD or how to treat the PWD. For example, the HCP can recommend elevating the health of the PWD to an optimal glycemic level or modifying one or more aspects of the process 100. As another example, the pre-training survey phase 102 can attempt to determine whether to apply a generic initiation regimen of insulin therapy to the PWD from the perspective of therapy adequacy or message receptivity.

[0130] The process 100 can include a user training phase 104, which can be directed to the PWD and / or the PWD's HCP. In some implementations, the user training phase 104 provides education about diabetes and / or insulin therapy and about other aspects of the process 100. The user training phase 104 can be performed to a person and / or presented on a display of a computer system (e.g., on a mobile electronic device) or using a speaker. The format and / or content of the user training phase 104 can be customized using data or other information collected in the pre-training survey phase 102.

[0131] The process 100 can include a high-touch interaction phase 106. For example, "high touch" can mean that the high-touch interaction phase 106 involves relatively intensive, frequent, or otherwise substantial interaction with the PWD. In some implementations, the high-touch interaction phase 106 can be characterized as an initial phase, as it precedes subsequent phases (described below) that involve less intensive / frequent / substantial interaction with the PWD. Information collected in the pre-training survey phase 102 can change the content of the high-touch interaction phase 106 or how the high-touch interaction phase 106 proceeds. For example, based on the collected information, the process 100 can identify other PWDs with similar medical and / or physiological characteristics to the current PWD and use their settings or other process configurations as a starting point for the PWD. As another example, in the absence of other PWDs with similar characteristics, the process 100 can use data obtained from / for the PWD as an initial setting.

[0132] In some implementations, some or all aspects of the high-touch interaction phase 106 can be characterized as a titration with respect to the PWD and the PWD's insulin therapy. The titration can involve the use of a variety of insights (illustrated below), where the intended action to be performed is adjustment of the insulin therapy. Initially (e.g., within the high-touch interaction phase 106), the titration can involve a collection of high-touch interactions with the PWD within a relatively short period of time (e.g., days or weeks) after the start of the high-touch interaction phase 106, which is designed to establish appropriate data and create conditions under which the insulin therapy can be quickly adjusted. The insight engine (illustrated below) can be designed to operate primarily based on available data, but the high-touch interaction phase 106 can be an exception. More specifically, in the high-touch interaction phase 106, the PWD can be asked to record meals, times of waking, or whether a dose was missed. The process 100 can also or instead augment these observations using other sources of information. For example, a wearable device can provide information for data collection.

[0133] Interactions during the high-touch interaction phase 106 can include establishing one or more insulin dose settings through iterative adjustments to insulin therapy. For example, these can be viewed as initial settings for starting an optimization procedure, where the settings can be modified one or more times. This can be characterized as part of titration of insulin dose amounts with respect to the PWB. Insulin settings can include, but are not limited to, basal dose settings 108, meal dose settings 110, and correction dose settings 112.

[0134] In some implementations, basal dose settings 108 for insulin for the PWD can be established through the American Diabetes Association (ADA) guidelines, which are widely accepted and used as an example of a publicly available guideline with respect to insulin therapy. Another guideline example is the American Association of Clinical Endocrinologists (AACE) recommendations. The guidelines can be applied through direct utilization of blood glucose values from a blood glucose meter to understand the PWD's fasting plasma glucose (FPG) level. The guidelines can be applied through interpretation of CGM values to ease the burden on the user at this critical juncture of starting a new therapy. In some implementations, the CGM can be used to assess the PWD's minimum morning glucose (MMG). For example, the MMG can be defined as the lowest glucose value between 4:00 AM and 30 minutes before the first activity of the day. These values can be processed in one or more ways. For example, highs due to nighttime lows (via eating something, etc.) can be excluded. As another example, morning highs due to nighttime lows causing a morning rebound can be excluded. As another example, adjustments can be made for non-standard wake times (e.g., for shift workers). A basic, consistent, and flexible initiation framework can be created that is independent of the given glucose measurement tool. According to the guideline construct, the PWD initially can use a pre-defined number of units or a specific amount of dose as indicated by the HCP before bed each day. The system can recommend increasing by a specific number of units or a certain percentage at regular intervals (e.g., once every fixed number of days) until the FPG and / or MMG falls within the target range. Other adjustments can also be made. For example, the system can assess basal insulin excess and can consider adjunct therapies (e.g., if the basal dose exceeds a pre-defined number of units / kg / day, the bedtime-to-morning (BeAM) glucose difference and / or the post-prandial-to-pre-prandial difference is elevated, hypoglycemia (aware or unaware), and / or high variability (e.g., coefficient of variation is higher than a pre-specified number)).

[0135] In some embodiments, meal bolus settings 110 of insulin for the PWD can be established using a stepwise approach, focusing on one meal at a time. Meal bolus settings 110 can take into account average measurements of blood glucose levels (e.g., A1C testing), basal dose settings 108, FPG, and / or MMG. Pre-meal glucose levels can also be taken into account. The system can recommend increasing the dose of insulin by a certain number of units or a certain percentage at regular intervals (e.g., once every fixed number of days) until the pre-meal glucose level for the next meal falls within the target range. If hypoglycemia occurs, then the system can review the blood glucose pattern and decrease the dose of insulin by a predefined amount.

[0136] In some embodiments, correction bolus settings 112 of insulin for the PWD can be established to compensate for average glucose levels (e.g., A1C) not being within a target range. The system can take into account insulin sensitivity factors for the PWD.

[0137] As mentioned, some or all of the settings in the high-touch interaction phase 106 (e.g., basal dose settings 108, meal bolus settings 110, and / or correction bolus settings 112) can be established based on publicly available guidelines for insulin therapy. This can be done after the PWD’s HCP confirms that blood glucose targets do not need to be individualized for the PWD. Such guidelines can specify one or more target ranges for A1C (e.g., taking into account that the PWD is not pregnant and does not have significant hypoglycemia), can use dynamic glucose profiles and / or glucose management indicators to assess time within target ranges, the system can accept lower than target A1C levels based on HCP judgment and PWD preferences, while monitoring for significant hypoglycemia or other adverse reactions, the system can apply less stringent targets (e.g., for A1C) when the harms of treatment outweigh the benefits. While the system can set blood glucose targets based on individual criteria, primary clinical targets can be defined as default values. For example, this can include A1C levels, pre-meal capillary plasma glucose levels, and / or peak post-meal capillary plasma glucose levels. For individual patients, more stringent or more lenient blood glucose targets can be more appropriate. Blood glucose targets can be assessed using CGM.

[0138] The duration of the high-touch interaction phase 106 can be defined in any of a variety of ways. In some embodiments, a target-based duration (e.g., a result-based duration) can be used. The system can determine that it has enough interaction with the PWD and data about the PWD such that the dose is the correct dose. For example, the dose can be close enough to the correct level that an interaction with less reliance on reinforcement learning can be initiated. The system’s assessment based on targets can take into account that blood glucose is maintained within targets for at least a certain percentage of time, and that the PWD is taking insulin as recommended. In some embodiments, a predetermined length of time (e.g., a fixed number of days) can be used.

[0139] Processing 100 may include an ongoing phase 114. The ongoing phase 114 includes collecting performance metrics of the PWD, applying reinforcement learning to the performance metrics, and automatically executing actions related to the PWD based on the reinforcement learning. The ongoing phase 114 may be performed based on survey information from the pre-training survey phase 102. For example, specific insulin therapy recommendations and / or the way communication with the PWD may influence whether to continue monitoring diabetes and observing new progression, whether to intensively manage diabetes, whether to minimize the cost and expense of the PWD, whether to maximize the health benefits of the PWD, and how to communicate with the PWD. In the ongoing phase 114, the system may look for behavioral and insulin therapy settings, as well as one or more of the most important things to tell the PWD. For example, the message could be that the PWD is not taking enough doses, rather than recommending how many doses should be taken each time. As another example, the PWD may be advised to take medication earlier or later. In some implementations, one or more insights may be evaluated and result in the execution of at least one action. Actions may include communicating with the PWD (or HCP) and / or changing settings regarding insulin therapy. What messages to generate for the PWD may be selected based on the PWD's preferences. After taking action on an insight, it can be monitored for a period of time. If the situation improves during this period (one or more), PWD can be notified and monitoring can be terminated. If there is no improvement, other remedial measures can be considered.

[0140] Ongoing phase 114 can include one or more ongoing therapy adjustment periods. The ongoing therapy adjustment period(s) can aim to accommodate the PWD's needs for the remainder of their course through multiple daily injection (MDI) insulin. The ongoing therapy adjustment period(s) can be structured around the review of performance metrics created to understand the PWD's behavior, physiology, and medication behavior. These metrics can be as up to date as possible, such as updating between once a day and once an hour. For example, the performance metrics are not intended to be real-time, and many observations look for recent trends, not sudden or real-time changes. The insight generation engine (illustrated below) can evaluate insights in order to determine which, if any, should be acted upon. The most important negative insights can be considered, and only the most relevant (i.e., likely to produce a positive outcome) insights can be presented to the PWD. The most positive celebrations can be considered. An insight is triggered and action can be taken (e.g., coaching information can be sent to the PWD or therapy can be adjusted); then, an observation period can begin and a cooling period can begin. The observation period is the period in which the system can seek improvement. The criteria for understanding whether the insight has improved can but need not be the same as the one or more criteria that originally triggered the insight. The system can evaluate other criteria or use a specially constructed classification method to determine whether the PWD has improved based on the action taken. The cooling period can be used to ensure that the system does not act on recently taken insights. Insights related to safety (e.g., involving hypoglycemia) can be the highest priority, and the cooling time can be very short or even nonexistent. Insights can not coach safety issues, but can coach non-urgent issues that tend to reduce insulin based on observing excessive hypoglycemia despite normal or low levels of insulin delivery.

[0141] Both titration and coaching can be included in this framework. For example, titration has the action of primarily changing the insulin therapy settings. As another example, coaching primarily has the action of instructing the PWD how to improve their behavior (or, if the PWD has such issues, guiding them where they can get a sensor or insulin).

[0142] The action / coaching step can ask the PWD for help with the issue that the system is better able to coach or instruct. For example, the communication can say "We noticed that you are not wearing a sensor. Do you need help with (a) prescription, (b) affordable sensor, (c) dealing with sensor malfunction / sensor falling off, (d) sensor adhesive allergy, (d) I want to use a sensor temporarily." The answer can help formulate and adjust the coaching. "We noticed that you are not taking in <brand of long-acting insulin>? How can we help you (a) prescription (b) get affordable insulin." The PWD can make an input to the system (e.g., enter text using the device or choose between options, or by speaking into a microphone).

[0143] An observation period can be implemented when an action is taken. The observation period can facilitate assessing the effectiveness of the taken action in improving the PWD’s course (PWD’s state). By assessing the effectiveness of the messaging / action, the system can change the likelihood of taking a given action in the future. For example, a change in messaging preferences (e.g., PWD’s response to messages about cost) would make future messages more likely to focus on areas that were effective in the past. Similarly, threshold, cool-off period, and observation period parameters can be adapted in response to successful actions.

[0144] Parameter adaptation can also or instead be based on similar patients. In some implementations, a given user can not require multiple insulin titration events after an initial titration period. However, if similar patients have been successful with a titration action, the system can adapt parameters for all similar patients to take advantage of this learning. Other aspects besides titration can also or instead be learned from another patient’s data. This can include, but is not limited to, coaching messages and / or the balance between basal and bolus doses.

[0145] Ongoing phase 114 can include one or more adjustments to one or more of basal dose setting 108, meal dose setting 110, and / or correction dose setting 112. In some implementations, processing 100 can consider one or more of the following during ongoing phase 114 to recommend an increase, decrease, or no change to basal dose setting 108: mean glucose values during a specified time interval; time percentage of hypoglycemia and hyperglycemia during a specified time interval; calculated rate of glucose change during a specified time interval; hypoglycemia treatments that occurred during a specified time interval; or hypoglycemia occurrence time exceeding a specified time proportion. Reinforcement learning can define positive and / or negative rewards for one or more of the scenarios. The target state can be considered when recommending an increase, decrease, or no change to basal dose setting 108. For example, the target state can be defined based on a mean nighttime glucose level and no hypoglycemia or hyperglycemia. If a fixed percentage of days have hypoglycemia, the system can only consider hypoglycemic days to find a recommendation. If hypoglycemia is found to be caused by a dinner or late-night snack bolus, the system can ignore the hypoglycemia of that day in its assessment. In some implementations, a positive reward can be generated to the system if the PWD reaches the target state and / or the hypoglycemia, hyperglycemia, or mean glucose error change is less or no change.

[0146] In some embodiments, the process 100 can consider one or more of the following during the ongoing phase 114 to recommend an increase, decrease, or no change to the meal bolus setting 110: the lowest glucose level during the specified time interval; the target glucose level; the calculated rate of change of glucose during the specified time interval; the time to hypoglycemia exceeds a specified proportion of time; no hypoglycemia occurred. Reinforcement learning can define positive and / or negative rewards for one or more of the scenarios. A target state can be defined. For example, the target state can include postprandial error within a specified range and no hypoglycemia. In some embodiments, a positive reward can be generated to the system if the PWD reaches the target state and / or the rate of change and postprandial error change less or no change. In some embodiments, a negative reward can be generated to the system if the hypoglycemia level is between specified levels. The system can only consider hypoglycemic days to find the recommendation if more than a fixed percentage of days have hypoglycemia.

[0147] In some embodiments, the process 100 can consider one or more of the following during the ongoing phase 114 to recommend an increase, decrease, or no change to the correction bolus setting 112: the lowest glucose level during the specified time interval; the calculated rate of change of glucose during the specified time interval; or the glycemic risk index. Reinforcement learning can define positive and / or negative rewards for one or more of the scenarios. A target state can be defined. For example, the target state can include postprandial error within a specified range and no hypoglycemia. In some embodiments, a positive reward can be generated to the system if the PWD reaches the target state and / or the rate of change and postprandial error change less or no change. In some embodiments, a negative reward can be generated to the system if the hypoglycemia level is between specified levels. The system can only consider hypoglycemic days to find the recommendation if more than a fixed percentage of days have hypoglycemia.

[0148] During the ongoing phase 114, the system can use various statistical tools for evaluation. For example, a mean and / or median can be used for one or more of the measured entities.

[0149] In evaluating whether to adjust the primary therapy, one or more considerations can be taken into account. Considerations can be defined for escalation between therapies or less likely to regress. For example, this can involve escalation from basal only to MDI. As another example, this can involve escalation from using a particular medication (e.g., glucagon-like peptide-1) to using a medication with a basal dose. Considerations can be defined for sharing parameters (e.g., insulin sensitivity factor) between algorithms.

[0150] FIG. 2 It is shown FIG. 1An example of a pre-training investigation phase 102 of the process 100. The pre-training investigation phase 102 can include a user survey 200. For example, a user can input into the user survey 200 by typing and / or speaking. In some implementations, a plurality of questions are asked of the PWD to determine their views on current therapy. Answers to these questions can be used to determine a psychological profile of the PWD. The system can determine how fearful the PWD is of hypoglycemia and what drives their decisions about their therapy (e.g., cost, time, help from family, understanding of how to treat their diabetes, etc.). This can facilitate conducting one or more settings 202. For example, the settings 202 can include setting therapy goals, meal psychology models, defining contact frequency, defining messaging focus, and / or specifying aggressiveness of communication / actions.

[0151] The pre-training investigation phase 102 can include an HCP survey 204. The HCP survey 204 can ask the HCP to set therapy parameters. This can facilitate conducting one or more settings 206. For example, the settings 206 can include setting glucose goals, long-acting (LA) insulin type, rapid-acting (RA) insulin type, RA initial therapy settings, high-touch phase orders, and / or regular orders.

[0152] The pre-training investigation phase 102 can include defining therapy regimen 208. The therapy regimen 208 can include defining a set of parameters of the therapy. These parameters can include insulin dosing and psychology models, and / or therapy adjustment aggressiveness, target glucose, contact frequency, methods of communication, and coaching focus. This can facilitate creating one or more state action tables 210. For example, the state action tables 210 can define how performance metrics lead to actions / recommendations.

[0153] FIG. 3 An example of a patient messaging profile 300 that can be created in the process 100 is shown. FIG. 1 An example of a patient messaging profile 300 that can be created in the process 100 is shown. The patient messaging profile 300 can include one or more entries 304 measured against the scale 302. For example, the entries 304 can specify one or more of: saving money, long-term health, feeling better, risk of hypoglycemia, and / or feeling like a diabetes care provider (DCP) understands the PWD. Other approaches can be used.

[0154] Based on the assessment reflected by the patient messaging profile 300, recommended goals are provided to the PWD. The PWD can be able to change the recommended goals (e.g., within the application) as their situation changes over time. While the PWD's goals can not change the type or method of clinical insights, it can alter the messaging of how the clinical insights are presented. A variety of different goal statements can be used. Goals can be personalized based on duration of diabetes, age / life expectancy, comorbidities, known cardiovascular disease or late microvascular complications, hypoglycemic unconsciousness, and individual patient considerations. Examples of goals include, but are not limited to: improve my overall long-term health; reduce hypoglycemia and manage associated stress levels; feel better so as to be more energetic and more focused; learn more about my diabetes and get more personalized therapy; or reduce overall healthcare costs. Based on the glycemic goals, the system then leverages standard guidelines (e.g., from the ADA or AACE) to titrate during initiation of therapy, starting with basal therapy.

[0155] FIG. 4 An example of a system 400 for diabetes management is shown. The system 400 can be used in combination with one or more of the other examples described elsewhere herein, or can include aspects of those examples. Here, the system 400 includes an insulin injection pen 402. In some implementations, the insulin injection pen 402 is considered to be an insulin injection pen for a certain particular type of insulin, such as a rapid-acting insulin pen. For example, the insulin injection pen 402 is a Humalog™ pen, a Novolog™ pen, or an Apidra™ pen. Here, the system 400 includes an insulin injection pen 404. In some implementations, the insulin injection pen 404 is considered to be an insulin injection pen for some other type of insulin that has a longer active time than the particular type of insulin, such as a long-acting insulin pen. For example, the insulin injection pen 404 is a Lantus™ pen, a Levemir™ pen, a Toujeo™ pen, or a Tresiba™ pen. Here, the system 400 includes a glucose monitor 406 (e.g., a CGM) or another glucose sensor, and a remote user interface device 408. As shown, each of the insulin injection pens 402 and 404 includes a corresponding pen cap 410 and 412, respectively, that wirelessly communicates with other components of the system 400. As shown, the insulin injection pens 402 and 404 can include a dial 414 and 416, respectively, for a user to set a dose to be delivered, and a corresponding dose indicator window 418 and 420. In some implementations, one or more of the insulin injection pens 402 and / or 404 can include dose capture technology and / or wirelessly communicate with other components of the system 400. Additional details regarding possible insulin pens and / or insulin pen caps are illustrated below.

[0156] The glucose monitor 406 or another glucose sensor can include any suitable sensor device and / or monitoring system capable of providing data that can be used to estimate one or more blood glucose values. As shown, the glucose monitor 406 or another glucose sensor can be a sensor configured to wirelessly transmit blood glucose data. For example, the glucose monitor 406 or another glucose sensor can include an optical communication device, an infrared communication device, a wireless communication device such as an antenna and / or a chipset such as a Bluetooth device (e.g., Bluetooth Low Energy (BLE), classic Bluetooth, etc.), an NFC device, an 802.6 device (e.g., a Metropolitan Area Network (MAN), a Zigbee device, etc.), a WiFi device, a WiMax device, a Long Term Evolution (LTE) device, a cellular communication facility, and / or the like. The glucose monitor 406 or another glucose sensor can exchange data with a network and / or any other device or system described in the present disclosure. In some cases, the glucose monitor 406 or another glucose sensor can be interrogated by an NFC device by a user moving one or more components of the system 400 into proximity with the glucose monitor 406 or another glucose sensor in order to power the glucose monitor 406 or another glucose sensor and / or to transfer blood glucose data from the glucose monitor 406 or another glucose sensor to other components of the system 400. For example, the pen cap 410 and / or 412 can exchange data with (e.g., obtain glucose values from) the glucose monitor 406 or another glucose sensor by coming into proximity with it.

[0157] As shown, the remote user interface device 408 is a mobile electronic device (e.g., a smartphone) in some examples. In some implementations, any suitable remote user interface device can be used, including but not limited to a computer tablet, a smartphone, a wearable computing device, a smartwatch, a fitness tracker, a laptop computer, a desktop computer, a smart insulin pen (e.g., pen caps 410 and / or 412), and / or other appropriate computing devices. As shown in an example user interface of an example mobile application running on the depicted smartphone, the user interface can include a bolus calculator button 422, and optionally other buttons for the user to enter data or request recommendations. The example user interface can also or instead include display of blood glucose data (e.g., past, current, and / or predicted data). As shown, the user interface includes a graph 424 of historical data (e.g., data from the previous 30 minutes), a continuation 426 of the graph with projected data, a point indicator 428 showing a current (or most recent) estimated blood glucose value, and a display 430 of the current (or most recent) estimated blood glucose value. The user interface can also or instead include text 432 explaining the glucose data, text 434 providing a suggested action, and / or text 436. For example, the text 434 can provide an insulin, carbohydrate, or other therapy suggestion. For example, the text 436 can suggest that the user obtain blood glucose data. In some cases, the user interface can allow the user to tap on the glucose data or otherwise navigate in the mobile application to obtain more detailed or complete blood glucose data. In some implementations, the user interface can also or instead provide one or more insights that are beneficial to a person with diabetes. For example, the insights can convey a message such as: "You typically make a meal bolus between noon and 2 PM, but you did not make a bolus today and your blood glucose level is rising. Did you forget to make a bolus?"

[0158] The user interface can depict insulin data. In some cases, the user interface can indicate an amount of IOB 438, which can be for only a particular type of insulin (including but not limited to rapid-acting insulin). In some embodiments, IOB (sometimes referred to as active insulin) can be defined as the amount of insulin that has been delivered based on an estimated duration of insulin action and is still active in the human body. In some cases, IOB calculations can apply to both rapid-acting and long-acting insulin. In some cases, the user interface can display information 440 including but not limited to the time and / or dose of the most recent rapid-acting and / or long-acting insulin administration. In some cases, the user interface can allow the user to tap on the insulin data, or otherwise navigate to more detailed and / or complete insulin delivery data in the mobile application. In some cases, the user interface can superimpose blood glucose data and insulin delivery data in any suitable format, such as to graphically display the timing of blood glucose data with the timing of insulin delivery data.

[0159] In use, a user (e.g., a PWD and / or HCP) can use the system 400 to obtain recommendations regarding appropriate insulin doses. In the case of an upcoming need to deliver long-acting insulin, the text 434 can be changed to provide a recommended long-acting insulin dose. In some cases, the recommended dose can appear on the pen cap 410 and / or 412. In the case of a user wanting to deliver a bolus of rapid-acting insulin, the user can press the bolus calculator button 422 to enter the bolus calculator. Any suitable bolus calculator can be used in the systems, methods, and devices provided herein. For example, the bolus calculator can provide a user interface for the user to enter a meal announcement, such as correction only, small meal, normal meal, or large meal. After selecting a meal size, the user interface can provide a recommended bolus dose based on the amount of carbohydrates associated with the corresponding button and optionally blood glucose data. Additionally or alternatively, the dose capture pen cap for the insulin injection pen 402 and / or 404 can include a user interface that allows the user to obtain meal bolus recommendations for different types of meals (small, medium, large; breakfast, lunch, dinner; 10 grams of carbohydrates, 20 grams of carbohydrates, 45 grams of carbohydrates, etc.), and / or announce meal sizes including but not limited to small meal, medium meal, or large meal. In some embodiments, the text 432, 434, and / or 436 is presented elsewhere other than the user interface device 408. For example, presentation can be made on the pen cap 410 and / or 412.

[0160] Cap 410 and / or 412 can include at least one display. In some embodiments, cap 410 includes display 442. In some embodiments, cap 412 includes display 444. Display 442 and / or 444 can include any suitable type of display technology, including but not limited to dynamic electronic displays (e.g., light-emitting diode displays) or static electronic displays (e.g., electronic ink displays). Display 442 and / or 444 can present information to a user, including but not limited to any of the information outputs described elsewhere herein. For example, insulin dose recommendations and / or alerts or other messages can be presented.

[0161] Cap 410 and / or 412 can include at least one input control. In some embodiments, cap 410 includes button 446. In some embodiments, cap 412 includes button 448. Button 446 and / or 448 can include any suitable type of input technology, including but not limited to electronic switches. Button 446 and / or 448 can trigger the corresponding cap 410 and / or 412 to perform one or more operations, including but not limited to any of the operations described elsewhere herein.

[0162] Caps 410 and / or 412 can record and / or communicate one or more types of cap information. Cap information (e.g., information about when a cap is secured to and / or released from an injection pen) can include information about a current cap period (e.g., time since last capping), information about the duration of one or more uncappings (also referred to herein as “uncapping(s)”), and / or the timing of each uncapping and each capping (e.g., time of day or time elapsed since). For example, cap information can include data reflecting when a cap was put on an insulin injection pen, data reflecting when a cap was removed from an insulin injection pen, or both. In some embodiments, cap information can be presented to a user on a display of a cap. In some embodiments, cap information can be presented through a speaker in a cap. For example, in some embodiments, a cap can provide a timer clock counting from the time of the last capping of the injection pen. In some embodiments, a cap accessory can wirelessly communicate cap information to a remote computing device (e.g., user interface device 408 and / or a smartphone, tablet, etc.). In some embodiments, one or more accessories or smart delivery devices can detect other events associated with a drug delivery action and use that information in the manner of cap information described herein. For example, in some cases, an injection pen accessory can be secured to an injection pen such that it can detect mechanical movement of a dosing mechanism to determine the time of a drug dose (and, optionally but not necessarily, the amount of drug delivered at that time).

[0163] Pen cap information can be stored, displayed, and / or analyzed in combination with glucose data to determine user behavior, such as, for example, whether the user properly injected insulin at mealtime and / or corrected elevated blood glucose levels. In some embodiments, pen cap information can be presented in a graphical representation of user glucose data and presented to the user and / or medical professional. In some embodiments, blood glucose data for a period of time after each cap event can be evaluated to determine whether the user properly injected insulin for that cap event, e.g., proper dose, under dose, or over dose.

[0164] In some embodiments, a pen cap event can be ignored when other information indicates that a dose was not provided. For example, the event can be ignored when a change in dose selection (e.g., dial) of an insulin pen is not detected. In some embodiments, pen uncapping and recapping events can be ignored if the total uncapping time is less than a first threshold (e.g., 4-6 seconds). For example, the threshold can be determined by setting the threshold to be too short to inject but long enough to allow the user to check the pen tail to see if insulin remains or if a needle is attached to the pen. In some cases, blood glucose data can be combined to analyze the total uncapping time of a cap off event (time between uncapping event and subsequent recapping) to determine whether an injection was made during the cap off event. In some cases, if the total uncapping time exceeds a second threshold period of time (e.g., at least 15 minutes, at least 30 minutes, etc.), then blood glucose data and methods described herein for detecting meal timing can be used to determine an approximate time of injection.

[0165] Some or all components of system 400 can perform one or more operations or functions described elsewhere herein. In some implementations, system 400 can evaluate insights based on reinforcement learning and perform one or more actions for triggered insights. System 400 can determine insulin usage by detecting removal and / or replacement of pen caps 410 and / or 412. System 400 can detect the amount of insulin injected.

[0166] FIG. 5 An example of a system 500 for guiding a person with diabetes to manage their insulin therapy is shown. System 500 can be used in combination with one or more other examples described elsewhere herein, or can include aspects of those examples. System 500 is shown to include a number of separate components. The functionality of system 500 can be implemented using more or fewer components. System 500 includes an insight generation engine 502, which can use the methods described below with reference to FIGS. 6-8, to generate insights for a user. System 500 also includes a user interface 504, which can be used to present the insights to the user and / or a medical professional. System 500 also includes a data store 506, which can be used to store data used by system 500. FIG. 12The described components to implement. The insight generation engine 502 evaluates multiple insights based on reinforcement learning and decides for each insight whether to generate the insight. Each insight can be associated with performing one or more actions. For example, performing an action can include providing a message to the PWD and / or automatically changing an insulin therapy. The insights can be designed to cover the entire diabetes journey of the PWD. The insights can involve observations from data that should be acted on so that an action can be taken. The insights should be relevant enough that if the appropriate action is taken, the PWD’s MDI therapy can be significantly improved.

[0167] The insights can describe a suboptimal MDI therapy condition for which an action should be taken. The insight generation engine 502 can evaluate the insight conditions and determine which insights meet the triggering criteria. The triggered insights are followed by actions. To evaluate whether the actions were successful, the system 500 can monitor the PWD during an observation period. If the condition has improved, the system 500 can give the insight generation engine 502 a positive reward and update the parameters so that the insight generation engine 502 will be more likely to take this action in the future. If the condition fails to improve, the system 500 can give the insight generation engine 502 a negative reward and update the parameters so that the insight generation engine 502 will be less likely to take this action in the future. After the observation period, the system 500 can not allow the triggered insights for some time, this scenario can be referred to as a cooling period. This ensures that the system 500 does not overwhelm the PWD with too many actions. If the PWD’s status has not triggered an insight for a long time, the insight generation engine 502 can trigger a continuous reward to celebrate their achievement.

[0168] Insights can have multiple parameters in a repository 504 accessible to the insight generation engine 502. Parameters can include, but are not limited to: trigger conditions, such as a set of conditions based on performance metrics indicating that a coaching action should be taken, for example when the RA dose taken per time period is less than a fixed amount and the time the PWD stays within a blood glucose level range is less than a threshold; coaching actions, such as a set of possible actions that can be taken to help the PWD improve, for example a message or a therapy adjustment, perhaps presenting the PWD with a card with postprandial glucose when the PWD takes a RA dose; an observation window for measuring the effectiveness of the action so that the system 500 can adjust the method(s) over time, for example specifying an observation window of how long to observe before determining if an intervention was successful (some interventions can take longer to see in performance metric data, so this parameter can allow the system 500 to look longer before determining if an intervention was effective); a cool down period, to avoid telling the PWDs they are doing wrong over and over again, a cool down period can be defined to ensure that the insight is not triggered too frequently (for therapy adjustments, the system 500 can also limit the rate of adjustments, such as setting a cool down period of two weeks to ensure that the system 500 does not consider another therapy adjustment too soon), where two or more cool down periods can be chained (for example, triggering a particular insight can start a cool down for multiple insights); a celebration condition, such as a condition where the system 500 celebrates that no insight was triggered for a certain time period, for example by presenting a message “Congratulations, you have taken <long acting dose brand> on time every day for the past 60 days!” The repository 504 can reflect the status of the PWDs in terms of insights. Because the generation of insights is based on understanding the observations and cool down periods, the user status is considered before determining the insights.

[0169] The system 500 can use data about the PWDs, or otherwise related to the PWDs. The data can be provided in any of a variety of ways, such as through a data lake 506. In some implementations, the data lake 506 can be a centralized repository that stores, processes, and secures large amounts of structured, semi-structured, and / or unstructured data. For example, the data lake 506 can be provided by a cloud infrastructure that collects sensor readings, smart cap removals / replacements, user inputs, and / or other information about the PWDs. At least one computation 508 can be performed in the system 500 based on information from the data lake 506. In some implementations, a performance metric computation can be performed. The performance metrics can be computed at regular intervals, such as daily. Examples of performance metrics include, but are not limited to: the number of times a first injection pen (e.g., with long acting insulin) has a smart cap removed or replaced per day; the number of times a second injection pen (e.g., with fast acting insulin) has a smart cap removed or replaced per day; time in range; or postprandial glucose levels. The performance metrics can be stored in a performance metric database 510 accessible to the insight generation engine 502.

[0170] The system 500 can include a component 512 that presents output from the insight generation engine 502. In some implementations, the output of the component 512 is specific to the PWD. For example, the output can include coaching and / or titration output that is specific to the PWD.

[0171] FIG. 6 An example of a state diagram 600 that can be used by the insight generation engine 502 of FIG. 5 The state diagram 600 can also or instead be used in combination with one or more other examples described elsewhere herein. The state diagram 600 represents different states for at least one insight, each state is schematically represented as a circle, and arrows indicate possible state transitions. The state diagram 600 includes an untriggered state 602. This can be a default initial state for each insight, for example. A triggered state 604 indicates a determination that an insight has been triggered. For example, the insight is triggered based on an evaluation of a performance metric that indicates that a criterion for the insight is satisfied. An action state 606 indicates that at least one action associated with the triggered insight is performed in response to the trigger. An observation state 608 indicates that the triggered insight is being observed after being triggered. An observation period can be used to gather information to be used for reinforcement learning. A positive feedback reward state 610 indicates that the system is given positive feedback based on observation(s) related to the triggered insight. A negative feedback reward state 612 indicates that the system is given negative feedback based on observation(s) related to the triggered insight. During the observation state 608, the positive feedback reward state 610, and the negative feedback reward state 612, the triggered insight can not meet the condition for being triggered. The observation state 608 includes a time in which the effect of the action is observed after the insight is triggered. With some insights, the system can look for a performance metric to change it to an acceptable level. With other insights, the system can use a specialized machine learning method to determine the success of the action. As an example, a machine learning method can be used to determine updates of long-acting insulin that examines glucose patterns to confirm whether the insulin dosage has changed.

[0172] A cooling state 614 indicates a cooling period after the triggered insight is in the observation state 608. During the cooling state 614, the triggered insight can not meet the condition for being triggered. After the cooling state 614, the insight can again present the untriggered state 602. During the untriggered state 602, an evaluation can be made for each insight to assess whether the insight has not been triggered for at least a threshold amount of time. This period can be considered a situation in which the PWD is doing well or is desired because their diabetes is being managed and thus no such specific coaching or change in therapy is needed during this period. A consecutive state 616 indicates that the insight has not been triggered for at least a threshold amount of time, equivalent to consecutive success. For example, the consecutive state 616 can include presenting congratulatory information to the PWD.

[0173] FIG. 7 An example of a prioritization 700 of insights that can be performed by the insight generation engine 502 of FIG. 5 The prioritization 700 can also or instead be used in combination with one or more other examples described elsewhere herein. The prioritization 700 is performed with respect to insights 702-1 through 702-N, where N = 2, 3,.... Here, the PWD is referred to as user X. For example, insights that can impact the PWD’s life can be given the highest priority. As another example, insights that can impact the PWD’s health condition can be given a priority lower than insights that impact life (e.g., a second priority) and higher than at least one other insight. As another example, insights that are related to improving or optimizing the PWD’s diabetes care but do not impact the PWD’s life or health condition can be given a priority lower than insights that impact the health condition. Based on the prioritization 700, the insight 702-1 can be considered the highest priority insight. The insight 702-2 can be considered the next highest priority insight. The insight 702-N can be considered the lowest priority insight. Thus, multiple insights can be ranked in the prioritization 700 and evaluated in that order.

[0174] Insight competition can occur between insights. Insight competition can be a process by which the insight generation engine 502 of FIG. 5 determines the most relevant insights. That is, insights can have a natural order of precedence with respect to one another (e.g., as described above). However, given the current state and data of the PWD, multiple positive actions (e.g., celebrations and continuations) and negative actions (needed coaching or therapy adjustments) can be possible. Insight competition can select the correct insight(s) to present to the PWD. This can ensure a balance in the number and type of insights presented at a time.

[0175] FIG. 8A-FIG. 8B An example of a process 800 that can be performed by the insight generation engine of FIG. 5 is described elsewhere herein. More or fewer operations can be performed than shown. Two or more operations can be performed in a different order unless otherwise indicated. The process 800 can be repeatedly performed to evaluate respective insights of a plurality of insights in an order of prioritization. Here, the process 800 is labeled “highest priority insight” to indicate that the insight currently being evaluated is the highest priority insight that has not yet been evaluated in a previous iteration of the process 800.

[0176] In operation 802, a performance metric (e.g., FIG. 5The determination of whether the performance metrics in the performance metric database 510 provide sufficient data. The sufficiency criterion can vary depending on the insight. For example, if the system has not observed a sufficient number of lunch events of PWD in the past period to make an accurate assessment of PWD's lunchtime situation, then the insight about lunch can be skipped. If the result of operation 802 is "no," then the processing at operation 804 can proceed to the next insight in order of priority. For at least one insight, the lack or absence of performance metrics can meet the conditions for triggering the insight. For example, if the system has too little data, then a coaching message encouraging PWD to use the system more to obtain data on their diabetes management can be generated.

[0177] If the result of operation 802 is "yes", then operation 806 can determine whether the current insight is in an observation state (e.g., FIG. 6 The observation state (608) is determined. If the insight is not in the observation state, then the insight meets the conditions for triggering evaluation (but may not trigger depending on the situation). Accordingly, if the result of operation 806 is "no", then in operation 810, a determination can be made as to whether the performance metric triggers the insight. This determination may consider setting 812, such as one or more thresholds for the insight.

[0178] If an insight is not triggered by the current state of the PWD, then the PWD may be in a continuous state regarding the non-triggering of this particular insight. If the result of operation 810 is "No," then in operation 814, a determination can be made as to whether the insight has not been triggered within a specified time period. This determination may consider setting 816, such as one or more thresholds for continuous celebration. If the result of operation 814 is "No," then in operation 818, processing 800 can proceed to the next insight in priority order. If the result of operation 814 is "Yes," then in operation 820, continuous celebration can be performed. Continuous celebration can be performed based on setting 822, such as one or more styles or methods for coaching.

[0179] If the result of operation 810 is "yes", then in operation 824, it is possible to determine whether the current period is a cooldown period (e.g., FIG. 6determination can take into account settings 826, such as one or more thresholds for the insight. If the result of operation 824 is "yes," then at operation 828, process 800 can proceed to the next insight in order of priority. If the result of operation 824 is "no," then at operation 830, process 800 can perform one or more actions associated with the triggered insight. For example, the action can involve coaching and / or therapy adjustment. The action can take into account settings 832, such as one or more styles or methods for coaching. After performing the action(s), observation of the insight can begin at operation 834 (and process 800 can continue to evaluate the next insight in order of priority).

[0180] Returning now to operation 806, if the result of this determination is "yes," then at operation 836, a determination can be made as to whether one or more improvement criteria are met. The determination can take into account settings 838, such as one or more improvement thresholds for the insight. If the result of operation 836 is "no," then at operation 840, a determination can be made as to whether the end of the observation window has been reached. The determination can take into account settings 842, such as a definition of the observation window for the insight. If the result of operation 840 is "no," then observation of the insight can continue at operation 844 (and process 800 can continue to evaluate the next insight in order of priority). If the result of operation 840 is "yes," then at operation 846, the parameters of the reinforcement learning can be updated with negative feedback regarding the action(s) previously performed for this insight (and process 800 can continue to evaluate the next insight in order of priority).

[0181] If the result of operation 836 is "yes," then at operation 848, an improvement celebration can be performed. The improvement celebration can take into account settings 850, such as one or more styles or methods for coaching. After operation 848, at operation 852, the parameters of the reinforcement learning can be updated with positive feedback regarding the action(s) previously performed for this insight (and process 800 can continue to evaluate the next insight in order of priority).

[0182] FIG. 9An example of a multi-modal insight trigger 900 is shown. The multi-modal insight trigger 900 can be used in combination with one or more of the examples described elsewhere herein. The multi-modal insight trigger 900 here is related to an insight 902. For example, the insight 902 can be related to high morning glucose and whether to increase the dose of long-acting insulin. The insight 902 can be triggered based on two or more criteria 904 being satisfied. Each criterion can specify one or more situations that the performance metric can reflect. In some implementations, N criteria 904 are used, where N = 1, 2, 3,....

[0183] The multi-modal insight trigger 900 can be multi-faceted and can span more than one type of performance metric, including but not limited to behavioral, physiological, and / or therapy metrics. Examples of criteria 904 include but are not limited to: the number of days per week that the PWD uses long-acting doses exceeds a pre-defined number of days (e.g., a behavioral metric); the amount of time that the PWD is below range is less than a pre-defined amount of time (e.g., a physiological metric); the glucose data coverage range for the PWD exceeds a pre-defined amount (e.g., a behavioral metric); the number of times per month that the PWD treats nighttime low glucose is less than a pre-defined amount; the amount of time that the PWD has nighttime low glucose is less than a pre-defined amount of time; the median lowest morning glucose for the PWD is below a pre-defined level; or the ratio between the PWD’s daily long-acting and rapid-acting insulin doses is less than a pre-defined value (e.g., a therapy metric). Accordingly, the operation 810 can take into account one or more of the criteria 904 in determining whether to trigger the insight 902.

[0184] FIG. 10 An example of a multi-modal insight satisfaction evaluation 1000 is shown. The multi-modal insight satisfaction evaluation 1000 can be used in combination with one or more of the examples described elsewhere herein. The multi-modal insight satisfaction evaluation 1000 here is related to the insight 902 of the example described above. The insight 902 can have two or more criteria 1002 to be satisfied. Each criterion 1002 can specify one or more situations that the performance metric can reflect. In some implementations, M criteria 1002 are used, where M = 1, 2, 3,.... The number of satisfaction criteria M can be the same as the number of trigger criteria N, or can be a higher or lower number.

[0185] The multi-modal insight satisfaction evaluation 1000 can be multi-faceted and can span more than one type of performance metric, including but not limited to behavioral metrics, physiological metrics, and therapy metrics. Examples of criteria 1002 include, but are not limited to: the number of days per week that the PWD uses long-acting doses exceeds a predefined number of days (e.g., a behavioral metric); the PWD’s glucose data coverage exceeds a predefined amount (e.g., a behavioral metric); the probability that the PWD makes an insulin therapy change is greater than a predefined number; or the PWD’s median lowest morning glucose is below a predefined level. Accordingly, operation 836 can consider one or more of the criteria 1002 in determining whether the improvement criteria for the insight 902 is satisfied. That is, satisfaction (or non-satisfaction) of the criteria 1002 determines whether the reinforcement learning generates positive (or negative) feedback for the action(s) with respect to the insight 902.

[0186] FIG. 11 An example 1100 of an action 1102 related to an insight is shown. The action 1102 can be used in combination with one or more examples described elsewhere herein. The action 1102 can be presented on a display device 1104 (e.g., in an application on a mobile electronic device). The PWD can opt-in (or opt-out) of any of the actions of the action 1102. For example, opt-in and / or opt-out inputs can be received. The action 1102 can be presented to encourage the PWD to set goals for managing their diabetes therapy.

[0187] FIG. 12 An example architecture of a computing device 1200 that can be used to implement aspects of the present disclosure, including any of the systems, apparatuses, and / or techniques described herein, or any other system, apparatus, and / or technique that can be used in various possible embodiments, is illustrated.

[0188] FIG. 12 The computing devices illustrated in the figures can be used to execute the operating systems, applications, and / or software modules (including software engines) described herein. The computing devices can use at least one non-transitory computer-readable storage medium.

[0189] The computing device 1200 includes at least one processing device 1202 (e.g., a processor) such as a central processing unit (CPU) in some embodiments. Various processing devices can be obtained from various manufacturers, Intel or Advanced Micro Devices, for example. In this example, the computing device 1200 also includes a system memory 1204 and a system bus 1206 that couples the various system components including the system memory 1204 to the processing device 1202. The system bus 1206 is one of any number of several types of bus structures used to link various components including a memory bus or memory controller, a peripheral bus, and a local bus using any of a variety of bus architectures.

[0190] Examples of computing devices that can be implemented using the computing device 1200 include a desktop computer, a laptop computer, a tablet computer, a mobile computing device such as a smartphone, a touchpad mobile digital device, or other mobile device, or other device configured to process digital instructions.

[0191] The system memory 1204 includes read-only memory 1208 and random access memory 1210. A basic input / output system 1212 containing the basic routines that help to transfer information

[0192] In some embodiments, the computing device 1200 also includes a secondary storage 1214, such as a hard disk drive, for storing digital data. The secondary storage 1214 is connected to the system bus 1206 via a secondary storage interface 1216. The secondary storage 1214 and its associated computer-readable media provide non-volatile and non-transitory storage for computing device 1200.

[0193] While the example environment described herein employs a hard disk drive as secondary storage, other types of computer-readable storage media can be used in other embodiments. Examples of these other types of computer-readable storage media include a magnetic tape, a flash drive, a digital video disc, a Bernoulli drive, an optical disc, a read-only memory, a digital multi-functional disc read-only memory, a random access memory, or a read-only memory. Some embodiments include non-transitory media. For example, a computer program product can be tangibly embodied in a non-transitory storage medium. Moreover, such computer-readable storage media can include local storage or cloud-based storage.

[0194] A number of program modules can be stored in secondary storage 1214 and / or system memory 1204, including an operating system 1218, one or more application programs 1220, other program modules 1222 such as the software engines described herein, and program data 1224. The computing device 1200 can use any suitable operating system, such as Microsoft Windows™, Google Chrome™ OS, Apple OS, Unix, or Linux variants, and any other operating system suitable for a computing device. Other examples can include Microsoft, Google, or Apple operating systems, or any other suitable operating system used in a tablet computing device.

[0195] In some embodiments, a user provides input to the computing device 1200 through one or more input devices 1226. Examples of input devices 1226 include a keyboard 1228, a mouse 1230, a microphone 1232 (for example, for speech and / or other audio input), a touch sensor 1234 (such as a touchpad or touch-sensitive display), and a gesture sensor 1235 (for example, for gesture input). In some implementations, the input device(s) 1226 provide detection based on presence, proximity, and / or motion. In some implementations, a user can walk into their home and this can trigger input into the processing device. For example, the input device(s) 1226 can facilitate an automated experience for the user. Other embodiments include other input devices 1226. Input devices can be connected to the processing device 1202 through an input / output interface 1236 coupled to the system bus 1206. These input devices 1226 can be connected by any number of input / output interfaces, such as a parallel port, a serial port, a game port, or a universal serial bus. It is also possible for wireless communication to occur between the input device 1226 and the input / output interface 1236, and in some possible embodiments, the wireless communication includes infrared, Bluetooth® wireless technology, 802.11a / b / g / n, cellular, Ultra Wide Band (UWB), ZigBee, or other radio frequency communication systems, just to name a few examples.

[0196] In this example embodiment, a display device 1238, such as a monitor, a liquid crystal display device, a light-emitting diode display device, a projector, or a touch-sensitive display device, is also connected to the system bus 1206 via an interface, such as a video adapter 1240. In addition to the display device 1238, the computing device 1200 can include various other peripheral devices (not shown), such as speakers or a printer.

[0197] The computing device 1200 can connect to one or more networks through network interface 1242. The network interface 1242 can be provided for wired and / or wireless communication. In some embodiments, the network interface 1242 can include one or more antennas to send and / or receive wireless signals. When used in a local area networking environment or a wide area networking environment (such as the Internet), the network interface 1242 can include an Ethernet interface. Other embodiments utilize other communication devices. For example, some embodiments of the computing device 1200 include a modem for communication over a network.

[0198] The computing device 1200 can include at least some form of computer-readable media. Computer-readable media includes any available media that can be accessed by the computing device 1200. By way of example, computer-readable media includes computer-readable storage media and communication media.

[0199] Computer-readable storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the computing device 1200.

[0200] Computer-readable communication media typically embodies computer-readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, computer-readable communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, radio frequency, infrared, and other wireless media. Combinations of the any of the above are also included within the scope of computer-readable media.

[0201] FIG. 12 The computing device illustrated in the figure is also an example of a programmable electronic device that can include one or more such computing devices, and when including multiple computing devices, such computing devices can be coupled together with a suitable data communication network to collectively perform various functions, methods, or operations disclosed herein.

[0202] Exemplary therapy management system

[0203] As discussed above, in order to maintain glucose levels within acceptable limits on a continuous basis, a permanent therapy that provides continuous glycemic control is needed. Such glycemic control can be achieved by regularly supplying the body of the PWD with an external medication that lowers elevated glucose levels. The external biologically effective medication (e.g., insulin or an analog thereof) is typically administered with the aid of daily injections. In some cases, a mixture of RA and LA insulins is injected multiple times daily via a reusable transdermal liquid administration device.

[0204] Currently, the method of monitoring A1C levels is limited to once every 3-6 months, depending on a variety of factors. This method of measuring patient progress and follow-up, which is limited to quarterly or semi-annual visits, can contribute to the emergence of significant therapeutic inertia in PWDs throughout the course of treatment, resulting in suboptimal efficacy and a "treat-to-failure" approach to diabetes therapy. Additionally, limited human resources continue to delay the advancement of therapy according to standards of care.

[0205] Aspects of the therapy management device, system, and method discussed below can regularly maintain one or more glucose metrics of a user within a target level or target range, provide frequent therapy interventions and adjustments (e.g., daily or weekly, rather than every 3-6 months), shorten the duration of interventions, and improve user compliance, efficacy, and satisfaction. System components can include, but are not limited to, a glucose meter or monitor, an insulin pump, an injection pen, a smart cap on an injection pen, an insulin therapy software application (app), and / or a cloud infrastructure.

[0206] FIG. 13A therapy management system 1300 is illustrated in accordance with various example aspects. The therapy management system 1300 can be configured to provide a therapy escalation pathway to manage diabetes and maintain one or more glucose metrics within one or more targets or ranges thereof. The therapy management system 1300 can also be configured to regularly monitor one or more metrics of a user (e.g., A1C level). The therapy management system 1300 can also be configured to provide frequent therapeutic interventions and adjustments to therapy (e.g., daily or weekly, rather than every 3-6 months). The therapy management system 1300 can also be configured to shorten the duration of interventions. The therapy management system 1300 can also be configured to improve user adherence, user efficacy, and user satisfaction. The therapy management system 1300 can also be configured to tailor a therapeutic plan to a user (e.g., based on the user's needs and values). The therapy management system 1300 can also be configured to select a potential therapeutic plan (e.g., dosing regimen) based on past successful interventions to the user or population (e.g., historical therapy similar to the user). The therapy management system 1300 can also be configured to provide more information to the user and / or medical professional more frequently, such that more options of therapy pathways are available. The therapy management system 1300 can also be configured to continuously and / or periodically monitor one or more user metrics (e.g., mean glucose level, weight, BMI, nausea, etc.), such that interventions to therapy can be made in a timely and small scale. The therapy management system 1300 can also be configured to continuously monitor and improve user adherence via coaching and direct feedback (e.g., notifications, warnings, recommendations, requests for user action, etc.), such that adherence deficiencies and poor treatment efficacy can be addressed separately.

[0207] While the therapy management system 1300 is illustrated in FIG. 13 as a standalone device and / or system, aspects of the present disclosure can be used with other devices, systems, and / or methods, such as, but not limited to, elements in FIG. 14A-FIG. 14C , FIG. 15-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 20-FIG. 23 , for example, the control chart 1400A, the therapy assessment 1400B, the control chart 1400C, the therapy assessment 1430, the one or more dosing regimens 1410, 1440, 1450, 1460, 1480, the flowchart 2000, the flowchart 2100, the flowchart 2200, and / or the computing device 2300.

[0208] As FIG. 13As shown in FIG. 13, therapy management system 1300 can include a remote device 1310, an on-body unit (OBU) 1350, one or more drug delivery devices such as a first injection pen 1360 and a second injection pen 1370, a first smart cap 1382, a second smart cap 1384, and / or a software application 1390. In some aspects, therapy management system 1300 can include one or more memories (e.g., memory 1394) and at least one processor (e.g., processor 1392) each coupled to at least one of the memories and configured to execute a software application (app) (e.g., software application 1390) configured to monitor one or more user metrics and implement one or more therapy regimens (e.g., one or more dosing regimens) for a user. In some aspects, therapy management system 1300 can include a drug delivery device (e.g., an injection pen, an insulin pump, etc.) in communication with software application 1390 and configured to monitor and deliver one or more drugs (e.g., insulin) to a user. In some aspects, therapy management system 1300 can include a body weight scale in communication with software application 1390 and configured to measure a user’s body weight.

[0209] In some aspects, therapy management system 1300 can be configured to implement one or more therapy escalation regimens. In some aspects, therapy management system 1300 can receive glucose data for a user from a CGM, calculate one or more metrics, the processor can compare the one or more metrics to one or more preset or user-adjustable thresholds stored in memory, and output a recommendation to the user for an adjusted dose and / or a new therapy to a display of a computing device. In some aspects, therapy management system 1300 can determine whether the user actually ingested the recommended dose and / or new therapy, determine one or more new metrics after the user ingested the recommended dose, and recommend an adjusted (titrated) dose based on the glucose data. In some aspects, therapy management system 1300 can implement a titration phase in which therapy management system 1300 requires the user to actively administer the recommended dose, review one or more user metrics after the user ingested the drug, and then recommend a new dose based on the user’s glucose data.

[0210] Remote device 1310 can be configured to receive or retrieve sensor data from analyte sensor 1352. As shown in FIG. 13, remote device 1310 can include a processor 1312 and a memory 1314. In some aspects, remote device 1310 can be configured to receive sensor data from analyte sensor 1352 and store the sensor data in memory 1314. In some aspects, remote device 1310 can be configured to receive sensor data from analyte sensor 1352 and transmit the sensor data to OBU 1350. FIG. 13As shown, remote device 1310 may include display 1312. Display 1312 may be a touchscreen display for receiving input. Remote device 1310 may include one or more input devices for receiving input, such as one or more buttons, keys, etc. Display 1312 may present various information to the user, such as glucose data, medication data, alarms, notifications, and recommendations, such as in order to request information from the user. Remote device 1310 may include a dosing calculator accessible via dosing calculator button 1314. The display may show analyte level 1321, dot indicator 1322, historical analyte data 1323, trend display 1324, one or more notifications or recommendations, such as first message 1331, second message 1332, third message 1333, first information display 1334, and second information display 1335. In some aspects, remote device 1310 may include processor 1392 coupled to memory 1394 and configured to execute software application 1390. In some respects, remote device 1310 may include a mobile application (e.g., software application 1390) configured to perform one or more operations of the therapy management system 1300 (e.g., control chart 1400A, treatment assessment 1400B, control chart 1400C).

[0211] like FIG. 13 As shown, remote device 1310 can communicate with OBU 1350, such as via one or more wireless communication protocols (e.g., NFC, BLE, etc.). Remote device 1310 can communicate with one or more drug delivery devices or dosing detection devices (such as first injection pen 1360, second injection pen 1370, first smart cap 1382, second smart cap 1384, and / or software application 1390). In some aspects, remote device 1310 may include a handheld computer (e.g., smartphone, cellular phone, mobile phone, PDA, smartwatch, etc.), personal computer, laptop computer, dedicated handheld device associated with an analyte sensor or drug delivery device, or any other portable communication device.

[0212] like FIG. 13 As shown, in an exemplary display 1312 of an exemplary mobile application (e.g., software application 1390) running on the depicted smartphone, display 1312 may include a betting calculator button 1314, and optionally one or more other buttons or input terminals for the user to enter data or respond to recommendations and / or requests. In some aspects, display 1312 may include a numerical and / or graphical display of glucose data (e.g., past, current, and / or predicted). For example, as... FIG. 13As shown, display 1312 may include glucose level 1321 showing the current (or most recent) estimated glucose level, dot indicator 1322 graphically indicating the current (or most recent) estimated glucose value as part of an overall graph, historical analyte data 1323 showing a graph of historical glucose data (e.g., data from the previous 30 minutes, etc.), and a trend display 1324 showing the predicted trend or expected continuation of the historical glucose data 1323.

[0213] In some respects, display 1312 may include one or more text messages to the user regarding the current treatment. For example, such as... FIG. 13 As shown, display 1312 may include a first message 1331 (e.g., a notification), a second message 1332 (e.g., a recommendation), and a third message 1333 (e.g., a request for user action). In some aspects, the first message 1331 may include a notification and / or warning to the user, such as explaining one or more characteristics of glucose data (e.g., "high glucose trend"). In some aspects, the second message 1332 may include a treatment recommendation for the user, such as recommending one or more treatments or therapies (e.g., "you may need more insulin"). In some aspects, the second message 1332 may provide recommendations for insulin, carbohydrates, and / or other therapies. In some aspects, the third message 1333 may include a request for user action, such as requesting the user to respond to or perform an action (e.g., "consume 15 grams of carbohydrates").

[0214] In some aspects, Display 1312 can allow users to tap on glucose data (e.g., glucose level 1321) or otherwise navigate within a mobile application (e.g., software application 1390) to obtain additional or more detailed or complete glucose data. In other aspects, Display 1312 can provide one or more insights (e.g., communications, notifications, recommendations, requests, etc.) for the benefit of the user (e.g., PWD). For example, an insight could convey a tailored message to the user related to their therapy: “You usually take a mealtime bolus between noon and 2 p.m., but you didn’t today and your glucose level is currently rising. Did you forget your bolus?”

[0215] In some aspects, the display 1312 can depict insulin data and / or dosing data. In some aspects, the display 1312 can include a first information display 1334 configured to display information for one or more dosing regimens, including but not limited to the time and / or amount of a most recent RA and / or LA insulin dose. In some aspects, the display 1312 can include a second information display 1335 configured to display information regarding one or more insulin on board (IOB), including but not limited to the amount of IOB for a particular type of insulin or insulin analog (e.g., RA, LA, etc.). In some aspects, IOB (e.g., active insulin) can be defined as the amount of insulin that has been delivered and is still active in the user’s body based on the duration of the estimated insulin action. In some aspects, IOB calculations can be for both RA and LA insulin. In some aspects, the display 1312 can allow the user to tap on the insulin data (e.g., the first information display 1334) or otherwise navigate in the mobile application (e.g., the software application 1390) to obtain additional or more detailed or complete insulin delivery data. In some aspects, the display 1312 can superimpose glucose data and insulin delivery data in any suitable format, e.g., to graphically display the timing of the glucose data with the time of the insulin delivery data.

[0216] In some aspects, the user (e.g., the PWD and / or medical professional) in use can utilize the therapy management system 1300 to receive recommendations regarding appropriate insulin dosages and therapy. For example, in the case of an upcoming need to deliver an LA amount of insulin, the second message 1332 can provide a recommendation for a particular LA insulin. In some aspects, the recommended dosage from the therapy management system 1300 (e.g., the software application 1390) can appear on the display of the first smart cap 1382 and / or the second smart cap 1384, e.g., on the first display 1383 and / or the second display 1385, respectively.

[0217] In some aspects, the user can enter a bolus calculator, e.g., to calculate and deliver a bolus of RA insulin, using the bolus calculator button 1314. In some aspects, the bolus calculator button 1314 can include any suitable bolus calculator, e.g., the bolus calculator can provide a user interface for the user to enter a meal announcement, such as correction only, small meal, normal meal, or large meal. Upon selection of a meal size or meal type (e.g., breakfast, lunch, dinner), the user interface can provide a recommended bolus dosage, e.g., based on the amount of carbohydrates associated with the corresponding meal size and / or meal type and optionally based on glucose data.

[0218] The OBU 1350 can be configured to measure and communicate sensor data of one or more analytes (e.g., glucose) of a user. The OBU 1350 can also be configured to communicate data (e.g., sensor data) from the analyte sensor 1352 to one or more components of the therapy management system 1300 (e.g., the remote device 1310, the first injection pen 1360, the second injection pen 1370, the first smart cap 1382, the second smart cap 1384, the software application 1390, etc.). In some aspects, the OBU 1350 can exchange data with a network and / or a remote server. As FIG. 13 As shown in FIG. 11, the OBU 1350 can include the analyte sensor 1352, the on-body electronics 1354, the on-body housing 1355, and / or the adhesive layer 1356.

[0219] The analyte sensor 1352 can be configured to measure an analyte (e.g., glucose) of a user. The analyte sensor 1352 can be configured to measure one or more analytes (e.g., glucose, ketones) of a user. The analyte sensor 1352 can also be configured to measure a concentration of one or more analytes of a user continuously in real-time (e.g., in vivo). In some aspects, a portion (e.g., a distal portion) of the analyte sensor 1352 can be placed in vivo through a skin surface (e.g., transcutaneously) of a patient and in fluid contact with a bodily fluid (e.g., interstitial fluid, etc.) of the patient. In some aspects, the analyte sensor 1352 can be insertable into a patient’s body (e.g., a vein, an artery, skin, etc.) that contains an analyte. In some aspects, the analyte sensor 1352 can include a CGM to continuously and automatically track glucose levels. In some aspects, the analyte sensor 1352 can measure and retrieve analyte levels in real-time (e.g., about 1-60 seconds) for continuous analyte (glucose) monitoring.

[0220] In some aspects, the analyte sensor 1352 can measure glucose. In some aspects, the analyte sensor 1352 can measure lactate. In some aspects, the analyte sensor 1352 can measure ketones. In some aspects, the analyte sensor 1352 can measure one or more analytes. For example, the analyte sensor 1352 can measure glucose and ketones. For example, the analyte sensor 1352 can measure one or more analytes (e.g., glucose, ketones, lactate, lactic acid, oxygen, hemoglobin A1C, lactones, lactose, galactose, vitamin C, glucuronate, glycogen, mannose, phosphate, diphosphate, fructose, glyceraldehyde, glycerol, triglycerides, sorbitol, phosphogluconate, phosphogluconate, xylulose, ribose, bile, cysteine, serine, homoserine, pyruvate, phenylpyruvate, glutamate, glycine, taurine, threonine, methionine, ethanol, acetone, acetate, oxaloacetate, alanine, phenylalanine, aspartate, asparagine, alcohol, cholesterol, vitamin D, progesterone, testosterone, estrogen, squalene, insulin, hydroxybutyrate, leucine, isoleucine, malonyl, malonate, glucagon, epinephrine, norepinephrine, palmitate, lysine, eicosanoids, melanin, dopamine, tyrosine, tryptophan, niacin, melatonin, serotonin, citrate, isocitrate, valine, porphyrin, histidine, urocanate, histamine, glutamine, proline, creatine, putrescine, spermidine, spermine, arginine, ornithine, citrulline, fumarate, succinate, argininosuccinate, succinyl, ketoglutarate, aconitate, glyoxylic acid, caffeine, sugar, carbohydrates, etc.). In some aspects, the analyte sensor 1352 can measure one or more analytes simultaneously, using one or more corresponding electrochemical biosensors for each different analyte measured.

[0221] The on-body electronics 1354 can be configured to process signals from the analyte sensor 1352. The on-body electronics 1354 can also be configured to communicate data (e.g., sensor data) from the analyte sensor 1352 to one or more external devices (e.g., the remote device 1310, the first injection pen 1360, the second injection pen 1370, the first smart cap 1382, the second smart cap 1384, the software application 1390, etc.). The on-body electronics 1354 can also be configured to wirelessly (e.g., NFC, WiFi, Bluetooth, BLE, the Internet, etc.) communicate sensor data related to an analyte. As shown in FIG. 13B, the on-body electronics 1354 can be operatively (e.g., electrically) coupled to the analyte sensor 1352 and wirelessly coupled to the remote device 1310, the first injection pen 1360, the second injection pen 1370, the first smart cap 1382, the second smart cap 1384, and / or the software application 1390. FIG. 13 The on-body electronics 1354 can be configured to process signals from the analyte sensor 1352. The on-body electronics 1354 can also be configured to communicate data (e.g., sensor data) from the analyte sensor 1352 to one or more external devices (e.g., the remote device 1310, the first injection pen 1360, the second injection pen 1370, the first smart cap 1382, the second smart cap 1384, the software application 1390, etc.). The on-body electronics 1354 can also be configured to wirelessly (e.g., NFC, WiFi, Bluetooth, BLE, the Internet, etc.) communicate sensor data related to an analyte. As shown in FIG. 13B, the on-body electronics 1354 can be operatively (e.g., electrically) coupled to the analyte sensor 1352 and wirelessly coupled to the remote device 1310, the first injection pen 1360, the second injection pen 1370, the first smart cap 1382, the second smart cap 1384, and / or the software application 1390.

[0222] In some aspects, the on-body electronics 1354 can include a printed circuit board (PCB) for connecting to various components (e.g., analyte sensor 1352, processor, ASIC, wireless transceiver, wireless transmitter, controller, memory, etc.). In some aspects, the on-body electronics 1354 can store (e.g., via memory) historical analyte-related data. In some aspects, the on-body electronics 1354 can be configured to store some or all analyte-related data (e.g., sensor data) from the analyte sensor 1352 in memory. In some aspects, the on-body electronics 1354 can include one or more processors and / or control logic configured to determine (e.g., via software programs and / or algorithms) current analyte levels, rates of change of analyte levels (ROC), rates of acceleration of analyte levels, and / or analyte trend information (e.g., trend display 1324) and / or analyte fluctuation levels (e.g., standard deviation, variability, variance, etc.).

[0223] In some aspects, the on-body electronics 1354 can be configured to transmit (broadcast) analyte-related data (e.g., sensor data) to one or more external devices (e.g., remote device 1310, first injection pen 1360, second injection pen 1370, first smart cap 1382, second smart cap 1384, software application 1390, etc.). In some aspects, the on-body electronics 1354 can be configured to transmit (broadcast) real-time data associated with monitored analyte levels from the analyte sensor 1352 to one or more external devices of the therapy management system 1300, e.g., when the external device is within a communication range (e.g., BLE range) of the data broadcast from the OBU 1350.

[0224] In some aspects, the on-body electronics 1354 can be configured to wirelessly transmit stored analyte-related sensor data to one or more external devices of the therapy management system 1300 during a monitoring time period (e.g., sensor wear time). In some aspects, the analyte-related data (e.g., sensor data) transmitted from the on-body electronics 1354 can be stored in one or more memory units (e.g., permanently, temporarily), e.g., memory units on one or more external devices of the therapy management system 1300. In some aspects, the remote device 1310 can be configured as a data conduit to pass data (e.g., sensor data) received from the on-body electronics 1354 to one or more external devices. In some aspects, the on-body electronics 1354 can be designed to store sensor data (e.g., glucose data) from the analyte sensor 1352 collected during sensor wear (e.g., 3 days, 7 days, 14 days, 30 days, etc.) (e.g., within 14 days).

[0225] The bulk housing 1355 can be configured to provide an internal partition for accommodating a portion (e.g., a proximal portion) of the analyte sensor 1352 and the bulk electronics 1354. FIG. 13 As shown, the body carrier housing 1355 may include an analyte sensor 1352 and body electronics 1354 and couple them to an adhesive layer 1356. In some aspects, the body carrier housing 1355 may include a hermetically sealed housing (e.g., an hermetically sealed biocompatible housing). The adhesive layer 1356 may be configured to attach the OBU 1350 to the user's skin surface. FIG. 13 As shown, the adhesive layer 1356 can be coupled to the body housing 1355 to securely position a portion (e.g., the distal portion) of the analyte sensor 1352 to the skin surface.

[0226] The first injection pen 1360 can be configured to administer one or more dosing regimens. In some aspects, the first injection pen 1360 can be combined with a first smart cap 1382 to transmit drug dosage data to a remote device 1310, an OBU 1350, and / or a software application 1390. FIG. 13 As shown, the first injection pen 1360 may include a first dial 1361 configured to set the dose to be delivered and a first dose indicator 1362 configured to indicate the dose. In some aspects, the first injection pen 1360 may include a corresponding first smart cap 1382 that wirelessly communicates with other components of the therapy management system 1300. In some aspects, the first injection pen 1360 may include an insulin pen for a specific type of insulin, such as a rapid-acting (RA) insulin pen. For example, the first injection pen 1360 may include a Humalog™ pen, a Novolog™ pen, or an Apira™ pen. In some aspects, the first injection pen 1360 may include dose capture technology, such as automatically capturing injection data (e.g., set dose, injected dose, dose history, date, time of administration, time since last administration, type of medication, amount of medication remaining in the pen, etc.) via, for example, the first smart cap 1382.

[0227] The second injection pen 1370 can be configured to administer one or more dosing regimens. In some aspects, the second injection pen 1370 can be combined with a second smart cap 1384 to transmit drug dosage data to a remote device 1310, an OBU 1350, and / or a software application 1390. FIG. 13As shown in FIG. 13, the second injection pen 1370 can include a second dial 1371 configured to set a dose to be delivered and a second dose indicator 1372 configured to indicate the dose. In some aspects, the second injection pen 1370 can include a corresponding second smart cap 1384 that wirelessly communicates with other components of the therapy management system 1300. In some aspects, the second injection pen 1370 can include an insulin injection pen for a particular type of insulin, such as a long-acting (LA) insulin pen. For example, the second injection pen 1370 can include a Lantus™ pen, a Levemir™ pen, a Toujeo™ pen, or a Tresiba™ pen. In some aspects, the second injection pen 1370 can include a dose capture technology, e.g., to automatically capture injection data (e.g., dose, administration history, date, time, etc.) via, e.g., the second smart cap 1384.

[0228] The first smart cap 1382 can be configured to wirelessly communicate with the remote device 1310, the OBU 1350, and / or the software application 1390. The first smart cap 1382 can also be configured to present information to a user, including but not limited to any information or sensor data described elsewhere herein (e.g., insulin dose recommendations, notifications, messages, etc.). In some aspects, the first smart cap 1382 can exchange data with the OBU 1350 (e.g., retrieve sensor data from the OBU 1350), e.g., by being brought in proximity to the OBU 1350. In some aspects, the first smart cap 1382 can receive a meal size from a user (e.g., the user announces the meal size, selects the meal size, etc.), including but not limited to a snack, a small meal, a medium meal, a large meal, or a snack. In some aspects, the first smart cap 1382 can include at least one input control, e.g., a button (e.g., an electronic switch). The input control (e.g., button) can be configured to trigger the first smart cap 1382 to perform one or more operations, including but not limited to any operations described elsewhere herein. As shown in FIG. 13, the first smart cap 1382 can include a first display 1383. FIG. 13 As shown in FIG. 13, the first smart cap 1382 can include a first display 1383.

[0229] The first display 1383 can include any suitable type of display technology, including but not limited to a dynamic electronic display (e.g., an LED display) or a static electronic display (e.g., an e-ink display). In some aspects, the first display 1383 can include a user interface for obtaining meal bolus recommendations for different types of meals (e.g., small, medium, large; breakfast, lunch, dinner, snack; 10 grams of carbohydrates, 20 grams of carbohydrates, 45 grams of carbohydrates, etc.). In some aspects, the first display 1383 can display the first message 1331, the second message 1332, the third message 1333, the first information display 1334, the second information display 1335, or a combination thereof.

[0230] The second smart cap 1384 can be configured to wirelessly communicate with the remote device 1310, the OBU 1350, and / or the software application 1390. In some aspects, the second smart cap 1384 can exchange data with the OBU 1350 (e.g., retrieve sensor data from the OBU 1350), for example, by bringing it in proximity to the OBU 1350. In some aspects, the second smart cap 1384 can receive a meal serving size from the user (e.g., the user announces the meal serving size, selects the meal serving size, etc.), including but not limited to a small, medium, large, or snack serving. In some aspects, the second smart cap 1384 can include at least one input control, for example, a button (e.g., an electronic switch). The input control (e.g., button) can be configured to trigger the second smart cap 1384 to perform one or more operations, including but not limited to any of the operations described elsewhere herein. As FIG. 13 As shown in FIG. 13B, the second smart cap 1384 can include a second display 1385.

[0231] The second display 1385 can include any suitable type of display technology, including but not limited to a dynamic electronic display (e.g., an LED display) or a static electronic display (e.g., an e-ink display). In some aspects, the second display 1385 can include a user interface for obtaining meal bolus recommendations for different types of meals (e.g., small, medium, large; breakfast, lunch, dinner, snack; 10 grams of carbohydrates, 20 grams of carbohydrates, 45 grams of carbohydrates, etc.). In some aspects, the second display 1385 can display the first message 1331, the second message 1332, the third message 1333, the first information display 1334, the second information display 1335, or a combination thereof.

[0232] In some aspects, the first smart cap 1382 and / or the second smart cap 1384 can be configured to record, store, and / or communicate one or more types of cap information, e.g., information about when the first smart cap 1382 and / or the second smart cap 1384, respectively, is secured to and / or released from the corresponding first injection pen 1360 and / or second injection pen 1370. In some aspects, the cap information can include information about a current cap period (e.g., time since last cap), about the duration of one or more uncaps (also referred to herein as “cap off(s)”), and / or the timing of each uncapping and each capping (e.g., time of day or elapsed time since last). For example, the cap information can include data reflecting when the first smart cap 1382 and / or the second smart cap 1384, respectively, is placed onto, removed from, or both, the corresponding first injection pen 1360 and / or second injection pen 1370. In some aspects, the cap information can be displayed on a display screen of the first smart cap 1382 and / or the second smart cap 1384 (e.g., via the first display 1383 and / or the second display 1385) for presentation to a user. In some aspects, the first smart cap 1382 and / or the second smart cap 1384 can include a speaker, microphone, receiver, or other audio device, and the cap information can be detected by a receiver (e.g., microphone) and / or presented by a speaker in the first smart cap 1382 and / or the second smart cap 1384.

[0233] For example, in some aspects, the first smart cap 1382 and / or the second smart cap 1384 can provide a timer clock that counts from the time the first smart cap 1382 and / or the second smart cap 1384, respectively, was last secured to the first injection pen 1360 and / or the second injection pen 1370. In some aspects, the first smart cap 1382 and / or the second smart cap 1384 can wirelessly communicate the cap information to one or more components of the therapy management system 1300 (e.g., remote device 1310) and / or a remote computing device (e.g., remote server, remote computer, network, cloud server, smart phone, tablet, etc.). In some aspects, one or more accessories or smart delivery devices can detect other events associated with a drug delivery action of the therapy management system 1300 and use that information in the manner described herein for the cap information. For example, in some cases, an injection pen accessory (e.g., smart cap) can be secured to an injection pen such that it can detect mechanical movement of the dosing mechanism to determine the time of administration of a drug, and optionally (but not necessarily) determine the amount of drug delivered at that time.

[0234] In some aspects, the pen cap information can be stored, displayed, and / or analyzed in combination with glucose data to determine user behavior, such as, for example, whether the user properly injected insulin at mealtime and / or to correct for elevated glucose levels. In some aspects, the pen cap information can be presented in a graphical representation of user glucose data and presented to the user and / or a medical professional. In some aspects, the glucose data can be evaluated for a period of time after each cap-on event of the first smart cap 1382 and / or the second smart cap 1384 to determine whether the user properly injected insulin in the cap-on event, e.g., proper dose, underdose, overdosed, basal insulin overdose, etc.

[0235] In some aspects, other information indicates that a pen cap-on event can be disregarded when a dose was not provided. For example, the event can be disregarded when a dose selection of the first injection pen 1360 and / or the second injection pen 1370 (e.g., first dial 1361 and / or second dial 1371, respectively) is detected to not have changed. In some aspects, a pen uncapping and recapping event can be disregarded if the total uncapping time is less than a first threshold (e.g., about 4-6 seconds). For example, the first threshold can be determined based on an amount of time that is too short to perform an injection but long enough to allow the user to inspect the end of the pen to see if there is remaining insulin or if a needle is attached to the pen. In some aspects, the total uncapping time of a cap-off event (e.g., the time between a cap-off event and a subsequent recapping) can be combined with glucose data analysis to determine whether an injection occurred during the cap-off event. In some aspects, if the total uncapping time exceeds a second threshold (e.g., at least 15 minutes, at least 30 minutes, etc.), then glucose data and methods described herein for detecting meal timing can be used to determine an approximate time of the injection.

[0236] In some aspects, some or all components of the therapy management system 1300 can perform one or more operations or functions described elsewhere herein. In some aspects, the therapy management system 1300 can evaluate insights based on reinforcement learning and perform one or more actions (e.g., one or more dosing regimens) for one or more triggered insights. In some aspects, the therapy management system 1300 can determine usage of insulin by detecting removal and / or replacement of the first smart cap 1382 and / or the second smart cap 1384. In some aspects, the therapy management system 1300 can detect an amount of insulin and / or other administered drugs (e.g., GLP-1, prandial insulin, MDI of prandial insulin, etc.).

[0237] Software application 1390 can be configured to monitor one or more user metrics and implement one or more therapeutic pathways (e.g., one or more dosing regimens) for the user. Software application 1390 can also be configured to provide therapy escalation pathways to manage diabetes and maintain one or more glucose metrics at target levels or within target ranges. Software application 1390 can also be configured to guide users with diabetes in managing their insulin therapy. Software application 1390 can also be configured to provide frequent therapy interventions and therapy adjustments (e.g., daily or weekly, instead of every 3-6 months). Software application 1390 can also be configured to continuously and / or periodically monitor one or more user metrics (e.g., mean glucose level, one or more glucose metrics, weight, BMI, nausea, etc.) so that therapy interventions can be timely and minimal. Software application 1390 can also be configured to continuously monitor and improve user compliance via coaching and direct feedback (e.g., notifications, warnings, recommendations, requests for user actions, etc.) so that inadequate compliance and poor treatment outcomes can be addressed separately. FIG. 13 As shown, remote device 1310 may include processor 1392 coupled to memory 1394 and configured to execute software application 1390.

[0238] like Exemplary control chart As shown, software application 1390 can be executed by one or more processors (e.g., processor, controller, microprocessor, microcontroller, ASIC, etc.), such as processor 1392 on remote device 1310. In some aspects, software application 1390 can be coupled to a memory storing instructions, such as memory 1394 on remote device 1310, which, when executed, cause one or more processors to perform operations, including but not limited to: recommending a first dosing regimen for basal insulin, determining an overdose of basal insulin in the first dosing regimen, recommending a second dosing regimen with the addition of GLP-1 or dual GIP / GLP-1, recommending a third dosing regimen with the addition of bolus insulin at a single meal, recommending a fourth dosing regimen with the addition of bolus insulin in a stepwise MDI, and recommending a fifth dosing regimen with the addition of basal insulin and bolus insulin at each meal.

[0239] In some aspects, the software application 1390 can be part of the remote device 1310. In some aspects, the software application 1390 can be part of the OBU 1350, the first smart injection pen 1360, the second smart injection pen 1370, the first smart cap 1382, and / or the second smart cap 1384. In some aspects, the software application 1390 can comprise a mobile application (app). In some aspects, the software application 1390 can comprise a web application (app). For example, the software application 1390 can be part of a remote device (e.g., in a web application), e.g., at a remote location (e.g., a medical professional computer, a service center, etc.).

[0240] In some aspects, the processing and functionality required by the software application 1390 can all be contained in a mobile application. In some aspects, some or portions of the software application 1390 (e.g., a mobile application) can be contained in a remote server that supports the software application 1390, e.g., the remote server can support a mobile application with processing, communication hub, and / or reporting functionality. In some aspects, the functionality of the software application 1390 described herein includes functionality with respect to a mobile application, a remote server, or both, noting that all or some of the functionality can be present in either or both. In some aspects, references herein to the software application 1390 refer to both a mobile application and to a web server (e.g., a remote server) that supports the mobile application.

[0241] In some aspects, the software application 1390 (e.g., a mobile application) can retrieve continuous glucose sensor data in real-time. In some aspects, the software application 1390 can retrieve various combinations of discrete and continuous analyte measurements.

[0242] In some aspects, the software application 1390 can be configured to evaluate one or more insights based on reinforcement learning and determine whether to generate each insight. In some aspects, each insight can be associated with performing one or more actions. For example, performing an action can include providing a message to a user and / or automatically changing an insulin regimen. In some aspects, the insights can be tailored to cover a user’s entire regimen for diabetes, including but not limited to management of diabetes, maintaining one or more glucose metrics at a target level or target range, weight loss, one or more dosing regimens, and / or one or more regimen escalation pathways. In some aspects, an insight can include detecting an observation from data (e.g., sensor data, user metrics, etc.) such that certain regimen actions can be taken. In some aspects, the insights are sufficiently related to the overall regimen such that a user’s regimen (e.g., MDI regimen) can be significantly improved.

[0243] In some aspects, the software application 1390 can be configured to implement therapy evaluation to monitor one or more user adherence metrics to confirm user adherence to therapy, e.g., for a first time period (e.g., a 3-day cycle). In some aspects, the software application 1390 can be configured to implement therapy evaluation to rapidly titrate basal insulin, e.g., for a second time period (e.g., a 3-day cycle). In some aspects, rapid titration can include recommending an adjusted dose at a first interval (e.g., daily) based on one or more user metrics for the first interval until no changes are made within a predetermined time period (e.g., 3 days). In some aspects, the software application 1390 can be configured to implement therapy evaluation to monitor no changes in bolus output status, e.g., for a third time period (e.g., no changes in the last 4 consecutive outputs). In some aspects, the software application 1390 can be configured to implement therapy evaluation to maintain titration of basal insulin, e.g., for a fourth time period (e.g., a 14-day cycle). In some aspects, maintenance titration can include recommending an adjusted dose at a second interval (e.g., days, weeks, bi-weeks, etc.) based on one or more user metrics for the second interval until a new issue is identified (e.g., a new medication regimen, a new exercise habit, a new diet, etc.).

[0244] In some aspects, the software application 1390 can be configured to determine basal insulin excess based on a comparison of one or more metrics to a predetermined threshold. The threshold can be preset by the system or can be adjustable by the user or a medical professional. In some aspects, basal insulin excess can be determined based on a ratio of TDD to weight. For example, the threshold can be based on a total insulin dose greater than 0.5 units (U) / kg / day. The total daily dose (TDD) can be determined by adding the total amount of insulin ingested by the user in a day. In some aspects, the TDD can be manually entered by the user. In some aspects, the user can manually enter the insulin dose for each administration, and the system can calculate the TDD by adding the individual doses. In some aspects, the doses can be automatically logged by a drug delivery device used to administer the insulin, such as an insulin pump, a smart insulin pen, or a dose monitoring device installed on the drug delivery device, such as a smart pen cap, etc. Such devices can communicate the dose information to the system for calculation of the TDD. A combination of manually entered doses and automatically captured doses can be used to determine the TDD. The user can manually enter the weight into the computing device. In some aspects, a weight scale can be in communication with the system. The user can weigh themselves using the weight scale, and the weight scale can automatically communicate the measured weight to the system. The system can periodically prompt the user to take a weight measurement, e.g., at corresponding intervals of a rapid titration phase or a maintenance titration phase.

[0245] In some aspects, the software application 1390 can be configured to determine a basal insulin excess based at least in part on a morning (AM)-bedtime (PM) glucose difference and / or a postprandial-preprandial glucose difference, or a rate of change of nighttime glucose levels or mealtime glucose levels, or a combination thereof.

[0246] In some aspects, the software application 1390 can be configured to determine a basal insulin excess based at least in part on a hypoglycemic metric exceeding a threshold. The system can determine a hypoglycemic metric using glucose data, such as time below range (TBR). The system can be configured to output a glucose alert to the user when the user’s glucose level falls below a low glucose threshold or a very low glucose threshold. The system can track a number of low glucose alerts or very low glucose alerts output during a predetermined period. If the number of alerts exceeds a threshold within the predetermined period, a hypoglycemic can be determined.

[0247] In some aspects, the software application 1390 can be configured to determine a basal insulin excess based at least in part on an increase in glucose variability. A basal insulin excess can be detected if glucose variability exceeds a predetermined variability threshold. Glucose variability can be calculated using a coefficient of variation (e.g., a ratio of a standard deviation to a mean). In some aspects, the glucose variability threshold can include a coefficient of variation greater than 25%, 30%, or 35%, etc. In some aspects, glucose variability can be determined based on an alternative measure of variability, such as a standard deviation from a mean or an interquartile range, etc.

[0248] In some aspects, the software application 1390 can be configured to implement one or more dosing regimens based on one or more goals of the user. In some aspects, for example, the goals can be based at least in part on one or more metrics of the user. In some aspects, for example, the goals can be based at least in part on a BMI of the user and a mean glucose level of the user. In some aspects, if one or more parameters of the user exceed one or more goals of the user, the software application 1390 can be configured to escalate therapy by recommending adding and / or modifying one or more dosing regimens to maintain the one or more parameters within the one or more goals or ranges thereof.

[0249] In some aspects, the therapy management system 1300 can include a processor configured to execute a software application (app) 1390 configured to monitor one or more user metrics and implement one or more therapy regimens (e.g., one or more dosing regimens) for a user. In some aspects, the software application 1390 can be part of the remote device 1310, the OBU 1350, the first injection pen 1360, the second injection pen 1370, the first smart cap 1382, and / or the second smart cap 1384. In some aspects, the software application 1390 can include a mobile application on the remote device 1310. In some aspects, the therapy management system 1300 can include a network or remote server configured to support the software application 1390. In some aspects, the software application 1390 can be contained entirely in a user mobile application (app), or some or portions of the software application 1390 can be contained in a remote server (e.g., a web server, a cloud server, an intranet server, etc.) that supports the software application (e.g., with processing, communication, and / or reporting functionality). In some aspects, the software application 1390 can include one or more application programming interfaces (APIs) for two or more computer programs to communicate with each other.

[0250] In some aspects, the software application 1390 can be configured to recommend one or more therapy escalation regimens. In some aspects, the software application 1390 can receive glucose data for a user from a CGM (e.g., the OBU 1350), calculate one or more user metrics (e.g., as described herein), compare the one or more user metrics to one or more preset or user-adjustable targets (thresholds) stored in memory, and output a recommendation for an adjusted dose and / or a new therapy to the user to the display 1312 of the remote device 1310. In some aspects, the software application 1390 can determine whether the user actually ingested the recommended dose and / or new therapy (e.g., monitor one or more glucose metrics), determine one or more new metrics after the user ingested the recommended dose, and recommend an adjusted (titrated) dose based on the glucose data. In some aspects, the software application 1390 can recommend a titration phase, where the software application 1390 requires the user to actively administer the recommended dose, review one or more user metrics after the user ingested the medication, and then recommend a new dose based on the user’s glucose data.

[0251] In some aspects, the software application 1390 can be configured to determine the number of days for one or more dosing regimens (e.g., a basal insulin regimen). For example, the number of days can be defined by the time between LA doses. In some aspects, the software application 1390 can define the number of days for basal titration based on the time between LA doses. In some aspects, for example, short days between LA doses that are less than a first interval (e.g., about 18 hours) can be considered invalid and discarded from determining the number of days for basal titration. In some aspects, for example, short days between LA doses that are greater than a second interval (e.g., about 18 hours) can be considered valid and used to determine the number of days for basal titration. In some aspects, for example, long days between LA doses that are greater than a third interval (e.g., about 24 hours) can be considered valid and used to determine the number of days for basal titration. In some aspects, for example, long days between LA doses that are greater than a fourth interval (e.g., about 24 hours) can be considered good days (e.g., 24 hour duration) and used to determine the number of days for basal dose titration. In some aspects, for example, long days between LA doses that are greater than a fifth interval (e.g., about 42 hours) can be considered missed days (e.g., 42 hours since last dose) and used to determine the number of days for basal dose titration. In some aspects, the missed days can repeat for a sixth interval (e.g., every 24 hours) until another LA dose is ingested and used to determine the number of days for basal dose titration.

[0252] FIG. 14A

[0253] FIG. 14A FIGURE illustrates a control chart 1400A for implementing one or more therapy pathways, according to various example aspects. The control chart 1400C can be configured to provide a therapy escalation pathway for managing diabetes. The control chart 1400C can also be configured to implement one or more therapy pathways (e.g., one or more dosing regimens) for a user. The control chart 1400C can also be configured to assess the adequacy of each dosing regimen and evaluate basal insulin excess.

[0254] While FIG. 13 The control chart 1400A is shown as a standalone process, device, and / or system in the FIG. 14B , FIG. 14C , FIG. 15-FIG. 18 , FIG. 19A-FIG. 19C , FIG. 20-FIG. 23 and FIG. 14AElements in the system, such as a therapy management system 1300, a software application 1390, a therapy assessment 1400B, a control chart 1400C, a therapy assessment 1430, one or more dosing regimens 1410, 1440, 1450, 1460, 1480, a flowchart 2000, a flowchart 2100, a flowchart 2200, and / or a computing device 2300.

[0255] like FIG. 14B As shown, control chart 1400A may include a first therapy 1401, therapy assessment 1403, and a second therapy 1405. In some aspects, control chart 1400A may be implemented via software application 1390. In some aspects, control chart 1400A may be implemented for one or more dosing regimens (e.g., one or more dosing regimens 1410, 1440, 1450, 1460, 1480) to provide one or more therapy escalation pathways. In some aspects, control chart 1400A may include a first dosing regimen 1410, a second dosing regimen 1440, a third dosing regimen 1450, a fourth dosing regimen 1460, a fifth dosing regimen 1480, or combinations thereof.

[0256] First therapy 1401 can be configured to recommend first therapy if one or more user metrics fall outside one or more targets. In some aspects, first therapy 1401 may include a first dosing regimen 1410 (e.g., basal insulin), a second dosing regimen 1440 (e.g., GLP-1 or dual GIP / GLP-1), or a combination thereof. In some aspects, one or more user metrics may include one or more glucose metrics (e.g., mean glucose, median glucose, glucose TIR, glucose TBR, glucose TAR, glucose TVL, GMI, MMG, MPDG, PPG, BeAM, or a combination thereof), BBR, ISF, PRA-CG, weight, BMI, TDD (e.g., TDD of insulin), TDD to weight ratio, A1C level (e.g., percentage of glycated hemoglobin, mmol / ml), heart rate, blood pressure, or a combination thereof. In some aspects, one or more targets may include a target glucose level (e.g., approximately 110 mg / dL), a target glucose level range (e.g., approximately 110 mg / dL to approximately 155 mg / dL), a target basal status (e.g., MMG approximately 100 mg / dL to approximately 130 mg / dL), a target meal status (e.g., MPDG approximately 100 mg / dL to approximately 120 mg / dL), a target corrected ISF status (e.g., PRA-CG approximately 70 mg / dL to approximately 180 mg / dL), a target body weight, a target A1C level (e.g., 5.7%), a target heart rate, a target blood pressure, or a combination thereof. In some aspects, one or more targets may be based at least in part on the user's BMI and mean glucose level.

[0257] Therapy evaluation 1403 can be configured to assess the adequacy of the first therapy 1401 and evaluate basal insulin excess. Therapy evaluation 1403 can also be configured to confirm user adherence to the first therapy 1401. In some aspects, therapy evaluation 1403 can be configured to determine basal insulin excess based at least in part on medicament delivery information. For example, basal insulin excess can be determined based at least in part on a ratio of TDD of insulin to user weight exceeding a predetermined threshold (e.g., exceeding about 0.5 U / kg / day). In some aspects, therapy evaluation 1403 can be configured to determine basal insulin excess based at least in part on one or more glucose metrics. For example, basal insulin excess can be determined based at least in part on a glucose level change during overnight (e.g., morning (AM) - bedtime (PM) difference), a glucose level change during a meal (e.g., post-meal - pre-meal difference), a low glucose metric below a predetermined threshold (e.g., a glucose concentration of about 70 mg / dL), a glucose variability exceeding a predetermined threshold (e.g., a pre-meal rise exceeding about 30 mg / dL, a post-meal spike exceeding about 110 mg / dL), or a combination thereof.

[0258] Second therapy 1403 can be configured to recommend adding a second therapy if one or more user metrics remain outside of one or more targets or if basal insulin excess is determined. In some aspects, second therapy 1403 can include a second dosing regimen 1440 (e.g., GLP-1 or dual GIP / GLP-1), a third dosing regimen 1450 (e.g., mealtime insulin given at one meal), a fourth dosing regimen 1460 (e.g., stepped MDI of mealtime insulin), a fifth dosing regimen 1480 (e.g., basal insulin and mealtime insulin given at each meal), or a combination thereof.

[0259] FIG. 14B FIG. 14B illustrates a therapy evaluation 1400B, according to example aspects. Therapy evaluation 1400B can be configured to assess the adequacy of a current therapy, confirm user adherence, and recommend adjusting one or more dose amounts based on one or more user metrics. Therapy evaluation 1400B can also be configured to implement for any of the dosing regimens described herein (e.g., one or more dosing regimens 1410, 1440, 1450, 1460, 1480).

[0260] While FIG. 13 Therapy evaluation 1400B is shown as a standalone process, device, and / or system in FIG. 14B, aspects of the present disclosure can be used with other processes, devices, systems, and / or methods, such as, but not limited to FIG. 14A , FIG. 14C , FIG. 15-FIG. 18 , FIG. 19A-FIG. 19C , FIG. 20-FIG. 23and FIG. 14B Elements in the system, such as a therapy management system 1300, a software application 1390, a control chart 1400A, a control chart 1400C, a therapy assessment 1430, one or more dosing regimens 1410, 1440, 1450, 1460, 1480, a flowchart 2000, a flowchart 2100, a flowchart 2200, and / or a computing device 2300.

[0261] like Exemplary dosing regimen As shown, therapy evaluation 1400B may include a monitoring phase 1402, a rapid titration phase 1404, and a maintenance titration phase 1406. In some aspects, therapy evaluation 1400B may be implemented by software application 1390. In some aspects, therapy evaluation 1400B may be implemented for one or more dosing regimens (e.g., one or more dosing regimens 1410, 1440, 1450, 1460, 1480) to evaluate the current therapy and adjust the dosage based on one or more user metrics.

[0262] Monitoring phase 1402 can be configured to monitor one or more user compliance metrics for the current therapy over a predetermined time period. Monitoring phase 1402 can also be configured to determine whether the user is correctly wearing and using the CGM (e.g., OBU1350) and whether the medication is being administered correctly and consistently. In some aspects, one or more user compliance metrics may include the frequency of glucose data (scans), the time between glucose data intervals, the time of administration, the amount of dosage (e.g., relative to a recommended dose), the receipt of user input, or a combination thereof. In some aspects, the predetermined time period may be in the range of approximately 1 day to approximately 7 days, for example, 3 days. In some aspects, once one or more user compliance metrics are received (satisfied) within the predetermined time period (e.g., 3 days), the current therapy can proceed to rapid titration phase 1404.

[0263] The rapid titration phase 1404 can be configured to recommend an adjusted dose for a first interval (e.g., midnight each day) based on one or more user metrics (e.g., those listed above). In some aspects, the rapid titration phase 1404 can continue the above treatment until no changes are made within a predetermined time period (e.g., day 3, day 6, etc. within a 7-day period). In some aspects, dose adjustments can be made at fixed intervals (e.g., an increase of 0.25U, an increase of 10%, etc.) or can be proportional to the degree of glycemic dysfunction (e.g., a higher dose change if significantly outside the glucose target). In some aspects, once no changes are received within the predetermined time period (e.g., day 3, day 6, etc. within a 7-day period), the current therapy can proceed to the maintenance titration phase 1406.

[0264] The maintenance dose titration phase 1406 can be configured to recommend an adjusted dose for a second interval (e.g., a few days, a week) based on one or more user metrics (e.g., listed above) during the second interval. In some aspects, the maintenance dose titration phase 1406 can continue the above-described process until a new issue with the current therapy is identified. In some aspects, the dose adjustment can be made at a fixed interval (e.g., increase by 0.25 U, increase by 10%, etc.), or can be proportional to the degree of glycemic dysfunction (e.g., higher dose change if significantly outside of glucose targets). In some aspects, the new issue can include a new medication, a new exercise habit, a new diet, or a combination thereof.

[0265] FIG. 14C

[0266] FIG. 15-FIG. 18 、 FIG. 19A-FIG. 19C and FIG. 14C FIG. 14C illustrates a control chart 1400C implementing one or more dosing regimens 1410, 1440, 1450, 1460, 1480, in accordance with various example aspects. The control chart 1400C can be configured to provide a therapy escalation pathway for managing diabetes. The control chart 1400C can also be configured to implement one or more therapy pathways (e.g., one or more dosing regimens) for a user. The control chart 1400C can also be configured to assess adequacy of each dosing regimen and evaluate basal insulin excess.

[0267] While FIG. 13 the control chart 1400C is illustrated as a standalone process, device, and / or system, aspects of the present disclosure can be used with other processes, devices, systems, and / or methods, such as, but not limited to, elements in FIG. 14A 、 FIG. 14B 、 FIG. 15-FIG. 18 、 FIG. 19A-FIG. 19C 、 FIG. 20-FIG. 23 and FIG. 14C , e.g., the therapy management system 1300, the software application 1390, the control chart 1400A, the therapy assessment 1400B, the therapy assessment 1430, the one or more dosing regimens 1410, 1440, 1450, 1460, 1480, the flowchart 2000, the flowchart 2100, the flowchart 2200, and / or the computing device 2300.

[0268] As FIG. 15As shown in FIG. 1400C, control chart 1400C can include a first dosing regimen 1410 (e.g., basal insulin), a therapy assessment 1430, a second dosing regimen 1440 (e.g., GLP-1 or GIP / GLP-1 dual regimen), a third dosing regimen 1450 (e.g., prandial insulin at mealtime), a fourth dosing regimen 1460 (e.g., stepped MDI of prandial insulin), and / or a fifth dosing regimen 1480 (e.g., basal insulin and prandial insulin at each mealtime). In some aspects, control chart 1400C can implement one or more therapies for a user, including one or more of first dosing regimen 1410, therapy assessment 1430, second dosing regimen 1440, third dosing regimen 1450, fourth dosing regimen 1460, fifth dosing regimen 1480, or combinations thereof. In some aspects, control chart 1400C can be implemented by software application 1390.

[0269] In some aspects, for example, software application 1390 can monitor user data (e.g., one or more user metrics) of therapy management system 1300 (e.g., via OBU 1350, first injection pen 1360, second injection pen 1370, first smart cap 1382, and / or second smart cap 1384), send one or more control signals or instructions to therapy management system 1300 (e.g., via remote device 1310, first smart cap 1382, and / or second smart cap 1384) to execute or instruct a user to execute one or more dosing regimens of control chart 1400C, and assess whether any basal insulin overdoses occurred with the one or more dosing regimens.

[0270] The first dosing regimen 1410 can be configured to initiate basal insulin therapy. In some aspects, the software application 1390 can implement the first dosing regimen 1410 if one or more user metrics are outside of one or more targets (e.g., mean glucose, median glucose, glucose TIR, glucose TBR, glucose TVL, GMI, MMG, PPG, BBR, BeAM, ISF, weight, BMI, A1C level, heart rate, blood pressure, or a combination thereof). In some aspects, the one or more targets can include a target basal state (e.g., MMG of about 100 mg / dL to about 130 mg / dL). In some aspects, the first dosing regimen 1410 can be based at least in part on user-specific considerations, for example, the selection of basal insulin can be based on cost and any pre-existing conditions of the user. In some aspects, the first dosing regimen 1410 can be based at least in part on glucagon prescription for emergency hypoglycemia. In some aspects, the first dosing regimen 1410 can have an initial insulin starting dose of about 0.1 U / kg / day to about 0.2 U / kg / day. In some aspects, the first dosing regimen 1410 can include adding a CGM (e.g., OBU 1350) to the user to set an initial glucose target (e.g., the glucose target can be in a range of about 117 mg / dL to about 154 mg / dL).

[0271] In some aspects, the first dosing regimen 1410 can include a monitoring phase to ensure the user is using the CGM correctly and adhering to the therapy regimen. This can be determined by monitoring one or more of system usage, sensor wear, sensor scan, and integrity of glucose data, and dosing administered by the user (correspondence of doses administered to doses recommended). For example, the monitoring phase can last for a first period of time. The first period of time can be one or more days. One or more adherence metrics can be assessed each day, where adherence to therapy is determined each day based on the adherence metrics. Once an adherence threshold is reached, such as 3 consecutive days of meeting the adherence goal, the user can be considered to be adhering to therapy. In some aspects, if the user is not adhering to the first dosing regimen 1410, the software application 1390 can provide coaching and interventions to help the user adhere to the first dosing regimen 1410 more effectively. For example, the coaching can include alerts and reminders (e.g., messages reminding the user to take therapy), education or encouragement (e.g., messages informing the user of the importance of regular therapy use, encouraging continued therapy use), and / or long-term education (e.g., general in-person or virtual diabetes education to better understand what is happening to the user’s body and the value of therapy use). The notifications can be based on the adherence metrics. For example, if the adherence metrics relate to timing of insulin doses, and the user is not taking insulin at consistent times, the notifications can alert the user and provide recommendations for taking doses at particular times. If the adherence metrics indicate incomplete glucose data (e.g., glucose data for 70% or less of the day), the notifications can alert the user to ensure the sensor is worn and the remote device is kept in range, or to scan the sensor more frequently to obtain glucose data.

[0272] In some aspects, the coaching can be user-directed. For example, the coaching can include brief educational messages (e.g., “Did you know that behavior A is associated with outcome Y?” “Why didn’t you walk for 45 minutes today?” “Did you know that walking can message Z?”), logging adherence alerts or warnings (e.g., missed dose warning, low dose warning, start moving warning), motivational messages encouraging behavior (e.g., “You have scanned your CGM at least 4 times per day for the past week, keep it up!” “You have taken your medication A on time 95% of the time for the past month, on days you have taken medication A you tell us you feel better than on days you have not taken medication A”), and / or long-term education (e.g., attending a cooking class, logging into a virtual type 2 diabetes education course).

[0273] In some aspects, the intervention can be guided by a medical professional. For example, the intervention can include: the user is not taking medication daily, so the user is encouraged to take medication (e.g., without escalation of therapy); the user is not taking medication, so a medication that is easier to administer is considered (e.g., once-daily medication, oral versus injectable, etc.); the user is taking medication but not seeing an effect, so intensification of the current therapy is considered (e.g., the pattern of physiologic markers does not match expected behavior, insulin is not lowering glucose levels, GLP-1 is not reducing weight); the user is taking medication but not seeing an effect, so addition of therapy is considered; and / or the user is taking medication but not seeing an effect, so substitution of therapy is considered (e.g., basal insulin or -> basal insulin + GLP-1).

[0274] In some aspects, the software application 1390 can define a preferred therapy algorithm (e.g., control chart 1400A, control chart 1400C). For example, the preferred therapy algorithm can be defined by the user (e.g., the user’s values and goals) or by one or more medical professionals. In some aspects, for example, the preferred therapy algorithm can include a predetermined therapy escalation pathway (e.g., use of diet and exercise -> metformin -> metformin + GLP-1 -> GLP-1 + basal insulin -> GLP-1 + MDI). In some aspects, for example, the preferred therapy algorithm can remove certain medications and / or ignore certain therapy pathways from consideration (e.g., no use of SGLT-2 agents or flozins, no use of diet and exercise, etc.). In some aspects, the software application 1390 can allow the medical professional to specify which changes the user can make directly to the preferred therapy algorithm (e.g., the user can increase the insulin dose by 20%, the user can increase the GLP-1 dose by 1 step (10 pg for 2 weeks), etc.).

[0275] In some aspects, if the user is adherent to the first dosing regimen 1410 but is not seeing an effect, the software application 1390 can provide one or more options to adjust therapy (e.g., therapy pathway). For example, for a user using injectable medication, the software application 1390 can adjust the dosing (e.g., basal insulin dosing). For example, for a user using oral medication, the software application 1390 can send a message to the user’s HCP to adjust the dosing of the oral medication and / or request the addition of other oral medication to the user’s current therapy. For example, the software application 1390 can escalate the user’s therapy to a higher strength medication (e.g., basal insulin -> MDI, metformin -> GLP-1, etc.). In some aspects, if the user is adherent to the first dosing regimen 1410 but is not seeing an effect, the software application 1390 can implement a second dosing regimen 1440 (e.g., basal insulin -> basal insulin + GLP-1).

[0276] Therapy assessment 1430 can be configured to assess the adequacy of one or more dosing regimens and evaluate basal insulin excess. Therapy assessment 1430 can also be configured to determine basal insulin excess by comparing one or more metrics to one or more thresholds for those metrics. In some aspects, therapy assessment 1430 can be performed with respect to first dosing regimen 1410. In some aspects, therapy assessment 1430 can determine basal insulin excess based at least in part on a ratio of total daily dose (TDD) of insulin to body weight of the user. In some aspects, for example, the ratio of TDD of insulin to body weight can be compared to a predetermined threshold (e.g., about 0.5 U / kg / day). In some aspects, therapy assessment 1430 can determine basal insulin excess based at least in part on glucose variability. In some aspects, for example, glucose variability can be compared to one or more predetermined thresholds (e.g., pre-meal rise of about 30 mg / dL, post-meal spike of about 110 mg / dL, total change in glucose levels from pre-meal period to post-meal period). In some aspects, therapy assessment 1430 can determine basal insulin excess based at least in part on a hypoglycemia metric. In some aspects, for example, the hypoglycemia metric can include low blood glucose index (LBGI), time below range (TBR), number of low glucose alerts, number of very low glucose alerts, and other indicators of hypoglycemia. In some aspects, for example, the hypoglycemia metric can be compared to a predetermined threshold (e.g., glucose concentration below about 70 mg / dL). In some aspects, therapy assessment 1430 can determine basal insulin excess based at least in part on a change in glucose levels during meal periods. In some aspects, for example, the change in glucose levels during meal periods can be compared to a predetermined threshold (e.g., post-meal - pre-meal difference). In some aspects, therapy assessment 1430 can determine basal insulin excess based at least in part on a change in glucose levels during nighttime periods. In some aspects, for example, the change in glucose levels during nighttime periods can be compared to a predetermined threshold (e.g., morning (AM) - bedtime (PM) difference).

[0277] If basal insulin excess is detected, software application 1390 can be configured to recommend that the user initiate a second dosing regimen. Remote device 1310 can output a notification on display 1312 to provide the recommendation to begin the second dosing regimen. The system can alternatively or additionally provide a notification to a computing device of an HCP to recommend initiation of the second dosing regimen. In some aspects, the computing device can generate a report including the recommended dosing regimen.

[0278] The second dosing regimen 1440 can include adding GLP-1 to an existing therapy (e.g., basal insulin therapy). GLP-1 can be added if it is not a contraindication for the patient and is not already part of the user’s therapy regimen. The system can retrieve current therapy information to determine if the therapy regimen already includes GLP-1. The system can include information about contraindications that can be entered by the user or HCP to determine if GLP-1 is a contraindication.

[0279] In some aspects, upon initiation of GLP-1 receptor agonist (RA) therapy, the basal insulin dose is reduced by a predetermined amount of an initial reduction. For example, the current basal insulin dose can be reduced by 20% of the current basal insulin dose. The basal insulin dose can be adjusted by further reducing or increasing the basal insulin dose during the rapid titration phase, as described herein.

[0280] The GLP-1 RA can be titrated concurrently or sequentially with the basal insulin or other existing therapy. The GLP-1 RA can be titrated within the approved range for the particular GLP-1 RA. The GLP-1 RA can start at a first dose and can be increased stepwise toward a maximum dose. The dose can be increased stepwise, for example, on a unit or fractional unit basis, as long as the user is able to tolerate the GLP-1 RA.

[0281] In some aspects, when no side effects (such as nausea) are reported or detected, the system can recommend increasing the dose of the GLP-1 RA. The system can prompt the user to input side effects. The system can specifically ask the user if they are experiencing nausea or vomiting. The system can ask the user for their feelings through free-form text. The system can require the user to select from a predetermined list of side effects. In some aspects, the system can be configured to automatically detect nausea (e.g., via an external sensor). If nausea is reported, the dose of the GLP-1 RA can be maintained at the current level and no further increase is recommended. Alternatively, if nausea is reported, the dose of the GLP-1 RA can be returned to the dose of the previously administered GLP-1 RA that the user reported did not cause nausea.

[0282] In some aspects, the GLP-1 RA is also titrated based on the user’s weight. The system can determine a target weight for the user. The target weight can be input by the user, such as based on input from a HCP, or can be input directly by the HCP, or can be a default setting. The target weight can be based on BMI. The user’s weight can be determined by a smart scale. The smart scale can automatically communicate the weight measurement to the system. The system can prompt the user to weigh himself or herself. The system can prompt the user to take a weight measurement. The system can periodically (every two days, every three days, every week, and other intervals) prompt the user to take a weight measurement. Alternatively, if a weight measurement is not received within a predetermined time period, the system can prompt the user to take a weight measurement. If the user’s weight falls below the target weight, the GLP-1 RA can be recommended to no longer be increased, to avoid excessive weight loss. Alternatively, if the user’s weight falls below the target weight, the GLP-1 RA can be decreased to inhibit further weight loss.

[0283] The second dosing regimen 1440 can be configured to add a GLP-1 receptor agonist therapy or a dual GIP / GLP-1 receptor agonist therapy. In some aspects, the software application 1390 can execute the second dosing regimen 1440 if one or more user metrics are above one or more targets (e.g., average glucose, median glucose, glucose TIR, glucose TBR, glucose TVL, GMI, MMG, PPG, BBR, BeAM, ISF, weight, BMI, A1 C level, heart rate, blood pressure, or a combination thereof). In some aspects, the one or more targets can include a target basal state (e.g., MMG of about 100 mg / dL to about 130 mg / dL), a target weight, a target meal state (e.g., minimum post-dose glucose (MPDG) of about 100 mg / dL to about 120 mg / dL), a target correction ISF state (e.g., post- rapid-acting-dose correction glucose (PRA-CG) of about 70 mg / dL to about 180 mg / dL), or a combination thereof. In some aspects, the second dosing regimen 1440 can add a GLP-1 receptor agonist or a dual GIP / GLP-1 receptor agonist, either in free combination or in a fixed ratio combination with insulin (e.g., basal insulin). In some aspects, the second dosing regimen 1440 (e.g., GLP-1 or dual GIP / GLP-1) can be added to the first dosing regimen 1410 (e.g., basal insulin). For example, if one or more user metrics remain above one or more targets after the first dosing regimen 1410, or if basal insulin excess is determined for the first dosing regimen 1410, the software application 1390 can recommend adding the second dosing regimen 1440 to the first dosing regimen 1410. In some aspects, the second dosing regimen 1440 (e.g., GLP-1 or dual GIP / GLP-1) can be recommended to be added to the first dosing regimen 1410 (e.g., basal insulin). For example, if one or more user metrics remain above one or more targets after the first dosing regimen 1410, or if basal insulin excess is determined for the first dosing regimen 1410, the software application 1390 can recommend adding the second dosing regimen 1440 to the first dosing regimen 1410.

[0284] If basal insulin excess is detected and the user’s therapy regimen already includes a GLP-1 RA and is fully titrated, or there is a contraindication to GLP-1 RA, the system determines whether the user has a high pre-meal-to-post-meal glucose difference in a meal. The pre-meal-to-post-meal glucose difference can be based on the change between the glucose level at or before the start of a meal and the highest glucose level post-meal or the highest glucose level over a predetermined period post-meal (e.g., 2-5 hours).

[0285] The third dosing regimen 1450 can be configured as a mealtime insulin therapy added to a meal. In some aspects, the software application 1390 can implement the third dosing regimen 1450 if a post-meal glucose rise for a meal exceeds a predetermined threshold. In some aspects, the predetermined threshold can be defined by a total change in glucose levels (difference between minimum and maximum) from pre-meal period to post-meal period, rate of change in glucose levels (slope), post-prandial-to-pre-prandial difference, or a combination thereof. In some aspects, the mealtime insulin therapy can include a bolus insulin, RA insulin, "mealtime" insulin, aspart, glulisine, lispro, or a combination thereof. In some aspects, the third dosing regimen 1450 (e.g., mealtime insulin with a meal) can include adding a dose of mealtime insulin in the largest meal of the user. In some aspects, the third dosing regimen 1450 (e.g., mealtime insulin with a meal) can include adding a dose of mealtime insulin in the meal with the largest PPG excursion of the user. In some aspects, the third dosing regimen 1450 (e.g., mealtime insulin with a meal) can be recommended to be added to the second dosing regimen 1440 (e.g., GLP-1 or dual GIP / GLP-1). For example, the software application 1390 can recommend adding the third dosing regimen 1450 to the second dosing regimen 1440 if the post-meal glucose rise for a meal exceeds a predetermined threshold after the second dosing regimen 1440 or if basal insulin overdosing is determined for the second dosing regimen 1440.

[0286] In some aspects, the third dosing regimen 1450 can have an initial starting dose of mealtime insulin in a meal in a predetermined amount or based on a ratio or proportion of mealtime insulin to basal insulin. For example, the initial mealtime insulin dose can be about 4 U / day or about 10% of the daily basal insulin dose. In some aspects, if the user's A1C level is below 8% (e.g., about 64 mmol / mol), the third dosing regimen 1450 can recommend a reduction of the basal insulin dose by about 4 U / day or about 10% of the daily basal insulin dose. In some aspects, for hypoglycemia, the software application 1390 can determine a cause of hypoglycemia by analyzing one or more user metrics, such as based on a low blood glucose index (LBGI), time below range (TBR), number of low glucose alerts, number of very low glucose alerts, and other hypoglycemia indicators. In some aspects, if there is no clear cause of hypoglycemia (e.g., based on the metrics described above), the daily insulin dose can be reduced by about 10% to about 20% for safety reasons.

[0287] In some aspects, the prandial dose is added to the meal that causes the glucose excursion, such as the meal with the highest pre-prandial-post-prandial glucose rise. In some aspects, the prandial dose is added to the largest meal of the day.

[0288] The fourth dosing regimen 1460 can be configured as a stepwise MDI of prandial insulin therapy added with corresponding meals. If the system determines that more than one meal has a high pre-prandial-post-prandial glucose difference based on glucose data, the system can recommend adding multiple daily injections (MDI). Prandial insulin doses are added for each of two meals or three meals of the day (i.e., breakfast, lunch, and dinner), rather than for a single meal. In some aspects, the MDI is the final therapy escalation recommended by the system.

[0289] In some aspects, the one or more targets can include a target basal state (e.g., MMG of about 100 mg / dL to about 130 mg / dL and BBR < 1.5), a target meal state (e.g., MPDG of about 100 mg / dL to about 120 mg / dL), a target correction ISF state (e.g., PRA-CG of about 70 mg / dL to about 180 mg / dL), or a combination thereof. In some aspects, the fourth dosing regimen 1460 can include a stepwise MDI of prandial insulin such that the therapy includes two, then three additional injections per day (e.g., with each meal). In some aspects, the fourth dosing regimen 1460 (e.g., stepwise MDI of prandial insulin) can be recommended to be added to the third dosing regimen 1450 (e.g., prandial insulin with a meal). For example, if one or more user metrics remain above one or more targets after the third dosing regimen 1450, the software application 1390 can recommend adding the fourth dosing regimen 1460 to the third dosing regimen 1450.

[0290] The fifth dosing regimen 1480 can be configured as basal insulin and prandial insulin therapy with each meal. In some aspects, the software application 1390 can recommend adding the fifth dosing regimen 1480 if one or more user metrics are above one or more targets (e.g., average glucose, median glucose, glucose TIR, glucose TBR, glucose TVL, GMI, MMG, PPG, BBR, BeAM, ISF, weight, BMI, A1 C level, heart rate, blood pressure, or a combination thereof). In some aspects, the one or more targets can include a target basal state (e.g., MMG of about 100 mg / dL to about 130 mg / dL and BBR < 1.5), a target meal state (e.g., MPDG of about 100 mg / dL to about 120 mg / dL), a target correction ISF state (e.g., PRA-CG of about 70 mg / dL to about 180 mg / dL), or a combination thereof. In some aspects, the fifth dosing regimen 1480 (e.g., basal insulin and prandial insulin therapy with each meal) can be recommended to be added to the fourth dosing regimen 1460 (e.g., stepped MDI of prandial insulin). For example, the software application 1390 can recommend adding the fifth dosing regimen 1480 to the fourth dosing regimen 1460 if one or more user metrics remain above one or more targets after the fourth dosing regimen 1460.

[0291] FIG. 15 FIGURE illustrates therapy assessment 1430, according to example aspects. While FIG. 13 therapy assessment 1430 is shown as a standalone process, device, and / or system, aspects of the present disclosure can be used with other processes, devices, systems, and / or methods, such as, but not limited to, elements in FIG. 14A-FIG. 14C , FIG. 16-FIG. 18 , FIG. 19A-FIG. 19C , FIG. 20-FIG. 23 and FIG. 15 , for example, therapy management system 1300, software application 1390, control chart 1400A, therapy assessment 1400B, control chart 1400C, one or more dosing regimens 1410, 1440, 1450, 1460, 1480, flowchart 2000, flowchart 2100, flowchart 2200, and / or computing device 2300.

[0292] As FIG. 15As shown in FIG. 14B, therapy evaluation 1430 can include a monitoring phase 1432, a rapid titration phase 1434, a no change phase 1436, and a maintenance titration phase 1438. In some aspects, therapy evaluation 1430 can be based at least in part on a ratio of TDD of insulin to body weight of the user, glucose variability, a hypoglycemia metric, a change in glucose levels during a meal period or a nighttime period, or a combination thereof. In some aspects, therapy evaluation 1430 can be based at least in part on the ratio of TDD of insulin to body weight of the user exceeding a predetermined threshold (e.g., basal insulin dosage exceeding approximately 0.5 U / kg / day), an increase in morning (AM)-bedtime (PM) difference and / or postprandial-preprandial difference, a hypoglycemia metric below a predetermined threshold, glucose variability exceeding a predetermined threshold (e.g., preprandial rise exceeding approximately 30 mg / dL and / or postprandial spike exceeding approximately 110 mg / dL), or a combination thereof.

[0293] Monitoring phase 1432 can be configured to monitor one or more user adherence metrics of the current therapy for a predetermined period of time to ensure user compliance with the therapy. In some aspects, software application 1390 can monitor one or more of system usage, sensor wear, analyte sensor scan, medication dose administration, or a combination thereof by wirelessly tracking sensor data over time (e.g., via OBU 1350) to ensure that the user is wearing the sensor sufficiently and scanning the sensor sufficiently (e.g., tracking the number of scans with remote device 1310, collecting glucose data for a predetermined proportion of the day, glucose TBR, glucose TVL, number of low events, etc.); and by wirelessly tracking medication (dose) data over time (e.g., via medication delivery device, first smart cap 1382) to ensure that the user is dosing correctly (e.g., tracking weekly doses, time between doses, dose regularity, etc.).

[0294] In some aspects, software application 1390 can implement monitoring phase 1432 until an adherence threshold is satisfied. The adherence threshold can be satisfied based on one or more adherence metrics (e.g., as described herein) over a predetermined period of time (e.g., 3 consecutive days). In some aspects, monitoring phase 1432 can continue to be implemented without allowing any therapy changes or escalation until user compliance with the current therapy is observed (e.g., the adherence threshold is satisfied) over a period of time (e.g., 3 consecutive days).

[0295] Once the monitoring phase is complete, the application proceeds to a rapid titration phase 1434. During the rapid titration phase 1434, the system recommends drug doses at a first interval, such as once per day. The rapid titration phase 1434 can titrate the dose by a fixed increment, for example, increasing or decreasing a fixed number of units, or increasing or decreasing a fixed percentage of the current dose. In some aspects, the rapid titration phase 1434 can be configured to apply a risk-based rapid dose adjustment to the first dosing regimen 1410. In some aspects, the dose adjustment can be proportional to the deviation of the glucose metrics from the corresponding target, for example, if the glucose metrics are far from the target, then a larger dose adjustment can be recommended than if the glucose metrics are close to the target value. In some aspects, the user administers a drug dose, and the system can determine one or more user metrics over a period of time after the administration of the dose to determine whether the user’s glucose control is improved and within the target level or target range of the one or more glucose metrics. If the glucose metrics are not within the target range, then the system can recommend an increase or decrease in the drug dose. The system can also monitor one or more drug (dosing) data during the rapid titration phase 1434 to titrate within the standard dosing range of the drug. The system can generate a notification to the user and / or to the HCP to adjust the dose of the drug.

[0296] In some aspects, during the rapid titration phase 1434, the software application 1390 can recommend adjusting the dose of basal insulin at a first interval, for example, on a daily or every 24 hour basis. In some aspects, the software application 1390 can monitor the user’s response to therapy during the rapid titration phase 1434 by determining one or more glucose metrics as discussed herein and comparing these metrics to target levels or ranges. For example, the system can wirelessly track sensor glucose data over time (e.g., track the distance of fasting or morning glucose from the target range, glucose TAR, glucose TBR, etc.) and drug (dosing) data over time (e.g., track LA insulin dosed the previous day, no nocturnal hyperglycemia and / or hypoglycemia treatment, sufficient nocturnal and / or morning data, sufficient time between last LA dose and morning glucose, etc.). In some aspects, any day of glucose hypoglycemia during the rapid titration phase 1434, as can be determined based on the TBR exceeding a TBR threshold, the number of low glucose alerts exceeding a predetermined number of low glucose alerts, will cause the software application 1390 to recommend a reduction in the dose of basal insulin by a predetermined amount (e.g., by about 10% to about 20%) to attempt to correct the low glucose.

[0297] In some aspects, the software application 1390 can implement the rapid titration phase 1434 for a period of time, e.g., a 3-day cycle. In some aspects, the rapid titration phase 1434 can be implemented for 3 consecutive days of dosing (e.g., basal insulin) and glucose sufficiency. In some aspects, the rapid titration phase 1434 can continue to be implemented without allowing any therapy changes or escalation until the user exhibits adequate glucose control (e.g., glucose metrics meet one or more targets or lie within a range thereof) for a predetermined period of time, e.g., 3 consecutive days of dosing and glucose sufficiency.

[0298] The no change phase 1436 can be configured to monitor the user’s response to the first dosing regimen 1410 (e.g., basal insulin). The no change phase 1436 can also be configured to monitor any side effects of the first dosing regimen 1410. In some aspects, the software application 1390 can monitor one or more basal states 1436a-1436h during the no change phase 1436 as well as from a target basal state (e.g., MMG of about 100 mg / dL to about 130 mg / dL) and a range thereof over time. In some aspects, the software application 1390 can monitor the user’s response to therapy during the no change phase 1436 by wirelessly tracking sensor data (e.g., tracking overall glucose TBR, glucose TVL, MMG, BeAM, basal insulin excess indicators, etc.) over time as well as by wirelessly tracking medication (dosing) data (e.g., tracking treatment nocturnal lows) over time.

[0299] In some aspects, the software application 1390 can implement the no change phase 1436 for a period of time, e.g., a no change cycle. In some aspects, the no change phase 1436 can be implemented for 4 consecutive no change outputs (e.g., basal states 1436a-1436h). In some aspects, the no change phase 1436 can continue to be implemented without allowing any therapy changes or escalation until the user exhibits no changes (e.g., no side effects) for a consecutive period of time, e.g., for the first 4 consecutive no change outputs.

[0300] As FIG. 16As shown in FIG. 14, the no change phase 1436 can be continuous no change based on one or more basal states 1436a-1436h. In some aspects, the one or more basal states 1436a-1436h can include a first basal state 1436a (e.g., far below target), a second basal state 1436b (e.g., significantly below target), a third basal state 1436c (e.g., below target), a fourth basal state 1436d (e.g., target), a fifth basal state 1436e (e.g., above target), a sixth basal state 1436f (e.g., significantly above target), a seventh basal state 1436g (e.g., far above target, saturation), an eighth basal state 1436h (e.g., basal insulin excess), or a combination thereof.

[0301] In some aspects, the first basal state 1436a can be determined based on a total glucose TBR greater than about 4% or a glucose TVL less than about 1%. In some aspects, the second basal state 1436b can be determined based on an MMG less than about 80 mg / dL or a treatment nocturnal low greater than about 30 minutes. In some aspects, the third basal state 1436c can be determined based on an MMG of about 80 mg / dL to about 100 mg / dL or a BeAM less than about -20 mg / dL / hour. In some aspects, the fourth basal state 1436d can be determined based on an MMG of about 100 mg / dL to about 130 mg / dL. In some aspects, the fifth basal state 1436e can be determined based on an MMG of about 130 mg / dL to about 150 mg / dL. In some aspects, the sixth basal state 1436f can be determined based on an MMG of about 150 mg / dL to about 180 mg / dL. In some aspects, the seventh basal state 1436g can be determined based on an MMG greater than about 180 mg / dL. In some aspects, the eighth basal state 1436h can be determined by the therapy assessment 1430 or one or more of the basal insulin excess metrics described above (e.g., ratio of TDD to weight, glucose variability, hypoglycemia metrics, change in glucose in meal period, change in glucose in nocturnal period).

[0302] Once the rapid titration phase is complete, the software application 1390 (e.g., an algorithm) proceeds to a maintenance titration phase 1438. The maintenance titration phase 1438 can be configured to apply the first dosing regimen 1410 (e.g., basal insulin) over an extended period of time and monitor the user’s response to therapy. The maintenance titration phase 1438 can also be configured to account for large-scale changes in the user’s life (e.g., adapting to new diet and / or exercise, adding a new anti-diabetic medication, ongoing changes in insulin sensitivity). In some aspects, during the maintenance titration phase 1438, the software application 1390 can recommend increasing the dose much more slowly than decreasing the dose. For example, a single day of TBR that is too high can result in a recommendation to decrease the daily dose, but can require a pattern of multiple days of high MMG to recommend an increase in the dose. In some aspects, the software application 1390 can monitor the user’s response to therapy during the maintenance titration phase 1438 by determining one or more glucose metrics as discussed herein and comparing these metrics to target levels or ranges. For example, the system can wirelessly track sensor glucose data over time (e.g., tracking average glucose, weekly average glucose, glucose TIR, etc.) as well as drug (dosing) data over time (e.g., tracking time between doses, time between last LA dose, no nocturnal hyperglycemia and / or hypoglycemia treatment, adequate nighttime and / or morning data, adequate time between last RA dose and morning glucose, etc.).

[0303] In some aspects, the software application 1390 can implement the maintenance titration phase 1438 for a period of time, e.g., a 14-day cycle. In some aspects, the maintenance titration phase 1438 can be conducted for 12 days of dosing (e.g., basal insulin) with adequate glucose control over 14 days. In some aspects, the maintenance titration phase 1438 can continue to be implemented without allowing any therapy changes or escalation until the user exhibits adequate glucose control (e.g., glucose metrics meet one or more targets or lie within a range thereof) over a predetermined period of time (e.g., 12 days of dosing with adequate glucose control over 14 days).

[0304] FIG. 16 FIG. 14 illustrates a second dosing regimen 1440, according to example aspects. While the second dosing regimen 1440 is shown as a separate process, device, and / or system in FIG. 13 , aspects of the present disclosure can be used with other processes, devices, systems, and / or methods, such as, but not limited to FIG. 14A-FIG. 14C , FIG. 15 , FIG. 17 , FIG. 18 , FIG. 19A-FIG. 19C , FIG. 20-FIG. 23 , and FIG. 15Elements in the system, such as a therapy management system 1300, a software application 1390, a control chart 1400A, a therapy assessment 1400B, a control chart 1400C, a therapy assessment 1430, one or more dosing regimens 1410, 1450, 1460, 1480, a flowchart 2000, a flowchart 2100, a flowchart 2200, and / or a computing device 2300.

[0305] For example, FIG. 17 The aspects of the treatment assessment 1430 shown are related to FIG. 15 The aspects of the second dosing regimen 1440 shown may be similar. Similar reference numerals are used to indicate... FIG. 17 The characteristics of various aspects of the treatment assessment 1430 shown are as follows: FIG. 15 Features of various aspects of the second dosing regimen 1440 shown. FIG. 17 The treatment assessment 1430 shown in the figure is related to... FIG. 17 One difference between the aspects of the second dosing regimen 1440 shown is that the second dosing regimen 1440 includes a GLP-1 receptor antagonist or a dual GIP / GLP-1 receptor antagonist and a rapid titration phase 1444 (e.g., 6 days of dosing over 7 days with adequate glucose), instead of having basal insulin, a rapid titration phase 1434, and a no-change phase 1436 as in the therapy evaluation 1430.

[0306] like FIG. 18 As shown, the second dosing regimen 1440 may include a monitoring phase 1442, a rapid titration phase 1444, and a maintenance titration phase 1446. The monitoring phase 1442 may be configured to monitor one or more user compliance metrics of the current therapy over a predetermined time period to ensure user adherence to the therapy. The rapid titration phase 1444 may be configured to introduce and apply a rapid dose of the second dosing regimen 1440 (e.g., a GLP-1 receptor antagonist or both a dual GIP / GLP-1 receptor antagonist and LA insulin) and monitor the user's response to the additional therapy. The maintenance titration phase 1446 may be configured to apply the second dosing regimen 1440 (e.g., a GLP-1 receptor antagonist or both a dual GIP / GLP-1 receptor antagonist and LA insulin) over an extended time period and monitor the user's response to the therapy.

[0307] FIG. 18 The illustration shows a third dosing regimen 1450 according to an exemplary aspect. Although FIG. 13 The third dosing regimen 1450 is shown as a standalone treatment, apparatus, and / or system, but aspects of this disclosure can be used with other treatments, apparatus, systems, and / or methods, such as, but not limited to, those described above. FIG. 14A-FIG. 14C , FIG. 15-FIG. 17 , FIG. 19A-FIG. 19C ,FIG. 20-FIG. 23 , FIG. 15 , FIG. 18 and FIG. 15 the elements shown in FIG. 13, such as therapy management system 1300, software application 1390, control chart 1400A, therapy assessment 1400B, control chart 1400C, therapy assessment 1430, one or more dosing regimens 1410, 1440, 1460, 1480, flowchart 2000, flowchart 2100, flowchart 2200, and / or computing device 2300.

[0308] Aspects of therapy assessment 1430 shown in FIG. 14B can be similar to aspects of therapy assessment 1430 shown in FIG. 14A. Like reference numbers are used to indicate features of aspects of therapy assessment 1430 shown in FIG. 14B and aspects of therapy assessment 1430 shown in FIG. 14A. FIG. 18 Aspects of therapy assessment 1430 shown in FIG. 14B can be similar to aspects of therapy assessment 1430 shown in FIG. 14A. Like reference numbers are used to indicate features of aspects of therapy assessment 1430 shown in FIG. 14B and aspects of therapy assessment 1430 shown in FIG. 14A. FIG. 15 Aspects of therapy assessment 1430 shown in FIG. 14B can be similar to aspects of therapy assessment 1430 shown in FIG. 14A. Like reference numbers are used to indicate features of aspects of therapy assessment 1430 shown in FIG. 14B and aspects of therapy assessment 1430 shown in FIG. 14A. FIG. 18 Aspects of therapy assessment 1430 shown in FIG. 14B can be similar to aspects of therapy assessment 1430 shown in FIG. 14A. Like reference numbers are used to indicate features of aspects of therapy assessment 1430 shown in FIG. 14B and aspects of therapy assessment 1430 shown in FIG. 14A. FIG. 18 Aspects of therapy assessment 1430 shown in FIG. 14B can be similar to aspects of therapy assessment 1430 shown in FIG. 14A. Like reference numbers are used to indicate features of aspects of therapy assessment 1430 shown in FIG. 14B and aspects of therapy assessment 1430 shown in FIG. 14A. FIG. 18 Aspects of therapy assessment 1430 shown in FIG. 14B can be similar to aspects of therapy assessment 1430 shown in FIG. 14A. Like reference numbers are used to indicate features of aspects of therapy assessment 1430 shown in FIG. 14B and aspects of therapy assessment 1430 shown in FIG. 14A. FIG. 19A One difference between aspects of therapy assessment 1430 shown in FIG. 14B and aspects of third dosing regimen 1450 shown in FIG. 14C is that third dosing regimen 1450 includes mealtime insulin with a meal, rather than therapy assessment 1430 having basal insulin and a no-change phase 1436.

[0309] As shown in FIG. 14C, third dosing regimen 1450 can include a monitoring phase 1452, a rapid titration phase 1454, and a maintenance titration phase 1456. Monitoring phase 1452 can be configured to monitor one or more user adherence metrics of a current therapy for a predetermined period of time to ensure user adherence to the therapy. Rapid titration phase 1454 can be configured to introduce and apply a rapid dose of third dosing regimen 1450 (e.g., mealtime insulin with a meal) and monitor user response to the additional therapy. Maintenance titration phase 1456 can be configured to apply third dosing regimen 1450 (e.g., mealtime insulin with a meal) for an extended period of time and monitor user response to the therapy. FIG. 19B

[0310] FIG. 15 illustrates a fourth dosing regimen 1460, according to example aspects. While FIG. 19C Aspects of the present disclosure can be used with other processes, devices, systems, and / or methods, such as, but not limited to, those shown in FIGS. 1, FIG. 19A , FIG. 19A , FIG. 13 , FIG. 14A-FIG. 14C , FIG. 15-FIG. 18 and FIG. 20-FIG. 23Elements in the system, such as a therapy management system 1300, a software application 1390, a control chart 1400A, a therapy assessment 1400B, a control chart 1400C, a therapy assessment 1430, one or more dosing regimens 1410, 1440, 1450, 1480, a flowchart 2000, a flowchart 2100, a flowchart 2200, and / or a computing device 2300.

[0311] For example, FIG. 19A The treatment assessment 1430 shown in the figure is related to... FIG. 19B The aspects of the fourth dosing regimen 1460 shown may be similar. Similar reference numerals are used to indicate... FIG. 19B The characteristics of various aspects of the treatment assessment 1430 shown are as follows: FIG. 13 The fourth dosing regimen 1460 shown has similar features in various aspects. FIG. 14A-FIG. 14C The treatment assessment 1430 shown in the figure is related to... FIG. 15-FIG. 18 One difference between the aspects of the fourth dosing regimen 1460 shown is that the fourth dosing regimen 1460 includes a stepwise MDI of prandial insulin with multiple meals and a maintenance titration phase 1466, which includes a basal assessment 1467, a meal assessment 1468, and a corrected ISF assessment 1469, instead of a therapy assessment 1430 with basal insulin, a basal state 1436a-1436h of no change phase 1436, and a maintenance titration phase 1438.

[0312] like FIG. 20-FIG. 23 As shown, the fourth dosing regimen 1460 may include a monitoring phase 1462, a rapid titration phase 1464, and a maintenance titration phase 1466. The monitoring phase 1462 may be configured to monitor one or more user compliance metrics of the current therapy over a predetermined time period to ensure user adherence to the therapy. The rapid titration phase 1464 may be configured to introduce and apply a rapid dose of the fourth dosing regimen 1460 (e.g., a step-through MDI of bolus insulin with multiple meals) and monitor the user's response to the additional therapy. The maintenance titration phase 1466 may be configured to apply the fourth dosing regimen 1460 (e.g., a step-through MDI of bolus insulin with multiple meals) over an extended time period and monitor the user's response to the therapy.

[0313] like FIG. 19B As shown, the maintenance titration phase 1466 may include basal assessment 1467, meal assessment 1468, and / or corrected ISF assessment 1469. In some aspects, basal assessment 1467, meal assessment 1468, and / or corrected ISF assessment 1469 may be used in conjunction with one or more dosing regimens (e.g., control chart 1400A) to determine basal insulin overdose and / or monitor any changes or side effects of the current therapy.

[0314] Basic assessment 1467 can be configured to monitor one or more basic states (e.g., FIG. 19C Changes in the basal state (1467a-1467h) shown in the figure, for example, during the maintenance titration phase 1466. The basal assessment 1467 can also be configured to determine basal insulin overdose and any changes or side effects of the current therapy. The basal assessment 1467 can also be configured to assist the software application 1390 in determining any trends in the basal state over time (e.g., increase, decrease, no change) and whether any mealtime actions and / or corrective actions should be recommended.

[0315] Meal rating 1468 can be configured to monitor the status of one or more meals (e.g., FIG. 19C Changes in meal status (1468a-1468h) as shown in the diagram, for example, during the maintenance titration phase 1466. Meal assessment 1468 can also be configured to determine basal insulin overdose and any changes or side effects of the current therapy. Meal assessment 1468 can also be configured to assist software application 1390 in determining any trends in meal status over time (e.g., increase, decrease, no change) and whether any basal and / or corrective actions should be recommended.

[0316] The calibration ISF assessment 1469 can be configured to monitor the status of one or more calibration ISFs (e.g., FIG. 13 Any changes in the corrected ISF status (1469a-1469e) shown, for example, during the maintenance titration phase 1466. The corrected ISF assessment 1469 can also be configured to determine basal insulin overdose and any changes or side effects of the current therapy. The corrected ISF assessment 1469 can also be configured to assist the software application 1390 in determining any trends in the corrected ISF status over time (e.g., increase, decrease, no change) and whether any basal and / or mealtime activities should be recommended.

[0317] FIG. 14A-FIG. 14C The illustration shows the basic assessment 1467 based on exemplary aspects. Although FIG. 15-FIG. 18 The basic assessment 1467 is presented as an independent process, apparatus, and / or system, but aspects of this disclosure can be used with other processes, apparatus, systems, and / or methods, such as, but not limited to, those described above. FIG. 20-FIG. 23 , FIG. 19C , Exemplary flowchart and FIG. 20Elements in the system, such as a therapy management system 1300, a software application 1390, a control chart 1400A, a therapy assessment 1400B, a control chart 1400C, a therapy assessment 1430, one or more dosing regimens 1410, 1440, 1450, 1460, 1480, a flowchart 2000, a flowchart 2100, a flowchart 2200, and / or a computing device 2300.

[0318] like FIG. 13 As shown, the baseline assessment 1467 may include monitoring one or more baseline states 1467a-1467h. In some aspects, one or more baseline states 1467a-1467h may include a first baseline state 1467a (e.g., well below target), a second baseline state 1467b (e.g., significantly below target), a third baseline state 1467c (e.g., below target), a fourth baseline state 1467d (e.g., target), a fifth baseline state 1467e (e.g., above target), a sixth baseline state 1467f (e.g., significantly above target), a seventh baseline state 1467g (e.g., well above target, saturated), an eighth baseline state 1467h (e.g., basal insulin excess), or a combination thereof.

[0319] In some respects, the first baseline state 1467a can be determined based on a total glucose total blood glucose (TBR) greater than approximately 4% or a total glucose total blood glucose (TVL) less than approximately 1%. In some respects, the second baseline state 1467b can be determined based on an MMG level less than approximately 80 mg / dL or a therapeutic nocturnal low greater than approximately 30 minutes. In some respects, the third baseline state 1467c can be determined based on an MMG level of approximately 80 mg / dL to approximately 100 mg / dL or a BeAM level less than approximately -20 mg / dL / hour, or an MMG level of approximately 100 mg / dL to approximately 130 mg / dL and a BBR greater than or equal to approximately 1.5. In some respects, the fourth baseline state 1467d can be determined based on an MMG level of approximately 100 mg / dL to approximately 130 mg / dL and a BBR less than approximately 1.5. In some respects, the fifth baseline state 1467e can be determined based on an MMG level of approximately 130 mg / dL to approximately 150 mg / dL. In some respects, the sixth basal state 1467f can be determined based on an MMG of approximately 150 mg / dL to approximately 180 mg / dL. In some respects, the seventh basal state 1467g can be determined based on an MMG greater than approximately 180 mg / dL or a BBR less than approximately 0.5. In some respects, the eighth basal state 1467h can be determined by therapy assessment 1430 or by one or more of the aforementioned basal insulin excess measures (e.g., TDD to body weight ratio, glucose variability, hypoglycemia measure, changes in glucose during mealtimes, changes in glucose during the nighttime).

[0320] FIG. 20 FIG. 16 illustrates a meal assessment 1468, according to example aspects. While FIG. 20 The meal assessment 1468 is shown as a standalone process, device, and / or system in FIG. 13 , FIG. 14A-FIG. 14C , FIG. 15-FIG. 18 and elements in FIG. 19A-FIG. 19C , e.g., the therapy management system 1300, the software application 1390, the control chart 1400A, the therapy assessment 1400B, the control chart 1400C, the therapy assessment 1430, the one or more dosing regimens 1410, 1440, 1450, 1460, 1480, the flowchart 2000, the flowchart 2100, the flowchart 2200, and / or the computing device 2300.

[0321] As shown in FIG. 23 , the meal assessment 1468 can include monitoring one or more meal states 1468a- 1468h. In some aspects, the one or more meal states 1468a-1468h can include a first meal state 1468a (e.g., significantly below target), a second meal state 1468b (e.g., below target), a third meal state 1468c (e.g., target), a fourth meal state 1468d (e.g., above target), a fifth meal state 1468e (e.g., significantly above target), a sixth meal state 1468f (e.g., far above target), a seventh meal state 1468g (e.g., satiation), an eighth meal state 1468h (e.g., basal insulin excess), or a combination thereof.

[0322] In some aspects, the first meal state 1468a can be determined based on a total glucose TBR greater than about 4% or a glucose TVL less than about 1% or an MPDG less than about 70 mg / dL. In some aspects, the second meal state 1468b can be determined based on an MPDG of about 70 mg / dL to about 100 mg / dL or a glucose TBR greater than about 4%. In some aspects, the third meal state 1468c can be determined based on an MPDG of about 100 mg / dL to about 120 mg / dL. In some aspects, the fourth meal state 1468d can be determined based on an MPDG of about 120 mg / dL to about 140 mg / dL. In some aspects, the fifth meal state 1468e can be determined based on an MPDG of about 140 mg / dL to about 180 mg / dL. In some aspects, the sixth meal state 1468f can be determined based on an MPDG of about 180 mg / dL to about 250 mg / dL. In some aspects, the seventh meal state 1468g can be determined based on an MPDG greater than about 250 mg / dL. In some aspects, the eighth meal state 1468h can be determined by the therapy assessment 1430 or by one or more of the basal glucose excess metrics described above (e.g., ratio of TDD to weight, glucose variability, hypoglycemia metrics, change in glucose during meal period, change in glucose at night).

[0323] FIG. 20 FIGURE illustrates a correction ISF assessment 1469, according to example aspects. While FIG. 13 the correction ISF assessment 1469 is shown as a separate process, device, and / or system in the middle, aspects of the present disclosure can be used with other processes, devices, systems, and / or methods, such as, but not limited to, elements in FIG. 14A-FIG. 14C , FIG. 15-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 21-FIG. 23 , e.g., the therapy management system 1300, the software application 1390, the control chart 1400A, the therapy assessment 1400B, the control chart 1400C, the therapy assessment 1430, the one or more dosing regimens 1410, 1440, 1450, 1460, 1480, the flowchart 2000, the flowchart 2100, the flowchart 2200, and / or the computing device 2300.

[0324] As FIG. 13-FIG. 18As shown, the corrected ISF assessment 1469 may include monitoring one or more corrected ISF states 1469a-1469e. In some aspects, one or more corrected ISF states 1469a-1469e may include a first corrected ISF state 1469a (e.g., below target), a second corrected ISF state 1469b (e.g., target), a third corrected ISF state 1469c (e.g., above target), a fourth corrected ISF state 1469d (e.g., significantly above target), a fifth corrected ISF state 1469e (e.g., basal insulin excess), or a combination thereof.

[0325] In some respects, the first corrected ISF status 1469a can be determined based on a total glucose TBR greater than approximately 4%, a glucose TVL less than approximately 1%, or an MPDG less than approximately 70 mg / dL. In some respects, the second corrected ISF status 1469b can be determined based on a PRA-CG of approximately 70 mg / dL to approximately 180 mg / dL. In some respects, the third corrected ISF status 1469c can be determined based on a PRA-CG of approximately 180 mg / dL to approximately 250 mg / dL. In some respects, the fourth corrected ISF status 1469d can be determined based on a PRA-CG greater than approximately 250 mg / dL. In some respects, the fifth corrected ISF status 1469e can be determined by a therapy assessment 1430 or by one or more of the aforementioned basal insulin excess measures (e.g., the ratio of TDD to body weight, glucose variability, hypoglycemia measures, changes in glucose during mealtimes, changes in glucose during nighttime periods).

[0326] FIG. 19A-FIG. 19C

[0327] FIG. 23 A flowchart 2000 is illustrated according to an exemplary aspect. For example, flowchart 2000 can be used for... FIG. 13-FIG. 18 The therapy management system 1300 is shown. Flowchart 2000 can be configured to measure one or more metrics (e.g., glucose metric, therapy metric) of a first therapy (e.g., basal insulin) and titrate the dose of the first therapy based at least in part on the one or more metrics. Flowchart 2000 can also be configured to determine basal insulin overdose of the first therapy based on the one or more metrics. If basal insulin overdose is determined, or if one or more user metrics remain outside one or more targets (e.g., one or more glucose metrics, A1C level, weight), then flowchart 2000 can also be configured to output a recommendation to add a second therapy (e.g., insulin analog, GLP-1, prandial insulin, MDI of prandial insulin, etc.).

[0328] It should be recognized that this is not the case. FIG. 19A-FIG. 19CAll of the steps in the method 2000 are required to perform the disclosure provided herein. Additionally, some of the steps can be performed simultaneously, sequentially, and / or in a different order than shown in the method 2000. The method 2000 will be described with reference to FIG. 23 , FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C , FIG. 23 , FIG. 13-FIG. 18 , and FIG. 19A-FIG. 19C . However, the method 2000 is not limited to those example aspects. While the method 2000 is shown as a standalone method in FIG. 23 , aspects of the disclosure can be used with other processes, apparatuses, systems, and / or methods, such as, but not limited to, elements in FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C , FIG. 23 , FIG. 13-FIG. 18 , and FIG. 19A-FIG. 19C , for example, the control chart 1400A, the therapy assessment 1400B, the control chart 1400C, the therapy assessment 1430, the one or more dosing regimens 1410, 1440, 1450, 1460, 1480, the flowchart 2100, the flowchart 2200, and / or the computing device 2300. In some aspects, the method 2000 can be implemented by the software application 1390. In some aspects, the method 2000 can be implemented by one or more models or algorithms running on one or more processors and / or computing devices based on one or more instructions stored in one or more memories.

[0329] In step 2002, glucose data for a user can be received from an in vivo glucose monitoring device, as shown in the examples of FIG. 23 , FIG. 13-FIG. 18 , and FIG. 19A-FIG. 19C . In some aspects, the glucose data can be received from the OBU 1350 of the therapy management system 1300 (e.g., via the software application 1390).

[0330] In step 2004, the glucose data can be analyzed to determine a glucose trend for the user, as shown in the examples of FIG. 23 , FIG. 13-FIG. 18 , and FIG. 19A-FIG. 19C .As shown in the example, first therapy information can be received. In some aspects, the first therapy may include basal insulin. In some aspects, first therapy information can be received from a drug delivery device of the therapy management system 1300 (e.g., a first pen 1360, a second pen 1370, an insulin pump, a smart vial, etc.) (e.g., via a software application 1390). In some aspects, the first therapy information may include one or more user metrics, including but not limited to user input, user feedback, data from the drug delivery device, weight measurement, applied dose, TDD, the ratio of TDD to body weight, time between administrations, type of drug, side effects of the first therapy, BMI, heart rate, blood pressure, meal data, exercise data, or combinations thereof.

[0331] In step 2006, as FIG. 23 , FIG. 13-FIG. 18 and FIG. 19A-FIG. 19C As shown in the example, one or more glucose measures can be calculated based on glucose data. In some aspects, the software application 1390 of the therapy management system 1300 can receive glucose data and calculate one or more glucose measures. In some aspects, one or more glucose measures may include mean glucose, glucose TIR, glucose TBR, glucose TVL, GMI, MMG, MPDG, PPG, BeAM, changes in glucose levels during mealtimes or nighttime periods, postprandial glucose elevation after one or more meals, or combinations thereof.

[0332] In step 2008, as FIG. 23 , ​ and ​ As shown in the example, the dose of basal insulin can be titrated based on one or more glucose measures. In some aspects, the software application 1390 of the therapy management system 1300 can titrate the dose of basal insulin based on one or more glucose measures.

[0333] In step 2010, as ​ , ​ and ​ As shown in the example, basal insulin overdose of the first therapy can be determined based on one or more of glucose data and first therapy information. In some aspects, the software application 1390 of the therapy management system 1300 can determine whether basal insulin overdose has occurred based on one or more of glucose data and first therapy information. In some aspects, the software application 1390 can determine basal insulin overdose based at least in part on the ratio of insulin TDD to user body weight, glucose variability, hypoglycemia measure, changes in glucose levels during mealtimes or nighttime periods, or combinations thereof.

[0334] In step 2012, as ​ ,​ and ​ As shown in the example of FIG. 21, when a basal insulin excess is determined, a recommendation to add a second therapy can be output. In some aspects, the software application 1390 of the therapy management system 1300 can output a recommendation to add or initiate a second therapy to the user or HCP (e.g., via the remote device 1310). In some aspects, the second therapy can include a basal analog, a GLP-1 receptor agonist, a dual GIP / GLP-1 receptor agonist, a prandial insulin, an MDI of prandial insulin, or a combination thereof.

[0335] In some aspects, the flowchart 2000 can further include recommending a reduction in the basal insulin dose when the second therapy is added. In some aspects, the flowchart 2000 can further include titrating the dose of the second therapy. In some aspects, for example, titrating the dose of the second therapy can include receiving user input (e.g., feedback) regarding any side effects of the second therapy and recommending an increased dose when the user input indicates no side effects (e.g., within a monitoring period (e.g., 14 days)). In some aspects, for example, titrating the dose of the second therapy can include receiving a body weight measurement of the user (e.g., via a body weight scale in communication with the software application 1390) and recommending an increased dose when the body weight measurement is above a target body weight (e.g., 80 kg).

[0336] In some aspects, the flowchart 2000 can further include recommending initiating a prandial (bolus) insulin dose for a first meal when the postprandial glucose rise for the meal exceeds a threshold. In some aspects, the flowchart 2000 can further include recommending initiating a prandial (bolus) insulin dose for multiple meals (e.g., an MDI) when the postprandial glucose rise for the multiple meals exceeds a threshold.

[0337] Exemplary non-compliance detection

[0338] Users can intentionally or unintentionally not adhere to the dose guidance system and its recommendations. If the user does not take the recommended dose, such as missing a dose or taking another dose amount, the titration algorithm is ineffective. Additionally, if the system recommends a dose and the user’s glucose level remains high due to non-compliance, the system can continue to recommend higher and higher doses. If the user decides to take a dose after a period of non-compliance, the dose can be too high and can be unsafe.

[0339] It would be beneficial to detect when a user is not adhering to the dose guidance and to encourage the user to start taking the recommended dose or otherwise provide guidance to the user to educate them and improve therapy adherence.

[0340] Some embodiments described herein relate to determining non-adherence to therapy recommendations. The system can determine non-adherence based on an analysis of glucose metrics before and after a dose recommendation. The system can determine non-adherence based on determining glucose metrics before and after a dose recommendation and determining whether the glucose metrics changed. The system can also determine an expected change and compare the actual change to the expected change to determine adherence.

[0341] The system can determine a lowest glucose metric over a first time period before a dose recommendation and can determine a lowest glucose metric over a second time period after a dose recommendation. The lowest glucose metric can be based on a fasting glucose level. If the change in the lowest glucose metric is less than a threshold change in the lowest glucose metric, then the system can determine non-adherence. This is because it is expected that administering the recommended dose would result in a change in the lowest glucose metric. Thus, no change or a small change can indicate that the user did not administer the recommended dose. The system can detect whether an increased dose recommendation resulted in a decrease in glucose levels or glucose metrics. Alternatively, the system can detect whether a decreased dose recommendation resulted in an increase in glucose levels or glucose metrics. A change in the expected direction can be sufficient to confirm adherence to therapy, while if the glucose levels increased despite an increased dose recommendation, then it can indicate non-adherence. The system can predict an expected range of glucose levels or an expected range of glucose metrics for a given dose recommendation. The system can determine whether the actual glucose levels after following the dose recommendation are within the predicted range of values to determine adherence. Once non-adherence is detected, the system can initiate one or more remedial actions.

[0342] The lowest glucose metric can be the minimum morning glucose (MMG). The longest fasting period is typically the nighttime period when the user is sleeping. Thus, MMG can be used instead of fasting glucose by measuring glucose levels in a morning window, such as from 4 AM to 8 AM, although other windows can be used. Using MMG can require the system to have more information about the user, such as to confirm when the user is awake or sleeping, to ensure that the morning glucose levels are a good proxy for fasting glucose levels. Additionally, MMG can not be a good proxy for fasting glucose when the user has atypical sleep times, such as a shift worker working overnight, or when the user is traveling in different time zones, or otherwise maintaining irregular sleep times. Another metric is the daily minimum hourly average glucose (DMHAG). The average glucose level can be calculated for each hour of the day, and the daily minimum hourly average can be the lowest average glucose level in the day. This metric can be beneficial because it does not require identifying a fasting period, or that the fasting period occurs at a particular time of day. However, DMHAG is only applicable to patients receiving a basal-only insulin therapy regimen, as prandial bolus insulin taken for meal intake would affect low glucose levels in addition to basal insulin.

[0343] The system as described below can detect user non-adherence to a dose recommendation based on glucose data. In some aspects, the system can receive glucose data before and after an administered dose to determine whether the user adhered to a dosing regimen. In some aspects, the system can calculate one or more glucose metrics before and after an administered dose. In some aspects, the system can calculate one or more minimum glucose metrics before and after an administered dose. In some aspects, for example, the minimum glucose metric can be MMG. In some aspects, for example, the minimum glucose metric can be DMHAG.

[0344] In some aspects, the system can determine whether the user adhered or non-adhered to a dosing regimen (e.g., a recommended dose) based on whether one or more minimum glucose metrics changed by a predetermined amount (e.g., MMG is outside of a predicted range of levels). In some aspects, the system can determine whether the user adhered or non-adhered to a dosing regimen (e.g., a recommended dose) based on whether one or more glucose metrics changed in the correct direction. For example, for an increased dose amount, if a decrease in glucose level is measured, then adherence can be determined. In some aspects, the system can determine whether the user adhered or non-adhered to a dosing regimen by predicting what level the glucose level and / or one or more glucose metrics should reach after an administered dose and whether the measured glucose data and / or one or more glucose metrics is outside of the predicted range. In some aspects, the system can determine whether the user adhered or non-adhered to a dosing regimen based on historical glucose data to determine a change in glucose level after each administered dose and / or a change in one or more glucose metrics after each administered dose. In some aspects, for example, the system can predict and / or infer the impact of a unit dose change based on the determined change in glucose level after each administered dose and / or the change in one or more glucose metrics after each administered dose.

[0345] FIG. 21 A flowchart 2100 is illustrated in accordance with example aspects. For example, the flowchart 2100 can be used in a therapy management system 1300 as shown in FIG. 13. FIG. 13 The flowchart 2100 can be configured to measure one or more metrics (e.g., minimum glucose metrics) of a first therapy (e.g., basal insulin) and titrate a dose of the first therapy based at least in part on the one or more metrics. The flowchart 2100 can also be configured to determine that a user did not adhere to one or more dose recommendations, e.g., did not adhere to one or more basal insulin dose recommendations. The flowchart 2100 can also be configured to output an indication or notification (e.g., to a user, to a third party, etc.) that titration of basal insulin will stop if a change in a minimum glucose metric (e.g., fasting glucose, daily minimum glucose (DMG), minimum morning glucose (MMG), daily minimum hourly average glucose (DMHAG), etc.) is outside of a predetermined metric.

[0346] It is recognized that not all of the steps in FIG. 21 are required to perform the disclosure provided herein. Additionally, some of the steps therein can be performed simultaneously, sequentially, and / or in a different order than shown in FIG. 21 . Flowchart 2100 will be described with reference to FIG. 13 , FIG. 14A-FIG. 14C , FIG. 15-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 . However, flowchart 2100 is not limited to those example aspects. While flowchart 2100 is shown as a standalone method in FIG. 21 , aspects of the present disclosure can be used with other processes, apparatuses, systems, and / or methods, such as, but not limited to, elements in FIG. 13 , FIG. 14A-FIG. 14C , FIG. 15-FIG. 18 , FIG. 19A-FIG. 19C , FIG. 20 , FIG. 22 and FIG. 23 , e.g., control chart 1400A, therapy assessment 1400B, control chart 1400C, therapy assessment 1430, one or more dosing regimens 1410, 1440, 1450, 1460, 1480, flowchart 2000, flowchart 2200, and / or computing device 2300. In some aspects, flowchart 2100 can be implemented by software application 1390. In some aspects, flowchart 2100 can be implemented by one or more models or algorithms running on one or more processors and / or computing devices based on one or more instructions stored in one or more memories.

[0347] In step 2102, as shown in the examples of FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 , glucose data for a user can be received from an in vivo glucose monitoring device. In some aspects, the glucose data can be received from OBU 1350 of therapy management system 1300 (e.g., via software application 1390).

[0348] In step 2104, as shown in the examples of FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 , a first dose of basal insulin can be recommended.

[0349] In step 2106, as shown in the examples of FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 , a second dose of basal insulin can be recommended.In the example shown in FIG. 13, one or more glucose metrics can be calculated based on the glucose data. The one or more glucose metrics can include a minimum glucose metric. In some aspects, the software application 1390 of the therapy management system 1300 can receive the glucose data and calculate the one or more glucose metrics. For example, the one or more glucose metrics can be calculated in a time period after the first dose recommendation. In some aspects, the one or more glucose metrics can include average glucose, glucose TIR, glucose TBR, glucose TVL, GMI, MMG, MPDG, PPG, BeAM, change in glucose levels in a meal period or a nighttime period, postprandial glucose rise for one or more meals, or a combination thereof. In some aspects, the minimum glucose metric can include fasting glucose, daily minimum glucose (DMG), minimum morning glucose (MMG), average glucose for a predetermined time period, daily minimum hourly average glucose (DMHAG), or a combination thereof.

[0350] In some aspects, one or more minimum glucose metrics (e.g., fasting glucose, DMG, MMG, DMHAG, etc.) can be calculated based on the glucose data. This one or more minimum glucose metrics can be superior to other glucose metrics to provide a more accurate indicator of the user’s glucose levels. For example, MMG can be used as a proxy for fasting glucose and is based on glucose levels in a morning window, which is typically at the end of the longest fasting period of the nighttime period when the user is sleeping. Since MMG is measured after the longest fasting period, it can provide a more accurate and safer indicator of the user’s fasting glucose level.

[0351] In some aspects, the one or more minimum glucose metrics can be based on DMHAG. For example, DMHAG can be used as a proxy for fasting glucose and is based on the hour of the day with the lowest average glucose, which can be determined without regard to fasting periods or specific times of the day, which can provide a proxy indicator of the user’s fasting glucose level. In some aspects, DMHAG can be used as a safer proxy than MMG because the accuracy of DMHAG is similar to MMG, but does not require meal and dosing data. For example, DMHAG can be used for users who maintain irregular sleep schedules, such as shift workers who work overnight, travelers in different time zones, or any other user who maintains an irregular sleep schedule.

[0352] In step 2108, as FIG. 13-FIG. 18 、 FIG. 19A-FIG. 19C and FIG. 23As shown in the example of FIG. 21, a recommended dose of basal insulin can be titrated based on one or more glucose metrics. In some aspects, the software application 1390 of the therapy management system 1300 can titrate a recommended dose of basal insulin based on one or more glucose metrics. In some aspects, the flowchart 2100 does not require basal insulin dose amount data and can titrate a recommended dose (e.g., via the software application 1390) based on one or more glucose metrics (e.g., via the OBU 1350) and / or basal insulin dosing time data (e.g., via the first smart cap 1382 and / or the second smart cap 1384).

[0353] In step 2110, as shown in the example of FIG. 21, FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 a second dose of basal insulin can be recommended. In some aspects, the second dose can be different than the first dose, e.g., due to the recommended dose being titrated.

[0354] In step 2112, as shown in the example of FIG. 21, FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 a change in the lowest glucose metric can be calculated. In some aspects, a change in the lowest glucose metric from a first time period to a second time period can be calculated. In some aspects, e.g., a change from a first time period before the second dose is recommended to a second time period after the second dose is recommended can be calculated. In some aspects, the software application 1390 of the therapy management system 1300 can receive glucose data and calculate a change in the lowest glucose metric. In some aspects, the change in the lowest glucose metric can include a change in fasting glucose, DMG, MMG, average glucose over a predetermined time period, DMHAG, or combinations thereof.

[0355] In step 2114, as shown in the example of FIG. 21, FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 whether the change in the lowest glucose metric is outside of a predetermined metric can be determined. In some aspects, the software application 1390 of the therapy management system 1300 can determine whether the change in the lowest glucose metric is outside of a predetermined metric. In some aspects, the predetermined metric can include the change in the lowest glucose metric being less than 5 mg / dL, less than 10 mg / dL, or less than 15 mg / dL, etc. In some aspects, the predetermined metric can be based on which lowest glucose metric is used. For example, the predetermined metric for MMG can include the change in MMG being less than 5 mg / dL, less than 10 mg / dL, or less than 15 mg / dL, etc. In some aspects, the predetermined metric for DMHAG can include the change in DMHAG being less than 0.1 mg / dL, less than 1 mg / dL, less than 5 mg / dL, less than 10 mg / dL, etc.

[0356] In some aspects, the predetermined metric can include a change in the lowest glucose metric that is less than a predetermined percentage of an expected change in the lowest glucose metric. The predetermined percentage can be 50% of the expected change in the lowest glucose metric. In some aspects, the expected change in the lowest glucose metric can be based on one or more user metrics. In some aspects, the one or more user metrics can include weight, BMI, age, ISF, TDD, a ratio of TDD to weight, A1C level, heart rate, blood pressure, or a combination thereof. A patient with higher insulin sensitivity will exhibit a smaller change in insulin level for a given dose of insulin than a patient with lower insulin sensitivity. Additionally, since weight can act as a proxy for insulin sensitivity, an expected impact of a 4U dose on glucose levels for a patient with a larger weight is less than the impact of a 4U dose on a patient with a relatively low weight. In some aspects, the expected change in the lowest glucose metric can be based on historical glucose data of the user. For example, if a previous increase of 1U dose resulted in a 10 mg / dL drop in glucose level, then the system can predict or expect that a further increase of 1U will result in a further 10 mg / dL drop in glucose level. Additionally, the system can determine trends or make inferences based on historical data. For example, if a previous 1U dose resulted in a 10 mg / dL drop in glucose level, then a 2U dose can be expected to result in a 20 mg / dL drop in glucose level. In some aspects, the expected change in the lowest glucose metric can be proportional to a change between the first dose and the second dose.

[0357] In some aspects, the predetermined metric can include a statistical test on the lowest glucose metric that does not support a hypothesis that the lowest glucose metric has changed. In some aspects, the statistical test can include an insulin sensitivity test (IST), an insulin tolerance test (ITT), an oral glucose tolerance test (OGTT), a fasting plasma glucose (FPG) test, a random plasma glucose test, or a combination thereof.

[0358] In step 2116, as shown in the example of FIG. 21, if the change in the lowest glucose metric is outside of the predetermined metric, an indication to stop the titration of basal insulin can be output. In some aspects, the software application 1390 of the therapy management system 1300 can output an indication to the user or HCP (e.g., third party) that the titration of basal insulin will stop (e.g., to avoid a dangerous dosing event, a hypoglycemic event, or a hyperglycemic event) (e.g., via the remote device 1310). FIG. 22 、 FIG. 13 and FIG. 22 In some aspects, the predetermined metric can include a statistical test on the lowest glucose metric that does not support a hypothesis that the lowest glucose metric has changed. In some aspects, the statistical test can include an insulin sensitivity test (IST), an insulin tolerance test (ITT), an oral glucose tolerance test (OGTT), a fasting plasma glucose (FPG) test, a random plasma glucose test, or a combination thereof.

[0359] In some aspects, flowchart 2100 can output a notification to the user. The notification can indicate that the user did not take the recommended dose. The notification can encourage the user to administer the recommended dose. The notification can prompt the user to confirm administration of the second dose. In some aspects, flowchart 2100 can further include resuming dose guidance to the user if the user confirms administration of the second dose. In some aspects, flowchart 2100 can further include recommending a third dose based on titrating the second dose if the user does not confirm administration of the second dose. The notification can provide educational materials or direct the user to educational materials regarding the operation of the therapy and / or the dose guidance system.

[0360] In some aspects, flowchart 900 can further include outputting a prompt to the user to confirm that the user followed the recommended dose. In some aspects, flowchart 900 can further include outputting a prompt to the user to seek guidance from a healthcare professional. In some aspects, flowchart 900 can further include outputting a quiz to the user to verify that the user followed the recommended dose. In some aspects, for example, software application 190 of therapy management system 100 can output a quiz to the user (e.g., via remote device 110) (e.g., “What is the current basal insulin dose amount?” “What was the last basal insulin dose amount?” “What is the recommended basal insulin dose amount?” etc.). If the user answers correctly, titration can continue. If the user enters a different dose than the recommended dose, the titration algorithm can proceed based on the dose entered by the user as the dose amount for titration.

[0361] In some aspects, flowchart 2100 can further include recommending limiting changes to the basal insulin dose if the minimum glucose metric does not change after titrating the recommended dose for a predetermined period of time. In some aspects, the predetermined period of time can include at least 3 days. In some aspects, the predetermined period of time can include at least 5 days. In some aspects, the predetermined period of time can include at least 7 days. In some aspects, the predetermined period of time can include a range of 1 day to 14 days.

[0362] In some aspects, flowchart 2100 can further include recommending stopping upward titration of the basal insulin (i.e., increasing the dose amount) if the minimum glucose metric (e.g., fasting glucose, MMG, DMHAG, etc.) does not decrease after titrating the recommended dose for a predetermined period of time. In some aspects, flowchart 2100 can further include recommending stopping downward titration of the basal insulin (i.e., decreasing the dose amount) if the minimum glucose metric (e.g., fasting glucose, MMG, DMHAG, etc.) does not increase after titrating the recommended dose for a predetermined period of time.

[0363] In some aspects, the flowchart 2100 can also include activating a blind mode such that glucose data is not displayed to the user. In some aspects, the blind mode can prevent glucose data from being displayed to the user to encourage the user to adhere to the dosing regimen and reduce inappropriate dosing and / or user interaction to correct their glucose levels (e.g., to prevent the user from deviating from the recommended dose).

[0364] In some aspects, the flowchart 2100 can also include initiating a counter configured to monitor the number of titration cycles if the change in the minimum glucose metric is outside of the predetermined metric. In some aspects, the flowchart 2100 can also include recommending to stop titration of the basal insulin if the change in the minimum glucose metric remains outside of the predetermined metric after the predetermined number of titration cycles of increasing or decreasing the dose of the basal insulin.

[0365] In some aspects, the flowchart 2100 can also include receiving basal insulin dose administration time data. In some aspects, the basal insulin dose administration time data can be determined via the software application 1390 based on changes in glucose levels (e.g., received from the OBU 1350) and / or received (e.g., via the software application 1390) from a medication delivery device and / or a cap (e.g., the first smart cap 1382, the second smart cap 1384) of the therapy management system 1300. In some aspects, the basal insulin dose administration time data can supplement one or more glucose metrics for determining the recommended dose.

[0366] In some aspects, the flowchart 2100 can detect non-adherence to the recommended basal insulin dose. In some aspects, the flowchart 2100 can prevent unsafe sustained increases or decreases in the recommended dose that can lead to unsafe basal insulin doses. In some aspects, the flowchart 2100 can include one or more outputs (e.g., indications, notifications, prompts, etc.) to the user to have the user confirm that they followed the dose recommendation, seek guidance from their HCP, and / or other verification means (e.g., quizzes, inquiries, etc.) to confirm that the user followed the dose recommendation.

[0367] In some aspects, the non-adherence determination can apply to a bolus dose for a meal. However, the glucose metrics will be based on post-meal glucose metrics after the post-meal dose, not the MMG or DMHAG. The glucose metrics for the post-meal period for a meal before the new dose recommendation can be compared to the glucose metrics for the post-meal period for a meal after the dose recommendation to determine the change in the metrics.

[0368] FIG. 22 FIG. 22 illustrates a flowchart 2200 in accordance with example aspects. For example, the flowchart 2200 can be used to determine a recommended dose of insulin for a user based on one or more glucose metrics. FIG. 13therapy management system 1300 shown in FIG. 14. The flowchart 2200 can be configured to measure one or more metrics of therapy (e.g., basal insulin) (e.g., a minimum glucose metric) to determine that the user did not comply with one or more dose recommendations. The flowchart 2200 can also be configured to output an indication or notification that the user did not comply with the dose recommendation (e.g., to the user, a third party, etc.).

[0369] It is to be appreciated that not all of the steps in FIG. 14A-FIG. 14C are required to perform the disclosure provided herein. In addition, some of the steps can be performed simultaneously, in a different order, and / or at different times than as shown in FIG. 15-FIG. 18 The flowchart 2200 will be described with reference to FIG. 19A-FIG. 19C , FIG. 23 , FIG. 22 , FIG. 13 and FIG. 14A-FIG. 14C However, the flowchart 2200 is not limited to those example aspects. While the flowchart 2200 is shown as a standalone method in FIG. 15-FIG. 18 Aspects of the disclosure can be used with other processes, apparatuses, systems, and / or methods such as, but not limited to, elements in FIG. 19A-FIG. 19C , FIG. 20 , FIG. 21 , FIG. 23 , FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 for example, the control chart 1400A, the therapy assessment 1400B, the control chart 1400C, the therapy assessment 1430, the one or more dosing regimens 1410, 1440, 1450, 1460, 1480, the flowchart 2000, the flowchart 2100, and / or the computing device 2300. In some aspects, the flowchart 2200 can be implemented by the software application 1390. In some aspects, the flowchart 2200 can be implemented by one or more models or algorithms running on one or more processors and / or computing devices based on one or more instructions stored in one or more memories.

[0370] In step 2202, as shown in the examples of FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23 the glucose data for the user for a first time period can be received from an in vivo glucose monitoring device. In some aspects, the glucose data can be received from the OBU 1350 of the therapy management system 1300 (e.g., via the software application 1390). In some aspects, the first time period can include a morning window period or a fasting period.

[0371] In step 2204, as shown in the examples of FIG. 13-FIG. 18 , FIG. 19A-FIG. 19C and FIG. 23As shown in the example of FIG. 21, a first lowest glucose metric for the first time period can be determined. In some aspects, the software application 1390 of the therapy management system 1300 can receive glucose data for the first time period and calculate the first lowest glucose metric. In some aspects, the first lowest glucose metric can include a fasting glucose, a DMG, a MMG, an average glucose for a predetermined time period, a DMHAG, or a combination thereof.

[0372] In step 2206, as shown in the example of FIGS. 22A, 22B, and 22C, a dose recommendation can be provided to the user based on the glucose data for the first time period. In some aspects, the software application 1390 of the therapy management system 1300 can calculate a dose recommendation based on the glucose levels and / or one or more glucose metrics (e.g., the lowest glucose metric) for the first time period. FIG. 13-FIG. 18 、 FIG. 19A-FIG. 19C and FIG. 23 In step 2208, as shown in the example of FIGS. 22A, 22B, and 22C, glucose data for the user for a second time period after the dose recommendation can be received from the in vivo glucose monitoring device. In some aspects, the glucose data can be received from the OBU 1350 of the therapy management system 1300 (e.g., via the software application 1390). In some aspects, the second time period can include a window after the dose recommendation is provided. In some aspects, the second time period can include a window after the user confirms administration of the dose recommendation.

[0373] In step 2210, as shown in the example of FIGS. 22A, 22B, and 22C, a second lowest glucose metric for the second time period can be determined. In some aspects, the software application 1390 of the therapy management system 1300 can receive glucose data for the second time period and calculate the second lowest glucose metric. In some aspects, the second lowest glucose metric can include a fasting glucose, a DMG, a MMG, an average glucose for a predetermined time period, a DMHAG, or a combination thereof. In some aspects, the first and second lowest glucose metrics can be the same type (e.g., both are MMG, both are DMHAG, etc.). In some aspects, the first and second lowest glucose metrics can be different (e.g., the first lowest glucose metric can be MMG and the second lowest glucose metric can be DMHAG, etc.). FIG. 13-FIG. 18 、 FIG. 19A-FIG. 19C and FIG. 23 In step 2212, as shown in the example of FIGS. 22A, 22B, and 22C, a determination can be made as to whether the second lowest glucose metric is lower than the first lowest glucose metric. In some aspects, the software application 1390 of the therapy management system 1300 can compare the second lowest glucose metric to the first lowest glucose metric. In some aspects, the software application 1390 can determine whether the second lowest glucose metric is lower than the first lowest glucose metric.

[0374] In step 2214, as shown in the example of FIGS. 22A, 22B, and 22C, a determination can be made as to whether the second lowest glucose metric is lower than the first lowest glucose metric. In some aspects, the software application 1390 of the therapy management system 1300 can compare the second lowest glucose metric to the first lowest glucose metric. In some aspects, the software application 1390 can determine whether the second lowest glucose metric is lower than the first lowest glucose metric. FIG. 13-FIG. 18 、 FIG. 19A-FIG. 19C and FIG. 23 In step 2216, as shown in the example of FIGS. 22A, 22B, and 22C, a determination can be made as to whether the second lowest glucose metric is lower than the first lowest glucose metric. In some aspects, the software application 1390 of the therapy management system 1300 can compare the second lowest glucose metric to the first lowest glucose metric. In some aspects, the software application 1390 can determine whether the second lowest glucose metric is lower than the first lowest glucose metric.

[0375] In step 2218, as shown in the example of FIGS. 22A, 22B, and 22C, a determination can be made as to whether the second lowest glucose metric is lower than the first lowest glucose metric. In some aspects, the software application 1390 of the therapy management system 1300 can compare the second lowest glucose metric to the first lowest glucose metric. In some aspects, the software application 1390 can determine whether the second lowest glucose metric is lower than the first lowest glucose metric. Exemplary computing device 、 FIG. 23 and FIG. 14AAs illustrated in the example, non-compliance with a dosage recommendation can be determined based on a comparison of a first minimum glucose measure and a second minimum glucose measure. In some aspects, the comparison can be based on whether the first and second minimum glucose measures have changed the predetermined amount (e.g., the change in MMG is outside the predicted range of change). In some aspects, the comparison can be based on whether the first and second minimum glucose measures have changed in the correct direction. For example, for a dosage recommendation with an increased dose, non-compliance can be determined if no subsequent decrease in glucose levels is measured. In some aspects, the software application 1390 of the therapy management system 1300 can receive glucose data for first and second time periods, determine the first and second minimum glucose measures, and compare the first and second minimum glucose measures.

[0376] In step 2214, as FIG. 20 , FIG. 21 and FIG. 22 As shown in the example, non-compliance instructions can be output, for example, based on comparison. In some aspects, the software application 1390 of the therapy management system 1300 can output non-compliance instructions to users and / or HCPs (e.g., third parties) (e.g., via remote device 1310).

[0377] In some aspects, software application 1390 may include one or more models or algorithms (e.g., as described herein) that run on one or more processors and / or computing devices based on one or more instructions stored in one or more memories. In some aspects, software application 1390 may be stored on and / or executed on a telephone (e.g., remote device 1310), a drug delivery device (e.g., a first injection pen 1360, a second injection pen 1370), a pen cap (e.g., a first smart cap 1382, a second smart cap 1384), a cloud server, or a combination thereof. In some respects, one or more of the algorithms described above for titration and / or dosage recommendation (e.g., control chart 1400A, therapy assessment 1400B, control chart 1400C, therapy assessment 1430, flowchart 2000, flowchart 2100, etc.) may be stored on and / or executed on a telephone (e.g., remote device 1310), a drug delivery device (e.g., first injection pen 1360, second injection pen 1370), a pen cap (e.g., first smart cap 1382, second smart cap 1384), a cloud server, or a combination thereof.

[0378] In some aspects, the one or more therapy regimens can include a premixed insulin, which includes a combination of long-acting (LA) insulin and rapid-acting (RA) insulin. In some aspects, basal insulin therapy and / or prandial insulin therapy can use premixed insulin. For example, the third dosing regimen 1450 can use premixed insulin with a meal to obtain a single combined dose of LA (basal) insulin and RA (bolus) insulin.

[0379] In some aspects, the software application 1390 can include one or more titration algorithms. In some aspects, the software application 1390 can use multiple titration algorithms (e.g., generic, personalized, optimized). In some aspects, the software application 1390 can provide a user with an option to select a particular titration algorithm. In some aspects, the software application 1390 can include a generic titration algorithm based on American Diabetes Association (ADA) guidelines (e.g., fasting blood glucose level 80-130 mg / dL, starting dose of insulin 10 units / day or 0.1-0.2 units / kg / day, insulin dose increment 5-15% or 1-4 units, etc.). In some aspects, the software application 1390 can include a personalized titration algorithm personalized to a user (e.g., control chart 1400A, therapy assessment 1400B, control chart 1400C, therapy assessment 1430, flowchart 2000, flowchart 2100, etc.), for example, based on one or more glucose metrics and / or one or more user metrics as described herein. In some aspects, the software application 1390 can include an optimized titration algorithm based on AI and / or machine learning, for example, a constructed user profile can be generated using an AI module trained using analytics. In some aspects, the optimized titration algorithm can utilize simulated annealing, gradient descent, finite differences, interpolation, population models, regression, parameter adaptation, supervised machine learning, unsupervised machine learning, neural networks, classification models, clustering, vector quantization, stochastic gradient descent, implicit updates, leaky averaging, momentum methods, adaptive gradient (AdaGrad), backpropagation, root mean square propagation (RMSProp), adaptive moment estimation (Adam), or combinations thereof.

[0380] FIG. 23

[0381] FIG. 14A-FIG. 18 FIG. 13 illustrates a computing device 1300, in accordance with various example aspects. The computing device 1300 can be configured to implement the operations described herein. The computing device 1300 can also be configured to execute the operating systems, applications, control charts, flowcharts, and / or software modules (e.g., software engines) described herein. For example, the computing device 1300 can be configured to implement the control chart 1400A shown in FIG. 14A. For example, the computing device 1300 can be configured to implement the control chart 1400B shown in FIG. 14B. For example, the computing device 1300 can be configured to implement the control chart 1400C shown in FIG. 14C. For example, the computing device 1300 can be configured to implement the therapy assessment 1430 shown in FIG. 14D. For example, the computing device 1300 can be configured to implement the flowchart 2000 shown in FIG. 20. For example, the computing device 1300 can be configured to implement the flowchart 2100 shown in FIG. 21. FIG. 19A-FIG. 19C FIG. 20-FIG. 22 ​The flowchart 2000 shown is illustrated. For example, computing device 2300 can be configured to implement... FIG. 12 The flowchart 2100 shown is illustrated. For example, computing device 2300 can be configured to implement... FIG. 23 The flowchart 2200 is shown. Although the computing device 2300 is in FIG. 12 While each aspect of this disclosure is shown as a separate device and / or system, it may be used in conjunction with other devices, systems, and / or methods, such as, but not limited to, those described herein. FIG. 23 , FIG. 23 and FIG. 23 Elements in the diagram, such as control chart 1400A, therapy assessment 1430, one or more dosing regimens 1410, 1440, 1450, 1460, 1480, flowchart 2000, flowchart 2100 and / or flowchart 2200.

[0382] For example, FIG. 23 The various aspects of the computing device 1200 shown are related to FIG. 23 The aspects of the computing device 2300 shown may be similar. Similar reference numerals are used to indicate... ​ Features of various aspects of the computing device 1200 shown and ​ The computing device 2300 shown herein exhibits similar features in various aspects. The computing device 1200 can implement the operations described herein and execute the operating system, application programs, control charts, flowcharts, and / or software modules (e.g., software engines) described herein.

[0383] like ​ As shown, computing device 2300 may include processing device 2302 (e.g., one or more processors, one or more microprocessors, microcontrollers), system memory 2304 (e.g., one or more memories), system bus 2306, read-only memory (ROM) 2308, random access memory (RAM) 2310, basic input / output system (BIOS) 2312, secondary storage device 2314 (e.g., hard disk drive), secondary storage interface 2316, operating system (OS) 2318, application program (app) 2320, program module 2322 (e.g., software engine, algorithm), program data 2324, input device 2326 (e.g., keyboard 2328, mouse 2330, microphone 2332, touch sensor 2334, gesture sensor 2335), input / output (I / O) interface 2336, display device 2338, video adapter 2340, and network interface 2342.

[0384] In some aspects, the computing device 2300 can include at least one processing device 2302 (e.g., a processor), such as a central processing unit (CPU). Various processing devices can be obtained from various manufacturers, such as Intel or AMD. In this example, the computing device 2300 also includes a system memory 2304 and a system bus 2306 that couples the various system components including the system memory 2304 to the processing device 2302. The system bus 2306 can be any of several types of bus structures including, but not limited to, a memory bus or memory controller; a peripheral bus; or a local bus using any of a variety of bus architectures.

[0385] Examples of computing devices that can be implemented using the computing device 2300 include desktop computers, laptop computers, tablet computers, mobile computing devices such as smartphones, tablet digital devices, or other mobile devices, or other devices configured to process digital instructions.

[0386] The system memory 2304 includes ROM 2308 and RAM 2310. A basic input / output system (BIOS) 2312 containing the basic routines that transfer information between elements within the computing device 2300, such as during startup, can be stored in the ROM 2308.

[0387] In some aspects, the computing device 2300 can include a secondary storage 2314, such as a hard disk drive, for storing digital data. The secondary storage 2314 can be connected to the system bus 2306 by a secondary storage interface 2316. The secondary storage 2314 and its associated computer-readable medium can provide non-volatile and non-transitory storage for the computing device 2300 of computer-readable instructions (e.g., including applications and program modules), data structures, and other data.

[0388] While the example environments described herein employ a hard disk drive as the secondary storage, other types of computer-readable storage media can be used in other aspects. Examples of these other types of computer-readable storage media can include a magnetic tape, a flash card, a digital video disc, a Bernoulli cartridge, an optical disc, a read-only memory, a digital versatile disc, a random access memory, or a read-only memory. Some aspects can include non-transitory media. For example, a computer program product can be tangibly embodied in a non-transitory storage medium. Moreover, such computer- readable storage media can include local storage or cloud-based storage.

[0389] A number of program modules can be stored in the secondary storage device 2314 and / or the system memory 2304, including an OS 2318, one or more application programs 2320, other program modules 2322 such as the software applications and software engines described herein, and program data 2324. The computing device 2300 can use any suitable operating system, such as the Microsoft Windows™, Google Chrome™ OS, Apple OS, Unix, or Linux, and variants thereof, as well as any other operating system suitable for use with a computing device. Other examples can include the Microsoft, Google, or Apple operating systems, or any other suitable operating system for use in a tablet computing device.

[0390] In some aspects, a user can provide one or more inputs to the computing device 2300 through one or more input devices 2326. Examples of input devices 2326 can include a keyboard 2328, a mouse 2330, a microphone 2332 (for example, for speech and / or other audio input), a touch sensor 2334 (for example, a touchpad and / or a touch-sensitive display), and a gesture sensor 2335 (for example, for gesture input). In some aspects, the input devices 2326 can provide detection based on presence, proximity, and / or motion. In some aspects, a user can walk into their home and this can trigger an input to the processing device 2302. For example, the input devices 2326 can then facilitate an automated experience for the user. Other aspects can include other input devices 2326. The input devices 2326 can be connected through an I / O interface 2336 to the processing device 2302, which can be coupled to the system bus 2306. The input devices 2326 can be connected by any number of I / O interfaces, such as parallel, serial, game port, and / or universal serial bus. In some aspects, the input devices 2326 can be in wireless communication with the I / O interface 2336, for example, including infrared, Bluetooth® wireless technology, 802.11a / b / g / n, cellular, Ultra Wide Band (UWB), ZigBee, or other radio frequency (RF) communication systems.

[0391] In this example aspect, a display device 2338, such as a monitor, a liquid crystal display device, a light-emitting diode display device, a projector, or a touch-sensitive display device, can also be connected to the system bus 2306 via an interface, such as a video adapter 2340. In some aspects, the computing device 2300 can include a variety of other peripheral devices (not shown) in addition to the display device 2338, such as speakers or a printer.

[0392] The computing device 2300 can connect to one or more networks through the network interface 2342. The network interface 2342 can provide wired and / or wireless communication. In some aspects, the network interface 2342 can include one or more antennas to transmit and / or receive wireless signals. In some aspects, the network interface 2342 can include an Ethernet interface when used in a local area networking environment or a wide area networking environment (e.g., the Internet). Other possible aspects can use other communication devices.

[0393] The computing device 2300 can include at least some form of computer-readable media. Computer-readable media can include any available media that can be accessed by the computing device 2300. For example, computer-readable media can include computer-readable storage media and computer-readable communication media.

[0394] Computer-readable storage media can include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data. Computer-readable storage media can include, but is not limited to, random access memory, read only memory, electrically erasable programmable read only memory, flash memory or other memory technology, compact disc read only memory, d...

Claims

1. A non-transitory computer-readable storage medium storing instructions that, when executed by a processor, cause the processor to perform operations for the administration of insulin therapy, the operations including: Conduct a survey on people with diabetes (PWD) and receive survey information in response to the survey; Perform a high-contact interaction phase regarding PWD, which includes iteratively adjusting insulin therapy based on collected data and publicly available guidelines on insulin therapy, and establishing at least basal dose settings, mealtime dose settings, and corrective dose settings for PWD; as well as After the termination of the high-contact interaction phase, an ongoing phase regarding PWD is performed, which includes collecting performance metrics for PWD, applying reinforcement learning to the performance metrics, and automatically performing actions related to PWD based on the reinforcement learning.

2. The non-transitory computer-readable storage medium of claim 1, wherein the high-touch interaction phase is performed for a predetermined duration.

3. The non-transitory computer-readable storage medium of claim 1, wherein the high-touch interaction phase has a target-based duration.

4. The non-transitory computer-readable storage medium of claim 3, wherein the target-based duration depends on the PWD’s blood glucose level being within the target range and the determination of the PWD’s insulin intake as specified in insulin therapy.

5. The non-transitory computer-readable storage medium of claim 1, further comprising evaluating each of a plurality of insights and determining whether an insight is triggered based on at least the performance metric and the collected data, wherein the action is selected based on at least one of the insights being triggered.

6. The non-transitory computer-readable storage medium of claim 5, wherein the insight is evaluated according to priority regarding PWD.

7. The non-transitory computer-readable medium of claim 6, wherein the evaluated insight is selected based on the highest priority from the set of insights.

8. The non-transitory computer-readable storage medium of claim 5, wherein evaluating at least one of the insights comprises multimodal evaluation.

9. The non-transitory computer-readable storage medium of claim 1, wherein the operation further includes observing the state of the PWD after the action is performed automatically.

10. The non-transitory computer-readable storage medium of claim 9, wherein reinforcement learning includes providing positive or negative feedback to the selection of the action.

11. The non-transitory computer-readable storage medium of claim 10, wherein the operation further includes performing cooling after the observation is terminated.

12. The non-transitory computer-readable storage medium of claim 11, the operation further comprising evaluating each of a plurality of insights and determining whether an insight is triggered based on at least the performance metric and the collected data, wherein the action is selected based on at least one of the insights being triggered.

13. The non-transitory computer-readable storage medium of claim 12, wherein the operation further includes checking whether the cooling involves the action before selecting the action.

14. The non-transitory computer-readable storage medium of claim 13, wherein if the cooling involves the action, then the operation instead evaluates the next insight among the plurality of insights.

15. The non-transitory computer-readable storage medium of claim 9, further comprising evaluating each of a plurality of insights and determining whether an insight is triggered based on at least the performance metric and the collected data, wherein the action is selected based on at least one of the insights being triggered.

16. The non-transitory computer-readable storage medium of claim 15, wherein the operation further includes checking whether the observation relates to the insight before selecting the action.

17. The non-transitory computer-readable storage medium of claim 14, wherein if the observation relates to the insight, then the operation evaluates improvement criteria with respect to the insight based on at least the performance metric and the collected data.

18. The non-transitory computer-readable storage medium of claim 17, wherein evaluating the improvement criteria includes multimodal evaluation.

19. The non-transitory computer-readable storage medium of claim 14, wherein for any insight not triggered in the evaluation, the operation further includes determining whether the insight has not been triggered for at least a predetermined time, and performing a series of actions in view of the determination.

20. The non-transitory computer-readable storage medium of claim 1, wherein automatically performing the action includes selecting one or more targets for the PWD and presenting the one or more targets to the PWD.

21. The non-transitory computer-readable storage medium of claim 20, wherein the operation further includes receiving a PWD select join input or select exit input.

22. A method for upgrading a treatment for patients with diabetes, the method comprising: Receives glucose data from the user's internal glucose monitoring device; Receive first therapy information for a first therapy, wherein the first therapy includes basal insulin; Calculate one or more glucose measures based on the received glucose data; The basal insulin dose is titrated based on one or more of the glucose measures; as well as One or more determinations of basal insulin excess are made based on the first therapy information and the glucose data.

23. The method of claim 22, further comprising outputting a recommendation to add a second therapy when it is determined that basal insulin is in excess.

24. The method of claim 22, wherein the one or more glucose measures include mean glucose, median glucose, time in range (TIR), time below range (TBR), time above range (TAR), time very low glucose (TVL), glucose management index (GMI), minimum morning glucose (MMG), minimum post-dose glucose (MPDG), postprandial glucose (PPG), bedtime to morning glucose (BeAM), or combinations thereof.

25. The method of claim 22, wherein the first therapy information is manually entered via an input terminal of a computing device.

26. The method of claim 22, wherein the first therapy information is collected by the drug delivery device and transmitted to the computing device.

27. The method of claim 22, wherein basal insulin overdose is determined based on the ratio of total daily insulin dose (TDD) to the user's body weight.

28. The method of claim 22, wherein the basal insulin excess is determined based on glucose variability.

29. The method of claim 22, wherein the basal insulin excess is determined based on a hypoglycemic measure.

30. The method of claim 22, wherein basal insulin excess is determined based on changes in glucose levels during mealtimes or nighttime periods.

31. The method of claim 22, further comprising reducing the basal insulin dose when adding the second therapy.

32. The method of claim 22, wherein the second therapy comprises a glucagon-like peptide-1 (GLP-1) receptor agonist.

33. The method of claim 32, further comprising titrating a dose of the GLP-1 receptor agonist, wherein titrating the dose comprises: Receive user input regarding the side effects of the second therapy, and Increased dosage is recommended when the user input is associated with no side effects.

34. The method of claim 32, further comprising titrating a dose of the GLP-1 receptor agonist, wherein titrating the dose comprises: Receive user's weight measurement, and The recommended dosage is increased when the measured weight is higher than the target weight.

35. The method of claim 22, wherein the one or more glucose measurements include postprandial glucose elevation at each of the multiple meals.

36. The method of claim 35, further comprising recommending the initiation of a mealtime insulin dose for the first meal when postprandial glucose rises above a threshold.

37. The method of claim 35, further comprising recommending the initiation of a mealtime insulin dose for the multiple meals when the postprandial glucose level at each of the multiple meals exceeds a threshold.

38. A system for upgrading a treatment for patients with diabetes, the system comprising: An in vivo glucose monitoring device, the in vivo glucose monitoring device being configured to measure a user's glucose data; A remote device that communicates with the in vivo glucose monitoring device, wherein the remote device is configured to receive or retrieve glucose data from the in vivo glucose monitoring device. A drug delivery device that communicates with the in vivo glucose monitoring device and the remote device, wherein the drug delivery device is configured to administer one or more dosing regimens; as well as A processor, which communicates with the analyte measurement system, the remote device, and the drug delivery device, wherein the processor is coupled to a memory storing instructions that, when executed, cause the processor to perform operations, including: Receive the user's glucose data from the in vivo glucose monitoring device; Receive first therapy information for a first therapy from the remote device, the drug delivery device, or both, wherein the first therapy includes basal insulin; Calculate one or more glucose measures based on the received glucose data; The basal insulin dose was titrated based on one or more of the glucose measures; and Based on the glucose data and one or more of the first therapy information, an excess of basal insulin is determined.

39. The system of claim 38, wherein the operation further includes outputting a recommendation to the remote device to add a second therapy when it is determined that basal insulin is in excess.

40. The system of claim 38, wherein the one or more glucose measures include mean glucose, median glucose, glucose TIR, glucose TBR, glucose TAR, glucose TVL, GMI, MMG, MPDG, PPG, BeAM, postprandial glucose elevation at each meal in multiple meals, or combinations thereof.

41. The system of claim 38, wherein basal insulin overdose is determined based on the ratio of insulin TDD to user weight.

42. The system of claim 38, wherein basal insulin excess is determined based on glucose variability, hypoglycemia measures, changes in glucose levels during mealtimes or nighttime periods, or a combination thereof.

43. The system of claim 38, wherein the second therapy comprises a GLP-1 receptor agonist, a first-meal insulin dose, a multiple-meal insulin dose, or a combination thereof.

44. A method for detecting therapy escalation in diabetic patients who have not adhered to basal insulin recommendations, the method comprising: Receives glucose data from the user's internal glucose monitoring device; Recommend the first dose of basal insulin to the user; One or more glucose measures are calculated based on the received glucose data, wherein the one or more glucose measures include the minimum glucose measure; The recommended dose of basal insulin is titrated based on one or more of the glucose measures; A second dose of basal insulin is recommended to the user, wherein the second dose differs from the first dose due to the dose recommended by titration; Calculate the change in the lowest glucose measure from a first time period before the recommended second dose to a second time period after the recommended second dose; Determine whether the change in the minimum glucose measure is outside the predetermined measure; as well as If the change in the minimum glucose measure is outside the predetermined measure, then the output will indicate that the titration of basal insulin has been stopped.

45. The method of claim 44, wherein the minimum glucose measure comprises minimum daily hourly average glucose (DMHAG).

46. ​​The method of claim 44, wherein the predetermined measure includes a predetermined percentage by which the change in the minimum glucose measure is less than the expected change in the minimum glucose measure.

47. The method of claim 46, wherein the expected change in the minimum glucose measurement is based on one or more user measurements.

48. The method of claim 47, wherein the one or more user metrics include insulin sensitivity factor (ISF).

49. The method of claim 46, wherein the expected change in the minimum glucose measurement is based on the user's historical glucose data.

50. The method of claim 46, wherein the expected change in the minimum glucose measurement is proportional to the change between the first dose and the second dose.

51. The method of claim 44, wherein the predetermined measure includes a change in the minimum glucose measure that is less than a predetermined change in the glucose level.

52. The method of claim 44, wherein the predetermined metric includes determining the change in the minimum glucose metric based on a statistical method.

53. The method of claim 44, further comprising prompting the user to confirm the administration of the second dose.

54. The method of claim 53, further comprising: If the user confirms the administration of the second dose, then the titration is resumed.

55. The method of claim 53, further comprising: If the user does not confirm the administration of the second dose, then a third dose is recommended based on the titration of the second dose.

56. The method of claim 44, further comprising: If the minimum glucose measure does not change after titrating the recommended dose within the predetermined time period, then it is recommended to limit changes in the amount of basal insulin.

57. The method of claim 56, wherein the predetermined time period includes at least 3 days.

58. The method of claim 44, further comprising: If the lowest glucose measure does not decrease after titrating the recommended dose within the predetermined time period, then stop the upward titration of basal insulin.

59. The method of claim 44, further comprising: If the minimum glucose measure does not increase after titrating the recommended dose within the predetermined time period, then stop the downward titration of basal insulin.

60. The method of claim 44, further comprising activating a blind mode such that glucose data is not displayed to the user.

61. The method of claim 44, further comprising: If the change in the minimum glucose measure is outside the predetermined measure, then a counter configured to monitor the number of titration cycles is initiated. as well as If the change in the minimum glucose measure remains outside the predetermined measure after a predetermined number of titration cycles of increasing or decreasing the basal insulin dose, it is recommended to discontinue the basal insulin titration.

62. The method of claim 44, further comprising outputting prompts to the user to seek guidance from a healthcare professional.

63. The method of claim 44 further includes outputting a test to the user to verify that the user is following the recommended dosage.

64. A method for detecting non-compliance with dosage recommendations, the method comprising: Receive glucose data from the user within a specific time period from an in vivo glucose monitoring device; Determine the first lowest glucose measure for the first time period; Based on glucose data within the first time period, a dosage recommendation is provided to the user; Receive glucose data from the user during a second time period following the recommended dosage; Determine the second lowest glucose measure for the second time period; The non-compliance with dosage recommendations is determined based on a comparison between the first lowest glucose measure and the second lowest glucose measure; as well as Output any instructions that were not followed.

65. The method of claim 64, wherein the first minimum glucose measure and the second minimum glucose measure comprise the minimum daily hourly average glucose (DMHAG).

66. The method of claim 64, wherein the comparison includes a change between the first minimum glucose measure and the second minimum glucose measure.

67. The method of claim 66, wherein determining non-compliance includes comparing the change between the first minimum glucose measure and the second minimum glucose measure with a predetermined percentage change threshold.

68. The method of claim 66, wherein determining non-compliance includes comparing the change between the first minimum glucose measure and the second minimum glucose measure with a predetermined change in glucose level.

69. The method of claim 64, wherein the comparison includes the orientation of the first lowest glucose measure and the second lowest glucose measure.

70. The method of claim 69, wherein the direction is inversely proportional to the recommended dose.

Images