Decision Support and Treatment Administration Systems

Abstract

Techniques for data analysis and user guidance are provided for determining and delivering one or more treatments to a user based on where the user is or will be in their menstrual cycle. In certain embodiments, a method for personalizing diabetes treatment based on information related to a user's menstrual cycle is provided. The method includes measuring blood glucose measurements of the user using a glucose monitoring system. The method further includes receiving information related to the user's menstrual cycle. The method further includes determining a treatment for the user to achieve a target blood glucose during a sub-phase or phase of the user's menstrual cycle based on at least one of historical data related to the user and historical data related to stratified groups of users.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims the benefit of U.S. Patent Application No. 62 / 976,778, entitled "WOMEN'S HEALTH AND GLYCEMIC CONTROL," filed February 14, 2020, and U.S. Patent Application No. 63 / 011,175, entitled "DECISION SUPPORT AND TREATMENT ADMINISTRATION SYSTEMS," filed April 16, 2020. The aforementioned provisional applications are incorporated herein by reference in their entireties. [Background technology]

[0002] Technical Field TECHNICAL FIELD This application relates generally to medical devices, such as analyte sensors, including systems and methods for using same to provide treatment to patients.

[0003] 2. Description of Related Art Diabetes is a metabolic condition associated with the body's production or use of insulin, a hormone that enables the body to use glucose for energy or store it as fat.

[0004] When a person eats a meal containing carbohydrates, the food is processed by the digestive system, which produces glucose in the person's blood. Blood glucose can be used for energy or stored as fat. The body normally maintains blood glucose levels in a range that provides enough energy to support bodily functions and avoids problems that can occur when blood glucose levels are too high or too low. Regulation of blood glucose levels depends on the production and use of insulin, which regulates the movement of blood glucose into cells.

[0005] If the body does not produce enough insulin or cannot effectively use the insulin that is present, blood glucose levels can rise above the normal range. Higher-than-normal blood glucose levels are called "hyperglycemia." Chronic hyperglycemia can lead to many health problems, including cardiovascular disease, cataracts and other eye problems, nerve damage (neuropathy), and kidney damage. Hyperglycemia can also lead to acute problems such as diabetic ketoacidosis, a condition in which the body becomes excessively acidic due to the presence of blood glucose and ketones, which are produced when the body cannot use glucose. Lower-than-normal blood glucose levels are called "hypoglycemia." Severe hypoglycemia can lead to an acute crisis that can result in seizures or death.

[0006] Diabetics may receive insulin to manage blood glucose levels. Insulin can be administered, for example, by manual injection using a needle. Wearable insulin pumps are also available. Diet and exercise also affect blood glucose levels.

[0007] The condition of diabetes is sometimes referred to as "type 1" and "type 2." Patients with type 1 diabetes can typically use insulin when it's available, but because of problems with the insulin-producing beta cells in the pancreas, their bodies are unable to produce enough insulin. Patients with type 2 diabetes may produce some insulin, but their sensitivity to insulin is reduced, making them "insulin resistant." As a result, even though insulin is present in the body, the patient's body does not use enough of it to effectively regulate blood sugar levels.

[0008] Managing diabetes can present a complex challenge for patients, clinicians, and caregivers, as a combination of many factors can affect a patient's glucose levels and glucose trends. For example, a female patient's menstrual cycle can significantly affect her insulin resistance, depending on which phase of her menstrual cycle she is in.

[0009] More specifically, the menstrual cycle typically lasts 21 to 35 days, averaging approximately 28 days. During this cycle, hormonal fluctuations not only trigger ovulation and menstruation but also affect the body's insulin resistance. The menstrual cycle generally includes four phases: the menstrual phase, the follicular phase, the ovulatory phase, and the luteal phase. During the luteal phase of the menstrual cycle, a hormone called progesterone is released, which can cause insulin resistance and lead to increased hyperglycemia, even if the patient follows the same exercise, diet, and / or insulin regimen. Therefore, treatments suggested to a female patient by a decision support system to help the patient manage her glucose levels may be less effective, for example, during the luteal phase of the patient's menstrual cycle.

[0010] This background is provided to introduce a brief context for the summary and detailed description that follow. This background is not intended to aid in determining the scope of the claimed subject matter, and should not be viewed as limiting the claimed subject matter to implementations that solve any or all of the disadvantages or problems presented above. Summary of the Invention [Problem to be solved by the invention]

[0011] One aspect is a system comprising: a glucose monitoring system comprising: a glucose sensor configured to measure a user's blood glucose; and a sensor electronics module configured to transmit sensor data corresponding to blood glucose measurements provided by the glucose sensor to a processor; and a memory circuit, wherein the processor is configured to receive information related to the user's menstrual cycle and determine a treatment for the user to achieve a target blood glucose during a sub-phase or phase of the user's menstrual cycle based on at least one of historical data associated with the user and historical data associated with stratified groups of users, wherein the historical data associated with the user includes blood glucose measurements of the user provided by the glucose monitoring system and the historical data associated with the user includes blood glucose measurements of the user provided by the glucose monitoring system and the historical data associated with the user includes blood glucose measurements of the user during a sub-phase or phase of the user's menstrual cycle. the system is structured to indicate at least one of a pattern of at least one of a user's blood glucose measurements and insulin resistance during a sub-phase or phase of the user's menstrual cycle and a pattern of a physiological effect of a treatment on the user's blood glucose measurements during a sub-phase or phase of the user's menstrual cycle, the pattern being indicative of the effectiveness of the treatment in relation to achieving the target blood glucose, and the historical data associated with the stratified groups of users is structured to indicate at least one of a pattern of at least one of a user's blood glucose measurements and insulin resistance during a sub-phase or phase of the menstrual cycle and a pattern of a physiological effect of a treatment on the glucose measurements of the stratified groups of users during a sub-phase or phase of the menstrual cycle, the pattern being indicative of the effectiveness of the treatment in relation to achieving the target blood glucose.

[0012] In the system, the processor is configured to provide a therapy. In the system, the therapy includes a dose of insulin. In the system, the dose of insulin is greater than an average dose of insulin administered to the user during a non-luteal phase subphase or phase of the user's menstrual cycle. In the system, the processor is configured to send a signal to a medication delivery device to administer the dose of insulin to the user.

[0013] In the above system, the processor is configured to provide a therapy recommendation to the user or another individual, the therapy recommendation indicating an insulin dosage. In the above system, the processor is configured to provide a therapy recommendation to the user or another individual, the therapy recommendation indicating at least one of an amount, type, duration, and intensity of exercise. In the above system, the processor is configured to provide a therapy recommendation to the user or another individual, the therapy recommendation indicating at least one of an amount and type of food.

[0014] Another aspect is a method of personalizing diabetes therapy based on information related to a user's menstrual cycle, comprising: measuring blood glucose measurements of a user using a glucose monitoring system; receiving, at a processor in data communication with the glucose monitoring system, information related to the user's menstrual cycle; and determining, at the processor, a therapy for the user to achieve a target blood glucose during a sub-phase or phase of the user's menstrual cycle based on at least one of historical data associated with the user and historical data associated with stratified groups of users, wherein the historical data associated with the user includes blood glucose measurements of the user provided by the glucose monitoring system, and the historical data associated with the user includes blood glucose measurements of the user during the sub-phase or phase of the user's menstrual cycle. and wherein the historical data associated with the stratified group of users is structured to indicate at least one of a pattern of at least one of blood glucose measurements and insulin resistance for the stratified group of users in the sub-phases or phases of their menstrual cycle and a pattern of a physiological effect of a treatment on the blood glucose measurements for the stratified group of users during the sub-phases or phases of their menstrual cycle, the pattern being indicative of the effectiveness of the treatment in relation to achieving the target blood glucose.

[0015] The method further includes providing a therapy. The method further includes providing a dosage of insulin. The method further includes providing a dosage of insulin that is greater than an average dosage of insulin administered to the user during a non-luteal phase subphase or phase of the user's menstrual cycle. The method further includes providing a therapy that further includes sending a signal to a drug delivery device to administer the dosage of insulin to the user. The method further includes providing a therapy recommendation to the user or another individual, the therapy recommendation indicating an insulin dosage.

[0016] In the above method, providing the treatment further includes providing a regimen recommendation to the user or another individual, the regimen recommendation indicating at least one of an amount, type, duration, and intensity of exercise.In the above method, providing the treatment further includes providing a regimen recommendation to the user or another individual, the regimen recommendation indicating at least one of an amount and type of food.

[0017] Another aspect is a non-transitory computer-readable medium having stored thereon instructions that cause a system to perform a method, the method, when executed by the system, including: measuring blood glucose measurements of a user using a glucose monitoring system; receiving, at a processor in data communication with the glucose monitoring system, information related to the user's menstrual cycle; and determining, at the processor, a treatment for the user to achieve a target blood glucose during a sub-phase or phase of the user's menstrual cycle based on at least one of historical data associated with the user and historical data associated with stratified groups of users, wherein the historical data associated with the user includes blood glucose measurements of the user provided by the glucose monitoring system and the historical data associated with the user includes blood glucose measurements of the user during the sub-phase or phase of the user's menstrual cycle. the historical data associated with the stratified group of users is structured to indicate at least one of a pattern of at least one of blood glucose measurements and insulin resistance for the stratified group of users in the subphases or phases of their menstrual cycle, and a pattern of a physiological effect of a treatment on the glucose measurements for the stratified group of users during the subphases or phases of their menstrual cycle, the pattern being indicative of the effectiveness of the treatment in relation to achieving the target blood glucose.

[0018] The method further includes providing a treatment, the treatment including a dose of insulin, the dose of insulin being greater than an average dose of insulin administered to the user during a non-luteal phase subphase or phase of the user's menstrual cycle.

[0019] Any feature of an embodiment is applicable to all embodiments identified herein. Furthermore, any feature of an embodiment may be combined in any way, partially or wholly independently, with other embodiments described herein; for example, one, two, or three or more embodiments may be combined in whole or in part. Furthermore, any feature of an embodiment may be optional with respect to other embodiments. Any embodiment of the method may include another embodiment of a system for personalizing diabetes treatment based on information related to a user's menstrual cycle, and any embodiment of a system for personalizing diabetes treatment based on information related to a user's menstrual cycle may be configured to implement a method of another embodiment. [Brief explanation of the drawings]

[0020] [Figure 1A] 1 illustrates an exemplary decision support and therapy management system (“DSTA”), according to certain embodiments disclosed herein. [Figure 1B] 1B illustrates the example glucose monitoring system of FIG. 1A in more detail along with several mobile devices, according to some embodiments disclosed herein. [Figure 2] 1B illustrates example inputs and example metrics calculated based on the inputs for use by the DSTA of FIG. 1A according to certain embodiments disclosed herein. [Figure 3] 1B is a flow diagram illustrating exemplary operations performed by a system such as the DSTA of FIG. 1A according to some embodiments disclosed herein. [Figure 4] FIG. 1 illustrates an example of how one or more treatments are determined for a user, according to certain embodiments. [Figure 5] 4 is a block diagram illustrating a computing device configured to perform one or more steps of the operations of FIG. 3 in accordance with certain embodiments disclosed herein. DETAILED DESCRIPTION OF THE INVENTION

[0021] In certain embodiments, applications as described herein provide guidance and treatments that may assist patients, caregivers, healthcare providers, or other users in improving lifestyle or clinical / patient treatment outcomes by responding to various challenges, such as overnight glucose control (e.g., reducing the incidence of hypoglycemic events or hyperglycemic excursions), mealtime and post-meal glucose control (e.g., using historical information and trends to improve glycemic control), hyperglycemia correction (e.g., increasing time in the target zone while avoiding hypoglycemic events from overcorrection), hypoglycemic treatment (e.g., addressing hypoglycemia while avoiding "rebound" hyperglycemia), exercise, and / or other health factors. In certain embodiments, applications may further comprise optimization tools that learn the patient's physiology and behavior and calculate guidance to help the patient identify optimal or desirable therapy parameters, such as basal insulin requirements, insulin-to-carbohydrate ratio, correction factors, and / or changes to insulin sensitivity with exercise.

[0022] The application may, for example, predict hypoglycemic or hyperglycemic events or trends, provide therapy to address occurring or potential hypoglycemic or hyperglycemic events or trends, and / or help the patient respond to problems in real time by monitoring the patient's blood glucose, physiology, and / or behavioral responses to various events in real time. This type of computed guidance and support may reduce the cognitive burden on the user.

[0023] While physiological sensors such as continuous glucose monitors can provide useful data that users can use to manage glucose levels, the data may require significant processing to develop effective strategies for glucose management. The sheer volume of data and the recognition of correlations between data types, trends, events, and treatment effects can far exceed human processing capabilities. This is particularly impactful when decisions about therapy or response to physiological conditions are being made in real time. Integrating real-time or recent data with historical data and patterns can provide useful guidance when making real-time decisions about therapy. Technology tools can process this information to provide calculated decision support guidance that is useful for a particular patient with a particular condition or situation at a particular time.

[0024] As described above, a female patient's menstrual cycle can significantly affect the patient's insulin resistance depending on which phase of the menstrual cycle the patient is in. However, certain existing decision support systems do not take this change in a user's insulin resistance into account. For example, it has been shown that patients have different levels of resistance to insulin during various phases. One example, without limitation, is during the luteal phase. As a result, during various phases of the menstrual cycle, existing decision support systems may continue to provide the same guidance (e.g., the same insulin dosage, exercise, or dietary recommendations) without taking into account the phase of the menstrual cycle. As a result, female users experience frustration when the same treatment that was effective just a few days ago is no longer effective.

[0025] Further complicating this issue is the fact that insulin resistance fluctuates by different amounts for different users. For example, during the luteal phase, a first female user may experience a 20% increase in insulin resistance, while a second female user may experience a 40% increase in insulin resistance. This difference may be due to one or more factors, including, but not limited to, age, weight, race, ethnicity, type of diet, other types of illnesses the users may have, etc. Furthermore, the type and amount of treatment that helps the first user combat the increase in insulin resistance may differ from the type and amount of treatment that helps a third user whose insulin resistance increases by 20% during a different phase of their menstrual cycle. Furthermore, the percentage by which the first user's insulin resistance changes during their menstrual cycle (e.g., increases during the luteal phase) may change over time for many reasons, including, but not limited to, age, weight changes, stress, pregnancy, other types of illnesses, dietary restrictions, etc.

[0026] Accordingly, certain embodiments described herein provide technical solutions to the above-mentioned technical problems in the field of diabetes intervention management. In certain embodiments, the technical solutions provided herein improve existing decision support systems by configuring such systems to provide more accurate guidance and treatment based on where the user is in their menstrual cycle and further based on at least one of the user's own historical data record (e.g., how the user's physiology has responded in the past during the same time / period of the user's menstrual cycle) and historical data record associated with one or more other users (e.g., how the physiology of other similar users (e.g., similarities based on one or more factors) has responded during the same time / period of the user's menstrual cycle). An integral part of the improved DSTA system described herein is a glucose monitoring system 104, which includes a sensor electronics module and a continuous analyte sensor 140 (see FIG. 1B ) that continuously measures the user's glucose level and enables the glucose measurements to be transmitted in real time or near real time to one or more processors within the DSTA system. Without receiving a continuous stream of glucose measurements from the glucose monitoring system 104 (e.g., in real time or near real time), it would be difficult, if not impossible, to provide a user with treatment related to the user's real-time glucose status that takes into account the user's menstrual cycle. In other words, without using a glucose monitoring system 104 that improves upon the DSTA system described herein, a user would be limited to certain existing techniques that use fingersticks to measure glucose levels. However, it would be very difficult, if not impossible or impractical, for a user to measure their own glucose level continuously (e.g., every 5 minutes) using fingerstick techniques.Thus, without the glucose monitoring system 104 described herein, a user's glucose measurements will be fragmented at best, thus complicating the operation of the DSTA system described herein or causing the delivery of potentially inaccurate or irrelevant therapy based on discrete, fragmented glucose measurements. As a result, the operation of the DSTA system described herein is improved by or reliant on a glucose monitoring system 104 that can provide a continuous, real-time, or near-real-time stream of glucose measurements.

[0027] In certain embodiments, the record of how the user's physiology responded during the same time / period of the user's menstrual cycle may include, among other things, a record of how the user became insulin resistant during such time / period in a previous cycle, changes in the user's glucose levels or other metrics in response to previously proposed treatments, etc. In certain embodiments, the record of how other similar users' physiologies responded during the same time / period may include, among other things, similar data regarding such users' physiologies. The precise treatment may include, for example, recommendations for various therapies to help the user manage their glucose levels by maintaining glucose levels in a desired range despite fluctuations in insulin resistance during various phases of the menstrual cycle. The precise treatment may include specific insulin dosages calculated based on the above factors to help the user maintain glucose levels within range, even taking into account fluctuations (e.g., increases) in insulin resistance. In certain embodiments, the insulin dosage may be provided to the user in the form of a therapy recommendation, based on which the user can manually administer (e.g., by injection or oral ingestion) the insulin dosage. In certain embodiments, the insulin dose may be signaled to a drug delivery device (e.g., an insulin pump or pen or another insulin administration device) based on which the drug delivery device automatically administers the recommended dose of insulin (e.g., after the user approves the recommended dose).

[0028] The precise treatment may additionally or alternatively include therapy recommendations to lower the user's glucose levels back into range by engaging in specific amounts and / or types of exercise. Further, the precise treatment may additionally or alternatively include therapy recommendations to consume and / or refrain from consuming specific amounts or types of foods and / or for specific periods of time to lower glucose levels back into range. Providing precise therapy recommendations (e.g., insulin or other medication dosages, activity, carbohydrate intake, etc.) wherever a user is in their menstrual cycle is an improvement over existing decision support systems and could lead to significant health improvements and therapeutic benefits for the user.

[0029] As noted above, in certain embodiments, the application utilizes input from one or more physiological sensors, such as one or more analyte sensors, to provide associated effective guidance and therapy. An example of an analyte sensor described herein is a glucose monitoring sensor that measures the concentration of glucose and / or a substance indicative of the concentration or presence of glucose and / or another analyte in the user's body. In some embodiments, the glucose monitoring sensor is a continuous glucose monitoring device, such as a subcutaneous, transcutaneous, transcutaneous, non-invasive, intraocular, and / or intravascular (e.g., intravenous) device. In some embodiments, the device is capable of analyzing multiple intermittent blood samples. The glucose monitoring sensor may use any method of glucose measurement, such as enzymatic, chemical, physical, electrochemical, optical, photochemical, fluorescence-based, spectrophotometric, spectroscopic (e.g., optical absorption spectroscopy, Raman spectroscopy, etc.), polarimetric, calorimetric, iontophoretic, radiometric, etc.

[0030] A glucose monitoring sensor can provide a data stream indicative of the concentration of an analyte in a host using any known detection method, including invasive, minimally invasive, and non-invasive sensing techniques. The data stream is typically a raw data signal used to provide a useful value of the analyte to a user, such as a patient or healthcare professional (HCP, e.g., doctor, physician, nurse, caregiver), who may be using the sensor.

[0031] In some embodiments, the glucose monitoring sensor is an implantable sensor such as those described with reference to U.S. Patent No. 6,001,067 and U.S. Patent Publication No. 2011 / 0027127 (Al). In some embodiments, the glucose monitoring sensor is a transcutaneous sensor such as those described with reference to U.S. Patent Publication No. 2006 / 0020187 (Al). In still other embodiments, the glucose monitoring sensor is a dual-electrode analyte sensor such as those described with reference to U.S. Patent Publication No. 2009 / 0137887 (Al). In still other embodiments, the glucose monitoring sensor is configured to be implanted in a main blood vessel or externally, such as the sensor described in U.S. Patent Publication No. 2007 / 0027385 (Al). These patents and publications are incorporated herein by reference in their entireties.

[0032] Exemplary System 1A illustrates an exemplary DSTA 100 that, in certain embodiments, includes a diabetes intervention application (“application”) 106 that provides decision support guidance to a user 102 (hereinafter “user”) and determines / administers one or more treatments. In certain embodiments, the user may be a patient or a patient's caregiver. In embodiments described herein, the user is assumed to be a patient for simplicity's sake only, but is not so limited. In certain embodiments, the DSTA 100 includes a user, a glucose monitoring system 104, a mobile device 107 running the application 106, a decision support engine 112, an optional insulin administration device (not shown), and a user database 110.

[0033] In certain embodiments, the glucose monitoring system 104 includes a sensor electronics module and a glucose sensor that measures blood glucose and / or the concentration of a substance indicative of the concentration or presence of glucose and / or another analyte in the user's body. In certain embodiments, the glucose sensor is configured to perform measurements continuously. The sensor electronics module transmits the blood glucose measurements to the mobile device 107 for use by the application 106. In some embodiments, the sensor electronics module transmits the glucose measurements to the mobile device 107 via a wireless connection (e.g., a Bluetooth connection). In certain embodiments, the mobile device 107 is a smartphone. However, in certain embodiments, the mobile device 107 may instead be any other type of computing device, such as a laptop computer, a smartwatch, a tablet, or any other computing device capable of running the application 106.

[0034] In particular embodiments, decision support engine 112 refers to a set of software instructions comprising one or more software modules, including data analytics module (DAM) 113. In some embodiments, decision support engine 112 executes entirely on one or more computing devices in a private or public cloud. In such embodiments, application 106 communicates with decision support engine 112 over a network (e.g., the Internet). In some other embodiments, decision support engine 112 executes partially on one or more local devices, such as mobile device 107, and partially on one or more computing devices in a private or public cloud. In some other embodiments, decision support engine 112 executes entirely on one or more local devices, such as mobile device 107.

[0035] In particular embodiments, the DAM 113 is configured to process a set of inputs received from the applications 106 and calculate a plurality of metrics 130, which may then be stored in the user profile 116. The inputs 127 and metrics 130 may be used by the applications 106, such as by different features of the applications 106, to provide real-time guidance and treatment to the user. Various data points in the user profile 116 are described in further detail below. In particular embodiments, the user profiles, including the user profile 116, are stored in a user database 110 that is accessible to the applications 106 and the decision support engine 112 via one or more networks (not shown). In some embodiments, the user database 110 refers to a storage server that may operate in a public or private cloud.

[0036] The real-time guidance and treatment provided to the user can help improve the user's physiological condition and / or enable the user to make more informed decisions. To provide effective, relevant, on-time guidance and treatment to the user, in particular embodiments, features of the application 106 may receive as input information related to the user stored in the user profile 116 and / or information related to a pool of similar users stored in such user's user profile in the user database 110. In particular embodiments, features of the application 106 may interact with the user in various ways, such as text, email, notifications (e.g., push notifications), phone calls, and / or other forms of communication, such as displaying content in the user interface of the application 106 (e.g., graphs, trends, charts, etc.).

[0037] As noted above, in certain embodiments, application 106 is configured to receive information related to a user as input and store that information in the user's user profile 116. For example, application 106 may obtain and record the user's demographic information 118, disease progression information 120, and / or medication information 122 in the user profile 116. In certain embodiments, demographic information 118 may include one or more of the user's age, body mass index (BMI), ethnicity, gender, etc. In certain embodiments, disease progression information 120 may include information about the user's disease, such as whether the user has Type 1, Type 2, or pre-diabetes, or whether the user has gestational diabetes. In certain embodiments, information about the user's disease may also include the length of time since diagnosis, the level of diabetes control, the level of adherence to diabetes management therapy, predicted pancreatic function, other types of diagnoses (e.g., heart disease, obesity) or health measures (e.g., heart rate, exercise, stress, sleep, etc.), and / or the like. In certain embodiments, medication regimen information 122 may include information regarding the amount and type of insulin or non-insulin diabetic medication and / or non-diabetic medication taken by the user. In certain embodiments, application 106 may obtain demographic information 118, disease progression information 120, and / or medication information 122 from the user in the form of user input or from other sources. In certain embodiments, application 106 may receive updates from the user or from other sources as some of this information changes.

[0038] In certain embodiments, in addition to the user's demographic information 118, disease progression information 120, and / or medication information 122, the application 106 acquires an additional set of inputs 127 that are also utilized by various features of the application 106 to provide guidance to the user. In certain embodiments, such inputs 127 are acquired continuously. In certain embodiments, the application 106 receives inputs 127 via multiple other sources, including user input and / or glucose monitoring system 104, other applications running on the mobile device 107, such as a menstrual cycle management application, and / or one or more other sensors and devices. In certain embodiments, such sensors and devices include, but are not limited to, one or more of an insulin administration device, other types of analyte sensors, sensors or devices provided by the mobile device 107 (e.g., an accelerometer, a camera, a global positioning system (GPS), a heart rate monitor, etc.) or other user accessories (e.g., a smart watch), or other sensors or devices that provide relevant information about the user.

[0039] In certain embodiments, application 106 further uses at least a portion of input 127 to obtain multiple metrics, such as metrics 130, which are also stored in user profile 116. As further described in connection with FIG. 2, in some embodiments, application 106 sends at least a portion of input 127 to DAM 113 for processing, based on which DAM 113 generates metrics 130. In certain embodiments, metrics 130 may then be used by application 106 as input to provide guidance to the user. It should be noted that in certain embodiments, user profile 116 and the user profiles of the pool of users in user database 110 are dynamic, as the information in the user profiles, including user profile 116, may change as new input 127 is periodically received or as existing information in the user profile changes (e.g., the user's medication information changes).

[0040] As further described in connection with FIG. 2 , in particular embodiments, metrics 130 may, at least in some cases, generally indicate a user's current or future health or condition, such as one or more of the user's physiological (e.g., glucose level, insulin resistance, etc.) or psychological state (e.g., stress level, happiness, etc.), trends associated with the user's health or condition, etc. For example, metrics 130 may include one or more of metabolic rate, glucose levels and trends, metrics related to the user's health or illness, etc. Metrics 130 may also include behavioral metrics that may indicate the user's behavior and habits, e.g., eating habits, exercise regime, etc. In particular embodiments, metrics 130 may include real-time metrics, historical metrics, and / or trends.

[0041] Without being limited to this list, some example features of the application 106 may include one or more of a reporting feature, an intervention feature, a medication reminder feature, a glycemic impact estimation feature, an educational feature, and the like.

[0042] In certain embodiments, the reporting feature can provide reports to the user in various forms. For example, the reporting feature can be configured to report blood glucose excursions to the user in isolation, allowing the user to consider the causes of the excursions. In certain embodiments, the reporting feature can provide a report that combines the user's glucose, insulin, and menstrual cycle information. For example, the report may show how the user's glucose levels and insulin resistance have changed in relation to various phases of the user's menstrual cycle. In certain embodiments, the report (e.g., real-time) may remind the user about where they are in their menstrual cycle and indicate the contributing factors to the blood glucose excursion they are currently experiencing. In certain embodiments, the report may remind the user about where they are in their menstrual cycle and further alert or notify the user that, for example, they will experience a blood glucose excursion in two days because they will enter their luteal phase in two days.

[0043] Additionally, as one skilled in the art will appreciate, reports may be provided to the user in a variety of forms. For example, a report feature may display a graph of the user's glucose measurement trend with two blood glucose excursions highlighted with text stating, "You had two high glucose events today, the first lasting 55 minutes and the second lasting 30 minutes." In one example, a graph of the user's glucose measurement trend or prediction may be supplemented with a timeline of the user's menstrual cycle to indicate, for example, why the user is experiencing higher-than-usual glucose levels, why the user will experience higher-than-usual glucose levels on a particular future date (e.g., if the user is not consuming or engaging in therapy), etc. Combining the user's past, current, and / or predicted physiological statistics with information about the user's menstrual cycle may enable the user to make informed decisions regarding available treatment options that may be provided by the DSTA 100.

[0044] In one example, the reporting feature may provide an afternoon report providing information about the user's blood glucose average so far that day, indicate the remaining day's average needed to move toward the user's target glucose range, and recommend a lower glycemic load or physical activity. In another example, the reporting feature may provide an overnight summary including daily, weekly, and monthly blood glucose averages and an estimated A1c. For example, the summary may inform the user what the next day's blood glucose average needs to be in order for the user to achieve their A1c goal.

[0045] In certain embodiments, reporting features may focus on providing teachable moments to the user. In certain embodiments, the teachable moments identify the effect of actions (e.g., physical activity, dietary restrictions, medication adherence, and / or sleep) on blood glucose. The teachable moments may be pushed to the user in the form of notifications and / or recorded on the glucose monitoring curve for timely review by the user. For example, the teachable moments may be visually displayed on the curve to illustrate actions and glucose responses, to inform the user as to which actions caused which glucose responses.

[0046] An example of a positive teachable moment may be provided when a user eats a high glycemic load breakfast that raises blood glucose levels around 10:00 AM. In particular embodiments, based on input from the user's accelerometer, the reporting feature then determines that the user has walked for 30 minutes, which brings the user's blood glucose back into the target range. In particular embodiments, the reporting feature may mark this event as a teachable moment (e.g., by displaying a star on the CGM curve) and send a notification to the user stating, "Nice walk, Sharon! 30 minutes of walking has brought your blood glucose back down to the desired value."

[0047] In particular embodiments, an intervention feature includes any feature that operates to modify a user's actions, such as by prompting the user to engage in a particular action or to refrain from engaging in a particular action. As an example, an intervention feature may be configured to send a push notification to the user to prompt the user to engage in a particular action. The intervention feature may also determine, for example, based on the user's past actions, that the user is about to engage in a particular action and send a push notification to the user not to engage in such action. In some embodiments, the push notification to the user may be based on information related to the user (e.g., inputs 127, metrics 130, etc.) and / or information related to tiered groups of users.

[0048] For example, certain intervention features may involve exercise management. One example includes an exercise management feature that prompts a user, e.g., via push notification, to exercise when it determines that the user's glucose level is high or becoming high, or that lack of exercise is at a level that may increase the user's glucose level. As an example, based on where the user is in their menstrual cycle and information related to the user and / or a group of similar users, the exercise management feature may recommend that the user exercise two more hours over the next few days as the user begins to enter the luteal phase.

[0049] In particular embodiments, the exercise management feature may be configured to receive and analyze data from an accelerometer, a global positioning system (GPS), a heart rate monitoring sensor, a glucose monitoring system 104, and / or other types of sensors and devices to provide more effective and tailored guidance to the user. For example, by receiving information from one or more of these sensors and devices, the exercise management feature may be able to determine whether the user actually engaged in exercise, how long the user should exercise to ensure the user's blood glucose returns to a normal range, which walking route the user should take, etc.

[0050] Another type of intervention feature may involve dietary management. For example, the dietary management feature may act as a virtual nutritionist to provide guidance to the user regarding one or more of when to eat, what to eat, how much to eat, etc. In certain embodiments, the dietary management feature may provide personalized dietary recommendations based on one or more of the user's real-time condition (e.g., real-time blood glucose measurements), the user's body's response to particular meals, etc. In certain embodiments, the dietary management feature also assists the user with meal preparation and / or shopping, and / or allows the user to input information about meals consumed so the user can understand nutritional values, etc. In certain embodiments, the dietary management feature may further generate menu and ingredient substitutions at restaurants, or suggest healthy restaurants and grocery stores within a particular area. In certain embodiments, based on where the user is in their menstrual cycle and information related to the user and / or a group of similar users, the dietary management feature may recommend, for example, that the user change their diet for the next few days because the user is beginning to enter their luteal phase. For example, the diet management feature can calculate portion sizes or amounts of different types of foods (e.g., carbohydrates, sweets, etc.) that the user can consume and still be within the target glucose range. The diet management feature may also remind the user to refrain from consuming certain types of foods or consuming more than a certain amount of that food because the user has been or will become insulin resistant for a certain period of time.

[0051] In certain embodiments, the dietary management feature may also provide notifications based on information about the user's meal information. For example, if a user eats a meal and their blood glucose does not subsequently fall into a target zone (e.g., if their next pre-meal peak (2 hours after the glucose rise associated with their first meal) exceeds 180 mg / dL), an urgent alert may be issued to the user to exercise immediately. However, if the user's last meal's post-meal peak is below 180 mg / dL and their pre-meal glucose is in the range (80-130), the dietary management feature may randomize when the user receives an alert after their next meal (e.g., reduce the likelihood of sending an alert by 33%). Note that the exercise and dietary management features described above are just two examples of intervention features.

[0052] In certain embodiments, the medication management feature may provide notifications to a user about when the user needs to take medication, what type of medication (e.g., oral medication for Type II diabetes patients, insulin injections for Type I diabetes patients, etc.) and in what dosage or amount the user should take. The medication management feature may provide such notifications based on user-specific information, such as the user's disease (e.g., Type I or Type II), current and predicted metrics 130 (e.g., current blood levels and metrics), the user's menstrual cycle information, information related to similar groups of users, etc. For example, the medication management feature may be configured to learn over a certain period of time (e.g., several months) how likely the user is to become insulin resistant during certain dates in their menstrual cycle and how much basal insulin the user needs to administer during or in preparation for those dates. As a more specific example, the medication management feature may determine that the user is two days away from entering the luteal phase and may prompt the user to administer a double dose of basal insulin in preparation for the user becoming insulin resistant, or may prompt the user if it may signal the user's insulin pump to automatically begin administering a double dose of basal insulin. In another example, the medication management feature may detect that the user is beginning to become insulin resistant and recommend administering twice the amount of basal insulin that the user normally administers on days when the user is not insulin resistant.

[0053] In certain embodiments, the medication management feature may determine, based on the user's historical information, that a particular extra dose of basal insulin administered during a particular phase of the user's menstrual cycle (e.g., the luteal phase) was successful in maintaining the user's glucose levels within range. In such an example, the medication management feature may recommend that the user administer that extra dose or automatically instruct the insulin pump to administer the extra dose during or in anticipation of an increase in the user's insulin resistance due to hormonal changes during the menstrual cycle. In certain embodiments, the medication management feature may determine how much extra insulin should be administered to the user based on what has been effective for a group of similar users.

[0054] In certain embodiments, the learning process involved in determining the appropriate amount of additional insulin to administer to counter changes (e.g., increases) in insulin resistance due to the user's menstrual cycle involves examining the user's historical information, such as how the user becomes insulin resistant during certain dates, how much insulin is typically needed to bring the user's glucose levels back into range, patterns regarding the user's time in range during certain dates given the amount of insulin taken, and / or similar information associated with one or more similar users. For example, in certain embodiments, the medication management feature may learn that in month X, during certain cycle-related dates, the user recommended that the user take 1.5 times the amount of basal insulin the user normally takes, but the user's glucose levels did not return to range or the user was out of range for more time than desired. Based on this, in certain embodiments, the application may recalculate dosage and recommend that the user take 1.7 times the amount of basal insulin the user normally takes during the same dates in month X+1. Based on the recommended pattern of insulin dosages and the user's physiological response (e.g., time in range), the medication management feature may eventually learn (e.g., via DAM113, as described below) the appropriate amount of insulin to recommend to the user depending on where the user is in their menstrual cycle.

[0055] In certain embodiments, the medication management feature may also track how well the user adheres to their medication schedule, automatically order medication for the user before they run out, and / or provide information about the medication itself (e.g., educate the user about the medication's effects and effectiveness). For example, the medication management feature may query the patient as to whether they have taken their medication. If the user answers "yes" three times in a row, the medication management feature may randomize and assign a 33% chance of asking the user the next day. If the user does not answer "yes" three times in a row, the medication management feature may send the user a reminder to take their medication the next day.

[0056] In certain embodiments, as described above, the medication management feature may automatically communicate with an insulin administration device, such as a pump or pen, to cause the device to administer the correct dose of insulin based on the user's current or predicted metrics 130. For example, the medication management feature may determine the correct amount of long-lasting insulin to be administered taking into account the user's current glucose level and metrics, as well as the user's predicted glucose level and metrics. In certain embodiments, the medication management feature may then signal the medication administration device to administer that amount of insulin. As described above, in certain embodiments, the medication management feature calculates the amount of insulin to be administered taking into account information related to the user and / or information related to tiered groups of users. Exemplary details regarding how the DSTA 100 (including the application 106) can set the insulin rate of an insulin administration device (also referred to as a medication delivery device) are described in paragraphs

[0425] -

[0426] of U.S. Patent Application Publication No. 2019 / 0246973, which is incorporated herein in its entirety.

[0057] In certain embodiments, the glycemic impact estimation feature can use the camera of the mobile device 107 to scan the menu and convert each meal item into an estimated glycemic impact metric. In some embodiments, the glycemic impact estimation feature shows the glycemic impact metrics overlaid on the menu items. In some embodiments, the glycemic impact metrics are based on data from user profiles of stratified groups of users. In some embodiments, the glycemic impact estimation feature can use different colors to highlight different menu items based on how healthy the items are (e.g., green for healthier items and red for unhealthy items).

[0058] In certain embodiments, the educational feature educates the user about the user's condition and how the user can improve their health. In one example, the educational feature educates the user about the potential impact the user may perceive if they adopt a particular lifestyle. In certain embodiments, to determine the potential impact, the educational feature may consider the impact experienced by other users in stratified groups who adopted the same lifestyle. For example, the educational feature may state to the user, "By following this program, patients like you have been able to lower their A1C by 5% during the luteal phase." In certain embodiments, the educational feature may also educate the user about the causes and effects of potential actions, such as based on the effects experienced by users in stratified groups.

[0059] In certain embodiments, the educational feature provides an alternative for administering insulin or a higher-than-desired amount of insulin during a particular period of a user's menstrual cycle. For example, the educational feature may examine information related to a tiered group of users and discover that a particular user in the group was able to maintain glucose within a target range without taking a higher-than-normal amount of insulin by exercising for an additional hour during the luteal phase. In such an example, the educational feature may notify the user of this discovery. Based on this discovery, the exercise management feature may also recommend that the user engage in an additional hour of exercise during the luteal phase, and further recommend the type and intensity of exercise based on the user's habits. In another example, the educational feature may examine information related to a tiered group of users and discover that a particular user in the group was able to maintain glucose within a target range by consuming less of certain foods during the luteal phase without taking a higher-than-normal amount of insulin. Similarly, in such an example, the educational feature may notify the user of this discovery, and the diet management feature may, based on the same discovery, make specific recommendations about how the user can modify their diet, how many portion sizes to eat, etc.

[0060] FIG. 1B shows glucose monitoring system 104 in more detail. FIG. 1B also shows several mobile devices 107a, 107b, 107c, and 107d. Note that mobile device 107 in FIG. 1A can be any one of mobile devices 107a, 107b, 107c, or 107d. In other words, any one of mobile devices 107a, 107b, 107c, or 107d can be configured to execute application 106. Glucose monitoring system 104 can be communicatively coupled to mobile devices 107a, 107b, 107c, and / or 107d. Glucose monitoring system 104 can also be communicatively coupled to an insulin administration device (not shown) that can be placed on a user's body to administer insulin to the user's body.

[0061] By way of overview and example, glucose monitoring system 104 may be implemented as an encapsulated microcontroller that performs sensor measurements, generates analyte data (e.g., by calculating values ​​of continuous glucose monitoring data), and engages in wireless communication (e.g., via Bluetooth and / or other wireless protocols) to transmit such data to remote devices, such as mobile devices 107a, 107b, 107c, and / or 107d. Paragraphs

[0137] -

[0140] and Figures 3A, 3B, and 4 of U.S. Patent Application No. 2019 / 0336053 further describe on-skin sensor assemblies that may be used in connection with glucose monitoring system 104 in certain embodiments. Paragraphs

[0137] -

[0140] and Figures 3A, 3B, and 4 of U.S. Patent Application No. 2019 / 0336053 are incorporated herein by reference.

[0062] In certain embodiments, glucose monitoring system 104 includes an analyte sensor electronics module 138 and a glucose sensor 140 associated with analyte sensor electronics module 138. In certain embodiments, analyte sensor electronics module 138 includes electronic circuitry related to measuring and processing analyte sensor data or information, including algorithms related to processing and / or calibrating the analyte sensor data / information. Analyte sensor electronics module 138 may be physically / mechanically connected to glucose sensor 140 and may be integral with (i.e., non-removably attached to) or removably attached to glucose sensor 140.

[0063] The analyte sensor electronics module 138 may also be electrically coupled to the glucose sensor 140 such that the components may be electromechanically coupled to one another. The analyte sensor electronics module 138 may include hardware, firmware, and / or software that enables measurement and / or estimation of analyte levels in a user via the glucose sensor 140 (e.g., which may be / include a glucose sensor). For example, the analyte sensor electronics module 138 may include a potentiostat, a power supply for powering the glucose sensor 140, other components useful for signal processing and data storage, and a telemetry module for transmitting data from the sensor electronics module to one or more display devices. The electronics may be fixed, such as to a printed circuit board (PCB) or platform within the glucose monitoring system 104, and may take a variety of forms. For example, the electronics may take the form of an integrated circuit (IC), such as an application-specific integrated circuit (ASIC), a microcontroller, a processor, and / or a state machine.

[0064] The analyte sensor electronics module 138 may include sensor electronics configured to process sensor information, such as sensor data, and generate transformed sensor data and displayable sensor information. Examples of systems and methods for processing sensor analyte data are described in further detail herein, as well as in U.S. Pat. Nos. 7,310,544 and 6,931,327, and U.S. Patent Publication Nos. 2005 / 0043598, 2007 / 0032706, 2007 / 0016381, 2008 / 0033254, 2005 / 0203360, 2005 / 0154271, 2005 / 0192557, 2006 / 0222566, 2007 / 0203966, and 2007 / 0208245, all of which are incorporated by reference in their entireties.

[0065] The glucose sensor 140 is configured to measure the concentration or level of an analyte in the user 102. The term analyte is further defined by paragraph

[0117] of U.S. Patent Application No. 2019 / 0336053, which paragraph

[0117] of U.S. Patent Application No. 2019 / 0336053 is incorporated herein by reference. In some embodiments, the glucose sensor 140 includes a continuous glucose sensor, such as a subcutaneous, transcutaneous (e.g., transdermal), or intravascular device. In some embodiments, the glucose sensor 140 is capable of analyzing multiple intermittent blood samples. The glucose sensor 140 can use any glucose measurement method, including enzymatic, chemical, physical, electrochemical, spectrophotometric, polarimetric, calorimetric, iontophoretic, radiometric, immunochemical, and the like. Additional details regarding continuous glucose sensors are provided in paragraphs

[0072] -

[0076] of U.S. Patent Application No. 13 / 827,577. Paragraphs

[0072] -

[0076] of U.S. Patent Application No. 13 / 827,577 are incorporated herein by reference.

[0066] 1B , mobile devices 107a, 107b, 107c, and / or 107d may be configured to display (and / or alarm) displayable sensor information that may be transmitted by sensor electronics module 138 (e.g., in a customized data package transmitted to a display device based on respective preferences). Mobile devices 107a, 107b, 107c, and / or 107d may each include a display, such as touchscreen display 109a, 109b, 109c, and / or 109d, respectively, for presenting sensor information and / or analyte data to user 102 and / or displaying a graphical user interface of application 106 for receiving input from user 102. In certain embodiments, the mobile devices may include other types of user interfaces, such as a voice user interface, instead of or in addition to a touchscreen display for communicating sensor information to mobile device user 102 and / or receiving user input. In particular embodiments, one, some, or all of mobile devices 107a, 107b, 107c, and / or 107d may be configured to display or otherwise communicate sensor information as communicated from sensor electronics module 138 (e.g., in data packages transmitted to a respective display device) without any additional predictive processing required for calibration and / or real-time display of sensor data.

[0067] 1B may include a custom or proprietary display device, such as analyte display device 107b specifically designed to display a particular type of displayable sensor information related to analyte data (e.g., in certain embodiments, numerical values ​​and / or arrows) received from sensor electronics module 138. In certain embodiments, one of mobile devices 107a, 107b, 107c, and / or 107d includes a smartphone, such as mobile phone 107c based on Android, iOS, or another operating system configured to display a graphical representation of continuous sensor data (e.g., including current and / or historical data).

[0068] FIG. 2 provides a more detailed view of exemplary inputs and exemplary metrics determined based on the inputs, according to certain embodiments. FIG. 2 illustrates exemplary inputs 127 on the left, application 106 and DAM 113 in the center, and metrics 130 on the right. In certain embodiments, each metric may correspond to one or more values, such as a discrete numeric value, a range, or a qualitative value (high / medium / low or stable / unstable). Application 106 obtains inputs 127 through one or more channels (e.g., manual user input, sensors, other applications running on mobile device 107, etc.). In certain embodiments, inputs 127 may be used by features of application 106 to provide guidance and therapy to the user (e.g., including signaling an insulin pump to administer a particular dose of insulin). Inputs 127 may also be further processed by DAM 113 to output multiple metrics, such as metric 130, which may in turn be used by features of application 106 to provide guidance and therapy to the user.

[0069] As shown, inputs 127 include, but are not limited to, food consumption information, activity information, patient demographics, insulin information, information from sensors, blood glucose information, time, calendar, user input, menstrual cycle information, and the like.

[0070] Food consumption information may include information about one or more of meals, snacks, and / or beverages, such as one or more of size, content (carbohydrates, fat, protein, etc.), order of consumption, and time of consumption. In certain embodiments, food consumption may be provided by the user through manual input, by providing a photo through an application configured to recognize food types and quantities, and / or by scanning a barcode or menu. In various examples, meal size may be manually entered as one or more of calories, quantity ("3 cookies"), menu item ("Royale with Cheese"), and / or food exchange (1 fruit, 1 dairy product). In some examples, meals may also be entered with items or combinations typical of the user for this time or situation (e.g., weekday breakfast at home, weekend brunch at a restaurant). In some examples, meal information may be received through a convenient user interface provided by application 106.

[0071] In certain embodiments, activity information is also provided as input. Activity information may be provided, for example, by an accelerometer sensor on a wearable device such as a watch, fitness tracker, and / or patch. In certain embodiments, activity information may also be provided through manual user input.

[0072] In certain embodiments, patient demographics, such as one or more of age, height, weight, body mass index, body composition (e.g., percentage of body fat), stature, build, or other information, may be provided. In certain embodiments, the patient demographics are provided via a user interface, by interfacing with an electronic source such as an electronic medical record, and / or from a measurement device. In certain embodiments, the measurement device includes, for example, one or more of a wireless, e.g., Bluetooth-enabled, scale and / or camera that may communicate with the mobile device 107 to provide patient data.

[0073] In certain embodiments, input related to the patient's insulin delivery may be received via a wireless connection on the smart pen, via user input, and / or from an insulin pump (a type of insulin administration device). Insulin delivery information may include one or more of insulin volume, delivery time, etc. Other parameters, such as insulin action time or duration of insulin action, may also be received as input.

[0074] In certain embodiments, input may be received from sensors such as physiological sensors that may detect one or more of heart rate, respiration, oxygen saturation, or body temperature (e.g., to detect illness). In certain embodiments, electromagnetic sensors may also detect low-power RF fields emitted from objects or tools in contact with or near objects, which may provide information about the patient's activity or location. An example of information that can be received from a sensor is the user's blood glucose level.

[0075] In certain embodiments, blood glucose information may also be provided as an input, for example, via glucose monitoring system 104. The blood glucose information may include any glucose-related measurement known in the art. In certain embodiments, the blood glucose information may be received from one or more of a smart pill dispenser that tracks when a user takes medication, a blood ketone meter, laboratory-measured or estimated AlC, other long-term control measurements, or a sensor that measures peripheral neuropathy using tactile responses, such as using the tactile features of a smartphone or a specialized device.

[0076] In certain embodiments, the time may also be provided as an input such as the time of day or the time from a real-time clock, which may also include the date, month, and year.

[0077] User input via a user interface, such as the user interface of the mobile device 107, may include other types of input that a user may provide to the application 106, such as the other types of input described above. For example, in certain embodiments, user input may include one or more of the following: type of amount of food consumed; delivery of therapy, such as the use of glucagon to stimulate hepatic release of glycogen in response to hypoglycemia; recommended basal amount or insulin-to-carbohydrate ratio (e.g., received from a clinician); recorded activity (e.g., intensity, duration, and time completed or started); etc. In certain embodiments, user input may also indicate medication intake (e.g., type and dosage of medication, and timing of medication intake).

[0078] In certain embodiments, input 127 further includes information regarding the user's menstrual cycle. As described above, this information may be received from a third-party application, such as a period-tracking application. In certain embodiments, the third-party application may periodically interface with application 106, for example, via an application programming interface. The information regarding the user's menstrual cycle may include information regarding one or more of the different phases of the user's cycle, the duration of each phase, the corresponding dates, the dates the user is scheduled to enter each phase, which phase the user is currently in, when the current date is scheduled to end, etc. In certain embodiments, the user may supplement the information provided by the third-party application with user input. For example, the user may provide input such as that the user's menstrual period has just begun. In certain embodiments, application 106 may not rely on any input from the third-party application, but instead rely solely on user input. In such embodiments, for example, application 106 may calculate information regarding the user's menstrual cycle based on user input and / or certain science-based logic.

[0079] As noted above, in certain embodiments, the DAM 113 determines or calculates metrics 130 for the user based on the inputs 127. An exemplary list of metrics 130 is shown in FIG.

[0080] In certain embodiments, metabolic rate is a metric that can indicate or include basal metabolic rate (e.g., energy expended at rest) and / or active metabolism, e.g., energy expended by activity such as exercise or exertion. In some examples, basal metabolic rate and active metabolism may be tracked as separate metrics. In certain embodiments, metabolic rate may be calculated by DAM 113 based on one or more of inputs 127, e.g., one or more of activity information, sensor input, time, user input, etc.

[0081] In certain embodiments, the activity level metric may indicate a user's activity level. In certain embodiments, the activity level metric may be determined based on input from, for example, an activity sensor or other physiological sensor. In certain embodiments, the activity level metric may be calculated by the DAM 113 based on one or more of the inputs 127, for example, one or more of activity information, sensor input, time, user input, etc.

[0082] In certain embodiments, the insulin sensitivity metric may be determined using historical data, real-time data, or a combination thereof, and may be based on one or more inputs 127, such as, for example, one or more of food consumption information, blood glucose information, insulin delivery information, resultant glucose levels, etc. In certain embodiments, the insulin on-board metric may be determined using insulin delivery information and / or a known or learned (e.g., from patient data) insulin time-action profile, which may take into account both basal metabolic rate (e.g., insulin updates to keep the body running) and insulin usage caused by activity or food consumption.

[0083] In certain embodiments, the meal state metric may indicate the state the user is in with respect to food consumption. For example, the meal state may indicate whether the user is in a fasting state, a pre-meal state, a eating state, a post-meal response state, or a stable state. In certain embodiments, the meal state may also indicate on-board nutrition, e.g., meals, snacks, or beverages consumed, and may be determined from, for example, food consumption information, mealtime information, and / or digestibility information that may correlate to food type, amount, and / or order (e.g., which food / drink was eaten first).

[0084] In particular embodiments, the health and illness metrics may be determined based on one or more of, for example, user input (e.g., pregnancy information or known illness information) from a physiological sensor (e.g., temperature), an activity sensor, or a combination thereof. In particular embodiments, for example, based on the values ​​of the health and illness metrics, the user's state may be defined as one or more of healthy, sick, rested, or exhausted.

[0085] In certain embodiments, glucose level metrics may be determined from sensor information (e.g., blood glucose information obtained from glucose monitoring system 104). In some examples, glucose level metrics may also be determined based on historical information regarding glucose levels in particular situations, e.g., given a combination of food consumption, insulin, and / or activity.

[0086] In certain embodiments, the metrics 130 also include a stage of disease, such as a type II diabetes patient. Exemplary stages of disease for a type II diabetes patient may include a prediabetic stage, an oral treatment stage, and a basal insulin treatment stage. In certain embodiments, the degree of glycemic control (not shown) may also be determined as a metric and may be based, for example, on one or more of glucose levels, glucose level variability, or insulin administration patterns.

[0087] In certain embodiments, clinical metrics generally indicate the clinical state a user is in with respect to one or more of the user's conditions, such as diabetes. For example, in the case of diabetes, clinical metrics may be determined based on blood glucose measurements including one or more of A1c, A1c trend, time in range, time spent below a threshold level, time spent above a threshold level, and / or other metrics derived from blood glucose values. In certain embodiments, clinical metrics may also include one or more of estimated A1c, blood glucose variability, hypoglycemia, and / or health indicators (amount of time outside a target zone).

[0088] In certain embodiments, the metrics 130 also include behavioral metrics, which may include dietary habits, adherence to disease treatment, medication type and adherence, exercise regimen, etc. As described further below, in certain embodiments, the DAM 113 can use a historical record of a user's behavioral metrics to identify trends and may predict the user's future behavior based thereon. In certain embodiments, dietary habits are measured by one or more metrics based on the content and timing of the user's meals. For example, if the dietary habit metric is on a scale of 0 to 1, in the example, the better / healthier the user eats, the closer the user's dietary habit metric will be to 1. Also, in this example, the more the user's food consumption adheres to a particular time schedule, the closer the dietary habit metric will be to 1. In certain embodiments, disease treatment and adherence is measured by one or more metrics that indicate how diligent the user is in treating the user's disease.

[0089] In certain embodiments, disease treatment and adherence metrics are calculated based on one or more of a user's dietary restrictions or food consumption, exercise regimen, medication adherence, etc. In certain embodiments, medication adherence is measured by one or more metrics that indicate how diligent a user is with their medication regimen. In certain embodiments, medication adherence metrics are calculated based on one or more of when a user takes their medication (e.g., whether the user is on time or on schedule), the type of medication (e.g., whether the user is taking the correct type of medication), and the dosage of the medication (e.g., whether the user is taking the correct dosage).

[0090] In certain embodiments, the exercise regimen is measured by one or more metrics indicative of one or more of the type of activity the user engages in, the intensity of the activity, the frequency with which the user engages in such activity, etc. In certain embodiments, the exercise regimen metrics may be calculated based on one or more activity sensors, calendar input, user input, etc.

[0091] In certain embodiments, the inputs 127 and metrics 130 are time-stamped to create a record of the user's historical data. Based on this record of historical data, the DAM 113 can determine correlations between different inputs 127, between different metrics 130, and / or between the inputs 127 and the metrics 130. For example, based on the historical data, a correlation between the user's menstrual cycle and the user's blood glucose levels during different phases of the menstrual cycle may be determined. As one skilled in the art will appreciate, correlations between various inputs 127 and / or metrics 130 can similarly be determined. For example, correlations between administered insulin doses, blood glucose levels, and different phases of the menstrual cycle may be determined. In certain embodiments, based on the record of historical data and / or the determined correlations, the DAM 113 can predict the user's changes in insulin resistance and blood glucose levels during different phases of the menstrual cycle, as well as the expected effects of various doses of basal and bolus insulin, exercise, and food consumption on glucose levels during different phases of the menstrual cycle. In certain embodiments, based on such predictions, different features of the application 106 may then recommend different treatments, such as different doses of basal and / or bolus insulin, particular types and / or lengths of exercise, and particular types and / or portions of food.

[0092] 3 is a flow diagram illustrating example operations 300 performed by a system (e.g., DSTA 100) that provides one or more treatments to a user based on where the user is in their menstrual cycle. The one or more treatments are determined based on information related to the user and / or information related to a pool of users, such as a stratified group of users who are similar to the user in one or more aspects. Operations 300 are described below with reference to FIGS. 1A-1B and 2 and their components. It should be noted that the steps of operations 300 may not necessarily be performed in the order described herein. Additionally, some steps herein may be omitted and / or additional states may be added.

[0093] In step 302, operation 300 begins with measuring a user's blood glucose. In certain embodiments, step 302 is performed by glucose monitoring system 104. In certain embodiments, glucose monitoring system 104 is a continuous glucose monitoring system that can measure a user's blood glucose level periodically (e.g., every five minutes). In certain embodiments, glucose measurements are received and recorded by application 106 over time so that a record of glucose measurements can be created. In certain embodiments, the record shows all past glucose measurements, including the most recent glucose measurement, which is considered the user's real-time glucose measurement. Note that in certain embodiments, application 106 can receive glucose measurements from glucose monitoring system 104, with the user going through a setup process with application 106 prior to using glucose monitoring system 104 to ensure that application 106 and glucose monitoring system 104 identify each other and communicate securely. In certain embodiments, the user provides at least one of demographic information 118 , disease progression information 120 , and medication information 122 to the application 106 during the setup process or at an early stage of using the application 106 .

[0094] In step 304, operations 300 continue, in some embodiments, by receiving information about the user's menstrual cycle. In particular embodiments, step 302 is performed by DAM 113. For example, DAM 113 may receive information about the user's menstrual cycle as part of input 127. As noted above, in particular embodiments, the information may be received from a third-party software application that can track where the user is in their menstrual cycle in real time and determine how long each phase lasts and when each phase begins. Such a software application may run on mobile device 107 or on another computing device in communication with mobile device 107 and / or DAM 113 over a network. In particular embodiments, as noted above, DAM 113 may receive information about the user's menstrual cycle in the form of manual user input. For example, the user may input information about the start and end of their period, as well as any additional information the user has about their menstrual cycle.

[0095] In step 306, operations 300 continue by determining one or more treatments for the user to maintain or return the user's glucose level to within a target range based on information about the user's menstrual cycle and at least one of the user's historical data and historical data associated with stratified groups of similar users. In certain embodiments, step 306 may be performed by DAM 113.

[0096] In certain embodiments, the DAM 113 bases one or more treatment decisions on several data points indicated by or calculated (e.g., predicted) based on the user's historical data and / or historical data associated with similar users in a stratified group. More specifically, in certain embodiments, the DAM 113 can base one or more treatment decisions on what the user's glucose level and / or insulin resistance rate are at a particular time point in the present and / or future (e.g., during different phases of the menstrual cycle). Furthermore, in certain embodiments, the DAM 113 may base one or more treatment decisions on treatments that have been effective in the past (e.g., over the past few days, months, or years) to maintain or return the user's glucose level to a target range and / or information regarding treatments that have been effective in the past to maintain or return the glucose level of one or more users in a stratified group. Note that a target range may refer to or include a target blood glucose level (e.g., a particular measurement).

[0097] As an example, a user's glucose level may currently be higher than a target glucose level. In such an example, the DAM 113 may base one or more treatment decisions on at least the user's current glucose level, the difference between the current glucose level and the target glucose level, and / or the user's current insulin resistance rate. The user's current insulin resistance rate in this case may be calculated in real time or based on the user's own historical data and / or historical data associated with stratified groups. For example, in certain embodiments, the user's current insulin resistance rate may be based on where the user is in their menstrual cycle and / or how insulin resistant the user previously became during the same period in the user's past menstrual cycles.

[0098] In another example, the DAM 113 may determine one or more treatments to help the user maintain or achieve a particular glucose level at some point in the future. In such an example, the DAM 113 may base one or more treatment decisions at least on the user's future glucose level and / or insulin resistance rate, which may be predicted based on the user's record of historical data and / or record of historical data for one or more users in stratified groups. As an example, a user may be two days away from entering the luteal phase. In such an example, the DAM 113 may predict this event, predict the user's insulin resistance during the luteal phase, and determine one or more treatments that have been effective in the past in helping the user achieve a particular glucose level during the luteal phase. As an example, in a simplified case, the DAM 113 may determine, for example, that administering a particular dose of basal insulin two days before the user enters the luteal phase will be effective in maintaining the user's glucose level in a target range, as long as the user continues to follow the same diet and exercise regimen.

[0099] In certain embodiments, when a user begins using the application 106, sufficient inputs 127 and metrics 130 may not be available for them. Thus, in certain embodiments, it is not possible to draw reliable conclusions about how the user's glucose levels will fluctuate and / or how the user will become insulin resistant in response to the user's hormonal changes during different phases of the menstrual cycle. Similarly, in such embodiments, it is not possible to draw reliable conclusions about what treatments will or may be effective in maintaining or bringing the user's glucose levels back into range during different phases of the menstrual cycle. In certain embodiments, at least several months' worth of inputs 127 and metrics 130 (e.g., one month or more) should be available to the user to be able to draw confident conclusions based on the user's own historical data, but this is not required. Thus, at least initially, the DAM 113 may use one or more users' historical data in the user database 110 to predict how the user's glucose levels will fluctuate and / or how the user will become insulin resistant during different phases of the menstrual cycle, and what treatments will or may be effective during such phases.

[0100] In certain embodiments, DAM 113 may utilize historical data for all users in user database 110 to make the above predictions. However, in certain other embodiments, DAM 113 may first stratify user database 110 based on one or more similarity or stratification factors. In certain embodiments, depending on the data model and analysis used, predictions made based on a dataset of stratified groups of similar users may be more accurate than predictions made based on a dataset associated with all users in user database 110.

[0101] A tiered group of users refers to a group of users in the user database 110 that are similar to the user in one or more aspects. For example, when the user first begins using the application 106, certain information may be determined about the user. Such information may include the user's demographic information 118, disease progression information 120, and / or medication information 122. As part of the input 127, the application 106 may also initially receive input regarding the user's menstrual information. As described above, all of these inputs may be recorded in the user profile 116. Thus, the DAM 113 may retrieve the user profile 116 from the user database 110 and select the tiered group of users from the user database 110 based on one or more similarities between the information in the user profile 116 and the user profiles of the pool of users in the user database 110. For example, the DAM 113 may use one or more similarity or stratification factors for stratification, where the one or more stratification factors include at least one of the user's disease progression information, medication information, demographic information, menstrual cycle information, and / or any other additional data available in the user profile 116 (e.g., inputs 127 and metrics 130, if available).

[0102] One of a variety of methods and approaches can be used to stratify the user database 110 based on one or more stratification factors (e.g., disease progression, medication information, demographic information, goals, menstrual cycle, inputs 127, metrics 130, or a combination thereof). In certain embodiments, the DAM 113 can use one of a variety of data filtering techniques to filter the broader user database 110 based on one or more stratification factors. For example, if a user has type 1 diabetes, the DAM 113 may filter all user profiles in the user database 110 that have type 1 diabetes. The stratified group of users then includes all such users. However, in certain embodiments, if additional stratification factors are used for stratification, additional filtering can be performed to further narrow the group of users in the stratified group. For example, if the stratification factors include disease progression and demographic information and the user is a woman with type 1 diabetes, the DAM 113 may filter all user profiles of all female users in the user database 110 that have type 1 diabetes.

[0103] In particular embodiments, the DAM 113 may use a machine learning algorithm to stratify the user database 110. For example, an unsupervised learning algorithm may be used to cluster all of the user profiles in the user database 110 and determine which cluster the user profile 116 belongs to. Unsupervised learning is a type of machine learning algorithm used to draw inferences from a dataset consisting of labeled, unresponsive input data. As one skilled in the art will appreciate, in addition to unsupervised learning algorithms that focus on clustering analysis, other types of unsupervised learning algorithms may be used.

[0104] In certain embodiments, a supervised learning algorithm may be used instead. Supervised learning is a machine learning task that learns a function that maps inputs to outputs, for example, based on example input-output pairs. In certain embodiments, the DAM 113 may be configured to classify the user profile 116 by using a supervised learning algorithm to determine which class or stratified group of users the user belongs to based on a machine learning model trained using a labeled dataset. In certain embodiments, the labeled data already includes different classes of users categorized based on one or more characteristics, such as disease progression. For example, in certain embodiments, one class of users includes all user profiles of women in the 25-27 age range, while another class of users includes all women in the 27-29 age range. In such an example, if the demographic information 118 of the user profile 116 indicates that the user is 26 years old, the DAM 113 selects the first class as the user in the stratified group (if age is the only stratification factor).

[0105] In some embodiments, when selecting users for a stratified group, DAM 113 may be configured to define ranges around each of the stratification factors. As an example, if a user is 25 years old, a four-year range may be defined such that all users in the 23-27 age range are included in the stratified group.

[0106] Once a group of users is selected from the user database 110, whether the group corresponds to all users in the user database 110 or to a stratified group of users, the DAM 113 uses the historical data records associated with such group to make predictions about the user's glucose levels and / or insulin resistance rates based on the user's menstrual cycle (e.g., during different phases of the menstrual cycle).

[0107] As an example, when a user first uses the application 106, the user profile 116 may indicate that the user is a 25-year-old Caucasian female who has Type 1 diabetes and injects insulin. The user profile 116 may also indicate details about the user's menstrual cycle. In such an example, the DAM 113 may stratify the user database 110 based on one or more of the stratification factors described above. For example, the DAM 113 may stratify the user database 110 to find a data set associated with all Caucasian female users in the age range of 24-26 who have Type 1 diabetes and inject insulin. Note that the DAM 113 may or may not use the user's menstrual cycle information as a stratification factor.

[0108] In certain embodiments, the DAM 113 can then examine the dataset to make a prediction about the user's glucose level and insulin resistance rate during a particular point in the user's menstrual cycle. For example, this may be two days before the user enters the luteal phase. In such an example, the DAM 113 makes this prediction based on the user's menstrual cycle information. Because information about how insulin resistant a user will be during the luteal phase or a particular subphase of the luteal phase (or other phases and / or subphases of the menstrual cycle) is not yet available, in certain embodiments, the DAM 113 then examines the dataset associated with stratified groups of users to determine how insulin resistant the users in the stratified groups will be, on average, during various phases and / or subphases of their menstrual cycle (e.g., the luteal phase).

[0109] In certain embodiments, a user's luteal phase (or any other phase of the menstrual cycle) may be divided into various subphases, with each subphase corresponding to a specific time range within the luteal phase. As an example, a user's luteal phase may include subphases such as a beginning subphase, a middle subphase, and an end subphase. In another example, subphases may correspond to days; for example, if a user's luteal phase is typically seven days, seven subphases may be defined. Subphases may also correspond to hours and minutes; for example, the first subphase of the luteal phase may correspond to the first hour of the luteal phase. Because insulin resistance varies by different amounts at different times during the luteal phase, in certain embodiments, dividing the luteal phase into subphases may help to more accurately determine how insulin resistant stratified groups of users are during a particular period, and based on this, the user's insulin resistance and / or glucose levels may be predicted.

[0110] Once the luteal phase is divided into subphases for all users, DAM 113 can determine the average change in insulin resistance for a stratified group of users during the same particular subphase that the user is in or will be in. For example, if a user is two days before entering the luteal phase, it means that the user is two days before entering the first subphase of the luteal phase, where the first subphase corresponds to the start phase, first day, or any other rule that DAM 113 may be configured for.

[0111] Thus, in certain embodiments, DAM113 examines datasets associated with stratified groups to determine how insulin resistant such users will become on average and / or how much their glucose levels will change during the first luteal subphase. Based on that information, in certain embodiments, DAM113 can predict how insulin resistant the user will become and / or how much their glucose levels will change during the first subphase if the user does not adopt additional treatment (e.g., additional exercise, a more restrictive diet, additional doses of basal and / or bolus insulin).

[0112] It should be noted that although certain embodiments herein describe changes in insulin resistance during the luteal phase, a user's insulin resistance may change during other phases of the menstrual cycle. Thus, the embodiments described herein are equally applicable to other phases or subphases of the menstrual cycle. In other words, the luteal phase is used merely as an example.

[0113] Also, note that in certain embodiments, instead of or in addition to examining datasets associated with stratified groups, DAM113 may consider scientific data points that indicate how much a user's insulin resistance and / or glucose levels may change, on average, during a particular phase and / or sub-phase of the user's menstrual cycle. For example, in certain embodiments, such scientific data points may be supported by scientific research and provided to DAM113 as a dataset that indicates how (e.g., how much) different users with different characteristics (e.g., demographic information, disease progression, medication information, menstrual cycle information, etc.) may experience changes in insulin resistance and / or glucose levels during different sub-phases and / or phases of their menstrual cycle. As an example, in such a case, a rules-based approach may be used; for example, if the user is 25 years old, a rule may indicate, based on scientific data points, that the user's insulin resistance will increase by 30% during the first sub-phase (e.g., the luteal phase) of a particular phase of the user's menstrual cycle, because women of that age generally experience that much increase in insulin resistance. The scientific data points may indicate changes in insulin resistance during each subphase and / or phase of the menstrual cycle. For example, the data may indicate that a user's insulin resistance increases by 40% during the second subphase.

[0114] In certain embodiments, predicting how insulin resistant a user may become during the first subphase and / or how much their glucose levels may potentially change can help the DAM 113 predict one or more therapies to maintain their glucose levels within a target range when the user enters the first subphase. For example, the DAM 113 may be configured with scientific data points indicating a particular type or amount of therapy that can help maintain the user's glucose levels within a particular range, even in light of changes in insulin resistance during a particular phase or subphase. For example, certain scientific data points may indicate that for a 25-year-old user, administering an additional 20% of basal insulin at a particular time before or during the first subphase is effective, on average, to counteract a 30% increase in insulin resistance during a particular subphase or phase of the menstrual cycle. In another example, scientific data points may indicate that an additional hour of exercise each day is effective to counteract a 10% increase in insulin resistance during a particular subphase or phase of the menstrual cycle. In another example, scientific data points show that following a more restrictive diet (e.g., reduced carbohydrates) daily is effective in counteracting a 15% increase in insulin resistance during a specific subphase or phase of the menstrual cycle.

[0115] Note that these are simplified examples to illustrate how data points based on scientific studies can be used to recommend treatments to a user. Accordingly, these simplified examples are not intended to limit the scope of the present disclosure. In certain embodiments, the DAM 113 may be configured with a rules-based approach, such that when scientific data points are used, for example, if a user's insulin resistance rate increases by 20% during the first subphase and the scientific data points suggest that an additional dose of insulin can counteract a 10% increase in insulin resistance, the DAM 113 may be configured to recommend a double dose to the user. In another example, the DAM 113 may instead be configured to recommend the same additional dose to counteract 10% of the increase and an additional hour of exercise each day to counteract another 10% increase, such as insulin resistance. In this manner, a combination of treatments (e.g., insulin, diet, exercise) may be recommended.

[0116] In certain embodiments, instead of or in addition to determining one or more treatments based on examining the above scientific data points, the DAM 113 may predict, based on datasets associated with stratified groups, which one or more treatments may be effective to counteract changes in a user's insulin resistance during a subphase or phase of the user's menstrual cycle. Note that, as noted above, in certain embodiments, the dataset may correspond to an entire pool of users rather than a stratified pool of users. In other words, a prediction regarding an effective treatment may be made similarly based on data associated with all users, and thus, the user database 110 need not be stratified. Those skilled in the art will appreciate various methods and operations that may be utilized to make such predictions based on datasets associated with stratified groups of users.

[0117] For example, in certain embodiments, one or more data models, machine learning models, regression models, functions, and algorithms may be used to predict one or more treatments, or combinations thereof, to counteract a particular amount of change in insulin resistance during a particular subphase or phase of the menstrual cycle. Some examples of different algorithms that may be used are described in connection with FIG.

[0118] In certain embodiments, these data models, machine learning models, regression models, functions, or algorithms may be used to look for correlations between different variables (e.g., data features, as described in more detail with respect to FIG. 4). In one example, one variable may be defined based on menstrual subphases or phases. Another variable may be glucose levels, or changes therein. Many other variables may be defined, including variables related to administered doses of insulin, variables related to amount and / or type of exercise, and variables related to type and / or amount of food consumed.

[0119] In certain embodiments, based on these correlations, DAM 113 may be able to identify consistent patterns, based on which DAM 113 may be configured to predict effective treatments for the user. These patterns, in certain embodiments, indicate the impact on the user's glucose levels of different types / amounts of medications (e.g., insulin) and types / amounts of user actions (e.g., exercise, foods) during different subphases / phases of the menstrual cycle.

[0120] For example, the dataset may indicate that, on average, for female users aged 24-26, administering a 20% additional dose of basal insulin (e.g., at a specific time before or during the first subphase) counteracts a 30% increase in insulin resistance during the first subphase of the luteal phase. In another example, the dataset may indicate that for Caucasian female users with type 1 diabetes, an additional hour of exercise daily counteracts a 10% increase in insulin resistance during a specific subphase or phase of the menstrual cycle. In yet another example, the dataset may indicate that for female users with the same exact menstrual cycle as the user, following a more restrictive diet (e.g., reduced carbohydrates) daily counteracts a 15% increase in insulin resistance during a specific subphase or phase of the menstrual cycle. Note that these are simplified examples intended to illustrate how datasets associated with groups of users can be used to recommend treatments to users. Accordingly, these simplified examples are not intended to limit the scope of the present disclosure. Based on these consistent patterns, DAM 113 can then predict that one or more treatments may be helpful to the user.

[0121] In particular embodiments, as additional inputs 127 and metrics 130 are received over time and stored in user profile 116, a dataset associated with the user's own historical data may be developed based on which DAM 113 may determine one or more treatments to help the user maintain or reach a particular glucose range based on where the user is in their menstrual cycle. For example, additional inputs 127 and metrics 130 may include information regarding different treatments provided to a user based on datasets and / or scientific data points associated with stratified groups of users (or entire groups of users in user database 110). Additional inputs 127 and metrics 130 may also include information regarding the impact such treatments have had on the user, such as the impact on the user's physiology (e.g., glucose levels, etc.).

[0122] In certain embodiments, the user's own historical data may provide a more accurate prediction of what the user's glucose levels and / or insulin resistance will be or will be during a particular subphase or phase of their menstrual cycle, and which one or more treatments will be effective during such a subphase or phase. Those skilled in the art will recognize various methods and operations that may be utilized to make such predictions based on datasets associated with the user themselves.

[0123] For example, in certain embodiments, one or more data models, machine learning models, regression models, functions, and algorithms can be used to predict one or more treatments, or combinations thereof, to counteract a particular amount of change in insulin resistance during a particular subphase or phase of the menstrual cycle. Some examples of different algorithms that can be used are described in connection with FIG. 4. In certain embodiments, these data models, machine learning models, regression models, functions, or algorithms can be used to find correlations between different variables (e.g., features). As noted above, the variables can include glucose levels and / or changes therein, insulin resistance and / or changes therein, menstrual subphase or phase, and exercise- and food-related variables.

[0124] In certain embodiments, based on these correlations, DAM 113 may be able to identify consistent patterns, based on which DAM 113 may be configured to determine an effective treatment for the user. These patterns, in certain embodiments, indicate the impact that different types / amounts of medications (e.g., insulin) and types / amounts of user behaviors (e.g., exercise, foods) during different phases of the menstrual cycle have on the user's glucose levels.

[0125] For example, the dataset may indicate that, on average, over the past 12 months, administering 40% more basal insulin counteracted a 30% increase in the user's insulin resistance during a particular subphase or phase of the menstrual cycle. In another example, the dataset may indicate that an additional hour of exercise each day was not sufficient to counteract a 10% increase in insulin resistance during a particular subphase or phase of the menstrual cycle. Similar examples are within the scope of this disclosure. Then, based on the user's own historical data and patterns found therein, the DAM 113 can determine which one or more treatments are effective or ineffective.

[0126] In step 306, the operations 300 continue by providing one or more treatments to the user. As described above, the one or more treatments may be determined based on historical data associated with the user, historical data associated with one or more users in the user database 110, and / or scientific data points.

[0127] In certain embodiments, if one or more therapies include administering a specific dose of insulin, once the specific dose of insulin is determined by the DAM 113, the medication management feature of the application 106 may send a therapy recommendation (e.g., a notification) to the user along with the delivery dose and / or delivery time so that the user can manually administer the insulin. Alternatively, the medication management feature may automatically communicate with the insulin administration device (e.g., upon receiving user approval) to deliver the determined dose at the delivery time. In certain embodiments, if the user consumes insulin only in oral form, the therapy may indicate the effective dosage of such oral insulin. Providing an accurate dosage of automatically or manually administered insulin is advantageous; otherwise, the user may either (1) overcompensate by administering excessive amounts of insulin to counteract changes in insulin sensitivity, or (2) administer too little insulin, resulting in spikes in glucose levels that may prompt the user to continue injecting additional doses.

[0128] In certain embodiments, if one or more therapies include exercising more and / or differently during a particular sub-phase or phase, the exercise management feature provides the user with a therapy recommendation, including the type and / or intensity of exercise. For example, a dataset associated with the user's historical data may indicate that running for one hour during the user's luteal phase consistently helps the user maintain glucose levels within a target range. In such an example, the exercise management feature suggests an additional hour of running, or exercise of a similar type and / or intensity (swimming), to the user. For example, the exercise management feature may calculate that if the user chooses to swim instead of run, 45 minutes of swimming would be sufficient.

[0129] In certain embodiments, if one or more treatments involve dietary changes during a particular subphase or phase, the dietary management feature may provide therapy recommendations, including different methods and forms, that allow the user to adapt their diet accordingly. For example, a dataset associated with a user's historical data may indicate that consuming less than 15 grams of sugar or 50 grams of carbohydrates during the user's luteal phase consistently helps the user maintain glucose levels within a target range. In such an example, the dietary management feature may recommend such findings to the user as a treatment and recommend a diet that includes meals and dishes consistent with those that have been effective in the past.

[0130] In certain embodiments, a combination of two or more treatments may be recommended to a user. For example, a particular user may generally want to reduce their reliance on insulin for various reasons, in which case the application 106 may recommend a combination of exercise and diet to counteract insulin resistance. Such combinations, which may exclude the administration of insulin, may be determined based on the user's own historical data and / or historical data associated with one or more users in the user database 110. For example, a user may have always only administered additional insulin to counteract changes in insulin resistance during a particular phase of their menstrual cycle, e.g., the luteal phase. However, the user may instead decide to engage in additional exercise during the luteal phase and follow a more restrictive diet instead of administering additional insulin. In such cases, the user's own historical data may not provide strong support for how the user's glucose levels would respond to more exercise and / or a more restrictive diet during the luteal phase. In such instances, inferences may be drawn from the historical data of similar users to indicate that a particular additional amount of exercise and / or a particular dietary change would be effective.

[0131] 4 illustrates an example of how one or more treatments are determined for a user, according to certain embodiments. As shown, in the example of FIG. 4, data is collected and prepared in three steps: A, B, and C (including steps C1 and C2). In step A, application 106 receives certain initial input from or about the user, such as demographic information 118, disease progression information 120, medication information 122, input 127 (including menstrual cycle information), and / or metrics 130. As noted above, because not enough input 127 and metrics 130 are initially received and / or available to the user, in the example of FIG. 4, DAM 113 initially determines one or more treatments for the user in step C1 based on datasets 440 associated with one or more users in user database 110.

[0132] Data set 440 may correspond to records of historical data associated with all users or a tiered group of users in user database 110. These options are indicated by various types of dashed lines. For example, in certain embodiments, in step B, DAM 113 stratifies user database 110 based on one or more stratification factors, as described above, resulting in a tiered group of users denoted as User Group 2. In such embodiments, data set 440 corresponds to records of historical data associated with User Group 2. In certain other embodiments, in step B, DAM 113 may decide not to stratify user database 110, in which case data set 440 corresponds to records of historical data associated with all users in user database 110.

[0133] In step C1, in certain embodiments, dataset 440 is used as a training dataset that is fed to machine learning (ML) algorithm 470 to output hypothesis function 450 (i.e., h). As described above, dataset 440 is developed and recorded to include various DFs, such as one or more data features (DFs) corresponding to time and / or where the user is in their menstrual cycle (e.g., which subphase or phase), one or more DFs corresponding to blood glucose levels and / or changes therein, one or more DFs corresponding to insulin resistance and / or changes therein, one or more exercise-related DFs corresponding to the type and amount of exercise performed, one or more diet-related DFs corresponding to dietary restrictions and / or the type and amount of food consumed, one or more DFs corresponding to the type and / or amount of insulin administered, and / or additional DFs that can be used in the model, as will be understood by those skilled in the art. For example, additional DFs may be defined using any of the inputs and metrics (e.g., inputs 127 and metrics 130). Note that in machine learning and pattern recognition, a DF is a discrete, measurable characteristic or property of the phenomenon being observed. In particular embodiments, ML algorithm 470 is a supervised learning algorithm. Supervised learning is a machine learning task that learns a function that maps inputs to outputs, for example, based on example input-output pairs. In the example of FIG. 4, ML algorithm 470 may include a supervised learning algorithm to solve a multivariate or multivariate regression problem.

[0134] As described above, feeding dataset 440 to ML algorithm 470 results in hypothesis function 450, which takes one or more x's as input and maps them to y's. Hypothesis function 450 is developed based on correlations between different DFs in dataset 440. For example, hypothesis function 450 may correspond to the following function, where Y is the dependent variable and X1, X2, ..., Xp are various independent variables:

number

[0135] In certain embodiments, each of the independent variables corresponds to a different DF. For example, Y may correspond to glucose level (e.g., or a drop in glucose level, or a target glucose level or range), X1 may correspond to time and / or where the user is in their menstrual cycle (e.g., which subphase or phase), X2 may be related to dietary restrictions, X3 may correspond to the type and / or amount of exercise performed, X4 may correspond to the type and / or amount of insulin administered, X5 may be related to insulin resistance, etc. B0, B1, ..., Bp are coefficients that, in certain embodiments, represent the correlation between the corresponding X and Y. Note that selecting glucose level as Y or output is just one way to configure hypothesis function 450. Details of how hypothesis function 450 is output and continually adjusted by ML algorithm 470 based on dataset 440 (potentially using cost functions, gradient descent algorithms, etc.) will not be described herein for brevity but are known to those skilled in the art.

[0136] Using hypothesis function 450, in certain embodiments, DAM 113 can predict a user's glucose level given a particular subphase, phase, or time point in the user's menstrual cycle, amount / type of exercise, amount / type of food, and / or amount / type of insulin administered. Using hypothesis function 450, DAM 113 can also determine one or more treatments for the user. To illustrate this with an example, a user may be two days away from entering the first subphase of the luteal phase. The user may indicate that they do not wish to engage in additional exercise or follow additional restrictive dietary restrictions. In that example, DAM 113 can use the target glucose range or level from hypothesis function 450 as "Y" and, given a value "X1" representing the first subphase of the luteal phase and the same values ​​for X2 and X3 (e.g., values ​​representing the same exercise and food regimen), determine the amount of insulin "X4" that needs to be administered during that subphase. In another example, the amount of insulin administered may remain the same, while the DAM 113 determines how much additional exercise the user needs to engage in during the first sub-phase to reach that target glucose level. As can be appreciated by one skilled in the art, there are many ways in which the hypothesis function 450 can be configured and used. For example, individual treatments or combinations of treatments may be determined based on the hypothesis function 450. In another example, "Y" may represent a decrease in glucose levels. In such an example, the DAM 113 may use the hypothesis function 450 to predict that one or more treatments may result in a particular amount of decrease in glucose levels.

[0137] It should be noted that while the development of hypothesis function 450 is shown in step C1 of FIG. 4, hypothesis function 450 may be developed by DAM 113 based on dataset 440 even before a user uses application 106 (e.g., before step A). ​​In other words, DAM 113 may use datasets associated with different stratified groups to develop functionality that can be used when a new user begins using application 106 and needs treatment recommendations. For example, a different hypothesis function may be developed for user group 3 such that if a new user begins using application 106 and is classified as user group 3, DAM 113 can use that hypothesis function to predict one or more treatments that will be effective for the user at a particular subphase, phase, or point in the user's menstrual cycle.

[0138] Utilizing a supervised learning algorithm to develop a function such as hypothesis function 450 is just one example in which DAM 113 may predict a user's glucose level during a particular subphase or phase of the menstrual cycle and / or predict one or more effective treatments for that subphase or phase to help the user maintain or reach a particular glucose level or range. Alternatively, other machine learning algorithms, such as neural network algorithms, may be used.

[0139] Output 460 represents one or more treatments that may be recommended or administered to the user. The physiological impact that output 460 has on the user (e.g., shown as user 102) is then received and recorded by application 106 in the form of input / metrics 461. For example, output 460 may include administering a specific dose of basal insulin one day before the user enters the first subphase of the luteal phase. In such an example, once the user enters the first subphase, the user's glucose level may be higher than desired. In that example, the user's glucose level and other metrics are then received, recorded, and analyzed as input / metrics 461. Input / metrics 461 are recorded in user profile 116, and not only is that information fed back into dataset 440, but they are also used to develop a training dataset 472 specifically for the user. Thus, output 460 and input / metrics 461 are used to develop both dataset 440 and dataset 472.

[0140] As additional inputs and metrics are fed back into dataset 440, the updated dataset 440 is again fed back to ML algorithm 470, resulting in an ever-changing dynamic hypothesis function 450 that reflects updates to the data in dataset 440. Ever-changing dynamic hypothesis function 450 refers to, among other things, a dynamic set of coefficients (e.g., B0, B1, ..., Bp).

[0141] After a certain period of time, dataset 472 may be developed such that predictions can be made with high confidence based on dataset 472 about the user's glucose levels and / or insulin resistance, as well as how effective different treatments will be during particular subphases or phases of the user's menstrual cycle. At such point, in step C2, in certain embodiments, DAM 113 may utilize predictions provided based on dataset 472 to provide treatment to the user, or at least give more weight to such predictions compared to predictions provided based on dataset 440. Similar to dataset 440, dataset 472 may be used as a training dataset that can be fed to machine learning algorithm 475 to develop hypothesis function 480. As one skilled in the art will appreciate, a similar or different type of machine learning algorithm 475 can be used as dataset 440. For example, ML algorithm 475 may be a supervised learning regression algorithm. Thus, based on the user's own historical data (dataset 472), the resulting hypothesis function 480 is used, in certain embodiments, to predict the user's glucose level and / or insulin resistance rate, as well as one or more treatments that will be effective in helping the user maintain or achieve a particular glucose level during a particular subphase or phase of the user's menstrual cycle.

[0142] In certain embodiments, output by hypothesis function 480 in the form of treatment recommendations and / or treatment administration is provided to a user as output 460. The physiological impact of such output 460 being implemented or administered is then received and / or recorded in the form of input / metrics 461 to further develop dataset 472. As additional input / metrics 461 are fed back into dataset 472, the updated dataset 472 is again fed back to ML algorithm 475, resulting in an ever-changing, dynamic hypothesis function 480 that reflects dynamic updates to the data in dataset 472.

[0143] In certain embodiments, DAM 113 may determine one or more treatments for the user based on the outputs provided by both hypothesis functions 480 and 450. For example, in certain embodiments, DAM 113 may not have a high degree of confidence in the output provided by hypothesis function 480. Thus, in such instances, DAM 113 may supplement the output provided by hypothesis function 480 with the output provided by hypothesis function 450. For example, DAM 113 may use a function that provides a final output based on weights assigned to the output provided by hypothesis function 480 and the output provided by hypothesis function 450.

[0144] It should be noted that using a combination of historical data associated with stratified groups of users and historical data associated with the user is just one example of how to predict and provide effective treatments to the user. In certain other embodiments, the DAM 113 may initially only predict and provide treatments to the user based on scientific data points, and then, if sufficiently available, use the user's own historical data. In yet certain other embodiments, sufficient information may be available about the user from the beginning, so only the user's own data may be used. As an example, a user may use the application 106 and a third-party period tracking application separately for several years. In such an example, at some point, the user may provide the application 106 with access to the user's past menstrual cycle information for the past several years by allowing the application 106 to communicate with the third-party period tracking application that has its records. Thus, in that example, the DAM 113 matches the user's menstrual cycle information to the user's glucose and / or insulin resistance trends, creating a time-stamped data set that can be fed into a machine learning algorithm to create a hypothesis function for prediction. In yet certain other embodiments, the DAM 113 may rely solely on historical data associated with stratified groups of users to provide effective treatments to the user.

[0145] 5 is a block diagram illustrating a computing device 500 configured to predict a user's glucose level and / or insulin resistance, as well as one or more treatments that may be effective in helping the user maintain or achieve a particular glucose level during a particular subphase or phase of the user's menstrual cycle. In certain embodiments, the one or more treatments are then provided to the user by an application, which runs either on computing device 500 or another computing device in communication with computing device 500, according to certain embodiments disclosed herein. While shown as a single physical device, in embodiments, computing device 500 may be implemented using a virtual device and / or across several devices, such as in a cloud environment. As illustrated, computing device 500 includes a processor 505, memory 510, storage 515, a network interface 525, and one or more I / O interfaces 520. In the illustrated embodiment, processor 505 retrieves and executes programming instructions stored in memory 510 and also stores and retrieves application data resident in storage 515. Processor 505 generally represents a single CPU and / or GPU, multiple CPUs and / or GPUs, a single CPU and / or GPU with multiple processing cores, etc. Memory 510 is included to generally represent random access memory. Storage 515 may be any combination of disk drives, flash-based storage devices, etc., and may include fixed and / or removable storage such as fixed disk drives, removable memory cards, cache, optical storage, network-attached storage (NAS), or storage area networks (SAN).

[0146] In some embodiments, input and output (I / O) devices 535 (e.g., keyboard, monitor, etc.) may be connected via I / O interface 520. Additionally, computing device 500 may be communicatively coupled to one or more other devices and components, such as user database 110, via network interface 525. In particular embodiments, computing device 500 is communicatively coupled to other devices via a network, which may include the Internet, a local network, etc. The network may include wired connections, wireless connections, or a combination of wired and wireless connections. As shown, processor 505, memory 510, storage 515, network interface 525, and I / O interface 520 are communicatively coupled by one or more interconnects 530. In particular embodiments, computing device 500 represents a mobile device 107 associated with a user. In particular embodiments, as noted above, mobile device 107 may include a user's laptop, computer, smartphone, etc. In another embodiment, computing device 500 is a server running in a cloud environment.

[0147] In the illustrated embodiment, storage 515 includes user profiles 116. In certain embodiments, storage 515 also includes any data sets that may be used in one or more of the operations described in connection with Figures 3 and 4. In certain other embodiments, such data sets may instead or additionally be stored in user database 110. Memory 510 includes decision support engine 112, which itself includes DAM 113. Decision support engine 112 is executed by computing device 500 to perform one or more steps of operation 300 of Figure 3.

[0148] Each of these non-limiting examples may stand on its own or may be combined with one or more other examples in various permutations or combinations. The above detailed description includes references to the accompanying drawings, which form a part of the detailed description. The drawings show, by way of illustration, specific embodiments in which the invention may be practiced. These embodiments are also referred to herein as "examples." Such examples may include elements in addition to those shown or described. However, the inventors also contemplate examples in which only the elements shown or described are provided. Furthermore, the inventors also contemplate examples using any combination or permutation of the elements shown or described (or one or more aspects thereof) with respect to a particular example (or one or more aspects thereof), or with respect to any other example (or one or more aspects thereof) shown or described herein.

[0149] In the event of inconsistent usage between this document and any document incorporated by reference, the usage in this document takes precedence.

[0150] In this document, the terms "a" or "an" are used, as is common in patent documents, to include one or more than one, regardless of any other instance or usage of "at least one" or "one or more." In this document, the term "or" is used to refer to a non-exclusive "or," such that "A or B" includes "A but not B," "B but not A," and "A and B," unless otherwise specified. In this document, the terms "comprising" and "in which" are used as the plain-English equivalents of the terms "comprising" and "wherein," respectively. Also, in the following claims, the terms "comprising" and "comprising" are open-ended, i.e., systems, devices, articles, compositions, formulas, or processes that include elements in addition to those recited after such terms in the claims are still considered to be within the scope of the claims. Furthermore, in the following claims, terms such as "first," "second," and "third" are used merely as labels and are not intended to impose numerical requirements on their objects.

[0151] Geometric terms such as "parallel," "perpendicular," "circular," and "square" are not intended to require absolute mathematical precision unless the context dictates otherwise. Instead, such geometric terms take into account variations due to manufacturing or equivalent functions. For example, if an element is described as "circular" or "nearly circular," components that are not exactly circular (e.g., slightly rectangular or multi-sided polygonal) are still included in this description.

[0152] The example methods described herein may be at least partially machine- or computer-implemented. Some examples may include computer-readable or machine-readable media encoded with instructions operable to configure an electronic device to perform the methods described in the examples above. Implementations of such methods may include code, such as microcode, assembly language code, high-level language code, etc. Such code may include computer-readable instructions for performing various methods. The code may form part of a computer program product. Furthermore, in one example, the code may be tangibly stored on one or more volatile, non-transitory, or non-volatile tangible computer-readable media, such as during execution or at other times. Examples of these tangible computer-readable media include, but are not limited to, hard disks, removable magnetic disks, removable optical disks (e.g., compact disks and digital video disks), magnetic cassettes, memory cards or sticks, random access memory (RAM), read-only memory (ROM), etc.

[0153] The above description is illustrative and not limiting. For example, the above examples (or one or more aspects thereof) may be used in combination with each other. Other embodiments may be employed, for example, by one of ordinary skill in the art, upon reviewing the above description. The Abstract is provided in accordance with 37 CFR §1.72(b) to enable the reader to quickly ascertain the nature of the technical disclosure. It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. Also, in the above Detailed Description, various features may be grouped together to streamline the disclosure. This should not be construed as intending that an unclaimed disclosed feature is essential to the claim. Rather, inventive subject matter may lie in less than all features of a particular disclosed embodiment. Accordingly, the following claims are incorporated into the Detailed Description as examples or embodiments, with each claim standing on its own as a separate embodiment, and such embodiments can be combined with each other in various combinations or permutations. The scope of the invention should be determined with reference to the appended claims, along with the full range of equivalents to which such claims are entitled. [Explanation of symbols]

[0154] 100 DSTA 102 users 104 Glucose Monitoring System 106 Applications 107 Mobile Devices 109 Touchscreen Display 110 User Database 112 Decision Support Engine 113 Data Analysis Module 116 User Profile 118 Demographic Information 112 Drug Information 120 Disease progression information 122 Drug Information 126 Application Data 127 inputs 130 metrics 138 Sensor Electronics Module 140 Glucose Sensor 440 datasets 450 Hypothesis Function 460 output 461 Inputs / Metrics 470 ML Algorithms 475 ML Algorithms 472 datasets 480 Hypothesis Function 500 computing devices 505 processor 510 memory 515 Storage 520 I / O interface 530 Interconnection (Bus) 525 network interface 535 I / O devices

Claims

1. 1. A system comprising:

1. A glucose monitoring system comprising: a glucose sensor configured to measure blood glucose of a user; a sensor electronics module configured to transmit sensor data corresponding to blood glucose measurements provided by the glucose sensor to a processor; and a memory circuit, the processor: receiving information regarding the user's menstrual cycle; and determining a treatment for the user to achieve a target blood glucose during the sub-phase or phase of the user's menstrual cycle based on at least one of historical data associated with the user and historical data associated with stratified groups of users; providing the user with educational features that educate the user about causes and effects of potential behaviors based on at least one of historical data associated with the user and historical data associated with stratified groups of users; It is structured as follows: the historical data associated with the user includes blood glucose measurements of the user provided by the glucose monitoring system; the historical data associated with the user, a pattern of at least one of the blood glucose measurements and insulin resistance of the user during the sub-phase or phase of the menstrual cycle of the user; and a pattern of physiological impact of the treatment on the blood glucose measurements of the user during the sub-phase or phase of the menstrual cycle of the user, the pattern being indicative of effectiveness of the treatment with respect to achieving the target blood glucose; the historical data associated with the users of the hierarchical group, patterns of at least one of blood glucose measurements and insulin resistance of the stratified groups of users during the subphases or phases of the menstrual cycle; and The system is structured to indicate at least one pattern of physiological impact of the treatment on the blood glucose measurements of the stratified group of users during the sub-phases or phases of the menstrual cycle, the pattern indicating the effectiveness of the treatment in achieving the target blood glucose.

2. The system of claim 1 , wherein the processor is configured to provide the therapy.

3. The system of claim 2 , wherein the therapy comprises a dose of insulin.

4. 4. The system of claim 3, wherein the dose of insulin is greater than an average dose of insulin administered to the user during a non-luteal phase subphase or phase of the user's menstrual cycle.

5. The system of claim 3 , wherein the processor is configured to send a signal to a medication delivery device to administer the dose of insulin to the user.

6. The system of claim 3 , wherein the processor is configured to provide a therapy recommendation to the user or another user, the therapy recommendation indicating a dosage of the insulin.

7. 4. The system of claim 3, wherein the processor is configured to provide a therapy recommendation to the user or another user, the therapy recommendation indicating at least one of an amount, type, duration, and intensity of exercise.

8. The system of claim 3 , wherein the processor is configured to provide a regimen recommendation to the user or another user, the regimen recommendation indicating at least one of an amount and type of food.

9. 1. A method for personalizing diabetes treatment based on information related to a user's menstrual cycle, comprising: measuring a blood glucose measurement of the user using a glucose monitoring system; receiving, at a processor in data communication with the glucose monitoring system, information related to the menstrual cycle of the user; determining, in the processor, a treatment for the user to achieve a target blood glucose during the sub-phase or phase of the user's menstrual cycle based on at least one of historical data associated with the user and historical data associated with stratified groups of users; providing, in the processor, educational features to the user that educate the user about causes and effects of potential behaviors based on at least one of historical data associated with the user and historical data associated with a tiered group of users; Including, the historical data associated with the user includes blood glucose measurements of the user provided by the glucose monitoring system; the historical data associated with the user, a pattern of at least one of the blood glucose measurements and insulin resistance of the user during the sub-phase or phase of the menstrual cycle of the user; and a pattern of physiological impact of the treatment on the blood glucose measurements of the user during the sub-phase or phase of the menstrual cycle of the user, the pattern being indicative of effectiveness of the treatment with respect to achieving the target blood glucose; the historical data associated with the users of the hierarchical group, patterns of at least one of blood glucose measurements and insulin resistance of the stratified groups of users during the subphases or phases of the menstrual cycle; and The method is structured to indicate at least one of a pattern of physiological impact of the treatment on the blood glucose measurements of the stratified group of users during the sub-phases or phases of the menstrual cycle, the pattern being indicative of the effectiveness of the treatment in achieving the target blood glucose.

10. 10. The method of claim 9, further comprising providing said treatment.

11. 11. The method of claim 10, wherein the treatment comprises a dose of insulin.

12. 12. The method of claim 11, wherein the dose of insulin is greater than an average dose of insulin administered to the user during a non-luteal phase subphase or phase of the user's menstrual cycle.

13. 12. The method of claim 11, wherein providing the therapy further comprises sending a signal to a medication delivery device to administer the dose of insulin to the user.

14. 12. The method of claim 11, wherein providing the therapy further comprises providing a therapy recommendation to the user or another user, the therapy recommendation indicating a dosage of the insulin.

15. 12. The method of claim 11, wherein providing the treatment further comprises providing a therapy recommendation to the user or another user, the therapy recommendation indicating at least one of an amount, type, duration, and intensity of exercise.

16. 12. The method of claim 11, wherein providing the treatment further comprises providing a therapy recommendation to the user or another user, the therapy recommendation indicating at least one of an amount and type of food.

17. 1. A non-transitory computer-readable medium having stored thereon instructions that, when executed by a system, cause the system to perform a method, the method comprising: measuring a blood glucose measurement of the user using a glucose monitoring system; receiving, at a processor in data communication with the glucose monitoring system, information related to the user's menstrual cycle; determining, in the processor, a treatment for the user to achieve a target blood glucose during the sub-phase or phase of the user's menstrual cycle based on at least one of historical data associated with the user and historical data associated with stratified groups of users; providing, in the processor, educational features to the user that educate the user about causes and effects of potential behaviors based on at least one of historical data associated with the user and historical data associated with a tiered group of users; Including, the historical data associated with the user includes the blood glucose measurements of the user provided by the glucose monitoring system; the historical data associated with the user, a pattern of at least one of the blood glucose measurements and insulin resistance of the user during the sub-phase or phase of the menstrual cycle of the user; and a pattern of physiological impact of the treatment on the blood glucose measurements of the user during the sub-phase or phase of the menstrual cycle of the user, the pattern being indicative of effectiveness of the treatment with respect to achieving the target blood glucose; the historical data associated with the users of the hierarchical group, patterns of at least one of blood glucose measurements and insulin resistance of the stratified groups of users during the subphases or phases of the menstrual cycle; and A non-transitory computer-readable medium structured to indicate at least one pattern of physiological impact of the treatment on the blood glucose measurements of the stratified group of users during the sub-phases or phases of the menstrual cycle, the pattern being indicative of the effectiveness of the treatment in achieving the target blood glucose.

18. 20. The non-transitory computer-readable medium of claim 17, wherein the method further comprises providing the treatment.

19. 20. The non-transitory computer-readable medium of claim 18, wherein the treatment comprises a dosage of insulin.

20. 20. The non-transitory computer-readable medium of claim 19, wherein the dose of insulin is greater than an average dose of insulin administered to the user during a non-luteal phase subphase or phase of the user's menstrual cycle.

Images