Bolus administration

Abstract

Various embodiments are directed to systems and methods for generating a bolus dose for a recipient. A bolus application can display a first bolus configuration parameter question on a user interface and receive a first answer to the first bolus configuration parameter question via the user interface. The first answer can describe the recipient's previous bolus determination technique. The bolus application can use the first answer to select a second bolus configuration parameter question and provide the second bolus configuration parameter question on the user interface. The bolus application can use the first answer and a second answer to the second bolus configuration parameter question to determine a set of at least one bolus configuration parameter.

Description

[Technical Field]

[0001] Incorporation by reference to any priority application This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 958,636, entitled "MANAGING BOLUS DOSES," filed January 8, 2020, the entire contents of which are incorporated herein by reference and hereby expressly made a part hereof.

[0002] The present disclosure relates generally to medical devices such as analyte sensors, and more particularly, by way of example and not limitation, to systems, devices, and methods that utilize analyte sensors to manage insulin bolus doses in diabetic patients. [Background technology]

[0003] Diabetes is a metabolic condition associated with the body's production or use of insulin, a hormone that allows 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 within a range that provides enough energy to support bodily functions and avoids problems that can occur if 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 is unable to effectively use the insulin that is present, glucose levels can rise above the normal range. Higher-than-normal 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 overly acidic due to the presence of glucose and ketones in the blood, which are produced when the body cannot use glucose. Lower-than-normal glucose levels are called "hypoglycemia." Severe hypoglycemia can cause acute attacks, which can result in seizures or death.

[0006] Diabetic conditions are sometimes referred to as "type 1" or "type 2." Type 1 diabetics can usually use insulin when it's available, but because of problems with the insulin-producing beta cells in the pancreas, their bodies don't produce enough insulin. Type 2 diabetics may produce some insulin, but their sensitivity to insulin is reduced, making them "insulin resistant." As a result, even though insulin is present, the patient's body doesn't use it effectively to effectively regulate glucose levels. Diabetics can receive insulin to manage their glucose levels. Insulin can be administered, for example, by manual injection with a needle. Wearable insulin pumps can also be used. Summary of the Invention [Means for solving the problem]

[0007] This disclosure describes, among other things, systems, devices, and methods for managing bolus doses, for example, for users of analyte sensors and related technology.

[0008] Example 1 is a system for generating a bolus dose for a recipient, the method comprising at least one processor programmed to perform operations including: displaying a first bolus configuration parameter question on a user interface; receiving a first answer to the first bolus configuration parameter question via the user interface, the first answer describing the recipient's previous bolus determination technique; selecting a second bolus configuration parameter question using the first answer; providing the second bolus configuration parameter question to the user interface; determining a set of at least one bolus configuration parameter using the first answer and the second answer to the second bolus configuration parameter question; receiving a recipient glucose concentration from a continuous glucose sensor; determining a bolus dose for the recipient using the recipient glucose concentration and the set of at least one bolus configuration parameter; and displaying bolus dose instructions on the user interface.

[0009] In Example 2, the subject matter of Example 1 optionally includes an operation further including using the first answer to select a second set of questions, wherein the second bolus configuration parameter question is part of the second set of questions.

[0010] In Example 3, the subject matter of any one or more of Examples 1-2 optionally includes operations further including receiving, via the user interface, a second answer to a second bolus configuration parameter question; determining, after receiving the second answer, that the system is capable of calculating fewer than all of the set of bolus configuration parameters; and providing, to the user interface, a third bolus configuration parameter question, wherein determining the set of at least one bolus configuration parameter is also based at least in part on the third answer to the third bolus configuration parameter question.

[0011] In Example 4, the subject matter of any one or more of Examples 1-3 optionally includes a first answer indicating that the recipient's previous bolus determination technique takes into account glucose concentration and meal size indications, and a second answer to the second bolus configuration parameter question indicating that the recipient's previous bolus determination technique uses a formula.

[0012] In Example 5, the subject matter of any one or more of Examples 1-4 optionally includes: a first response indicating that the recipient's previous bolus determination technique takes into account a bolus-associated meal; and a second response to the second bolus configuration parameter question requesting the recipient provide a bolus insulin dose indication from the previous bolus determination technique and a meal indication associated with the bolus insulin dose from the previous bolus determination technique.

[0013] In Example 6, the subject matter of any one or more of Examples 1-5 optionally includes: a first response indicating that the recipient's previous bolus determination technique takes into account the recipient's glucose concentration; and a second response to the second bolus configuration parameter question requesting that the recipient provide an indication of a bolus insulin dose and an indication of a deviation between the recipient's glucose concentration and the recipient's target glucose concentration.

[0014] In Example 7, the subject matter of any one or more of Examples 1-6 optionally includes: the first response indicating that the recipient's previous bolus determination technique uses a fixed bolus dose; and the system operations further include executing a model based at least in part on the first response and the second response to generate a first bolus configuration parameter of the set of at least one bolus configuration parameter.

[0015] In Example 8, the subject matter of any one or more of Examples 1-7 optionally includes an operation further including transmitting, to the insulin delivery system, data describing the bolus dose, the data for use in delivering the bolus dose to the recipient by the insulin delivery system.

[0016] Example 9 is a method of generating a bolus insulin dose for a recipient using a bolus application, the method including: displaying, by the bolus application, a first bolus configuration parameter question on a bolus application user interface; receiving, by the bolus application via the bolus application user interface, a first answer to the first bolus configuration parameter question, the first answer describing a previous bolus determination technique of the recipient; selecting, by the bolus application, a second bolus configuration parameter question using the first answer; and receiving, by the bolus application, a second bolus configuration parameter question describing a previous bolus determination technique of the recipient. providing a second bolus configuration parameter question to a bolus application user interface; determining, by the bolus application, a set of at least one bolus configuration parameter using the first answer and a second answer to the second bolus configuration parameter question; receiving, by the bolus application, a recipient glucose concentration from the continuous glucose sensor; determining, by the bolus application, a bolus dose for the recipient using the recipient glucose concentration and the set of at least one bolus configuration parameter; and displaying, on the bolus application user interface, an indication of the bolus dose.

[0017] In Example 10, the subject matter of Example 9 optionally includes using the first answer to select a second set of questions, and the second bolus configuration parameter question is part of the second set of questions.

[0018] In Example 11, the subject matter of any one or more of Examples 9-10 optionally includes receiving, by the bolus application via the bolus application user interface, a second answer to a second bolus configuration parameter question; determining, by the bolus application after receiving the second answer, that the bolus application is capable of calculating less than all of the set of bolus configuration parameters; and providing, by the bolus application, a third bolus configuration parameter question in the bolus application user interface, wherein determining the set of at least one bolus configuration parameter is also based at least in part on the third answer to the third bolus configuration parameter question.

[0019] In Example 12, the subject matter of any one or more of Examples 9-11 optionally includes a first answer indicating that the recipient's previous bolus determination technique takes into account glucose concentration and meal size indication, and a second answer to a second bolus configuration parameter question indicating that the recipient's previous bolus determination technique uses a formula.

[0020] In Example 13, the subject matter of any one or more of Examples 9-12 optionally includes: a first response indicating that the recipient's previous bolus determination technique takes into account a bolus-associated meal; and a second response to the second bolus configuration parameter question requesting the recipient provide a bolus insulin dose indication from the previous bolus determination technique and a meal indication associated with the bolus insulin dose from the previous bolus determination technique.

[0021] In Example 14, the subject matter of any one or more of Examples 9-13 optionally includes: a first response indicating that the recipient's previous bolus determination technique takes into account the recipient's glucose concentration; and a second response to the second bolus configuration parameter question requesting that the recipient provide an indication of a bolus insulin dose and an indication of a deviation between the recipient's glucose concentration and the recipient's target glucose concentration.

[0022] In Example 15, the subject matter of any one or more of Examples 9-14 optionally includes the first response indicating that the recipient's previous bolus determination technique uses a fixed bolus dose, and the method further includes executing a model based at least in part on the first response and the second response to generate a first bolus configuration parameter of the set of at least one bolus configuration parameter.

[0023] In Example 16, the subject matter of any one or more of Examples 9-15 optionally includes transmitting, by the bolus application, data describing the bolus dose to an insulin delivery system, the data for use by the insulin delivery system in delivering the bolus dose to a recipient.

[0024] Example 17 is a machine-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations including displaying a first bolus configuration parameter question on a user interface; receiving a first answer to the first bolus configuration parameter question via the user interface, the first answer describing a recipient's previous bolus determination technique; selecting a second bolus configuration parameter question using the first answer; providing the second bolus configuration parameter question to the user interface; determining a set of at least one bolus configuration parameter using the first answer and the second answer to the second bolus configuration parameter question; receiving a recipient glucose concentration from a continuous glucose sensor; determining a bolus dose for the recipient using the recipient glucose concentration and the set of at least one bolus configuration parameter; and displaying a bolus dose indication on the user interface.

[0025] Example 18 is a system for managing a recipient's therapy using a continuous glucose sensor, the system including at least one processor programmed to perform operations including accessing bolus dose instructions to be provided to the recipient, receiving glucose concentration data from the continuous glucose sensor describing the recipient's glucose concentration, using the glucose concentration data to generate effect data describing the effect of the bolus dose, and displaying the effect data to the recipient at a user interface.

[0026] In Example 19, the subject matter of Example 18 optionally includes operations further including receiving a bolus dose indication from an insulin delivery system.

[0027] In Example 20, the subject matter of any one or more of Examples 18-19 optionally includes, wherein the glucose concentration data includes a plurality of glucose concentrations of the recipient over a first period of time, and the operation further includes determining the bolus dose indication using the plurality of glucose concentrations of the recipient over the first period of time.

[0028] In Example 21, the subject matter of any one or more of Examples 18-20 optionally includes: the glucose concentration data indicating the recipient's current glucose concentration; and the operations further include determining a glucose correction for the bolus dose based at least in part on the current glucose concentration and the recipient's target glucose concentration; determining a correction component for the bolus dose based at least in part on the glucose correction and the bolus dose; and determining a meal component for the bolus dose based at least in part on the correction component; and generating the effect data includes determining a carbohydrate coverage of the meal component.

[0029] In Example 22, the subject matter of any one or more of Examples 18-21 optionally includes operations further including: accessing meal data describing a meal associated with the bolus dose; determining a meal component of the bolus dose based at least in part on the meal data; and determining a correction component of the bolus dose based at least in part on the meal component, wherein generating the effect data includes determining a glucose correction based at least in part on the correction component.

[0030] In Example 23, the subject matter of Example 22 optionally includes, wherein accessing the meal data includes determining a meal associated with the bolus dose and accessing a carbohydrate count associated with the meal.

[0031] In Example 24, the subject matter of any one or more of Examples 22-23 optionally includes where determining the meal associated with the bolus dose includes receiving, from the insulin delivery system, an image of at least a portion of the meal associated with the bolus dose.

[0032] In Example 25, the subject matter of any one or more of Examples 18 to 24 optionally includes, wherein the effect data includes carbohydrate coverage associated with the bolus dose, and wherein displaying the effect data in the user interface includes displaying an indication of the carbohydrate coverage.

[0033] In Example 26, the subject matter of any one or more of Examples 18-25 optionally includes wherein the effect data includes a glucose correction, and wherein displaying the effect data in the user interface includes generating an estimated future glucose concentration trace based at least in part on the glucose correction, and displaying the estimated future glucose trace.

[0034] In Example 27, the subject matter of any one or more of Examples 18-26 optionally includes operations further including: accessing model data describing a physiological model associated with the recipient; accessing previous meal data describing meals previously ingested by the recipient; and accessing previous bolus dose data describing previous bolus doses administered to the recipient; and determining carbohydrate coverage using the previous meal data, the previous bolus dose data, and the model data, wherein the effect data is based at least in part on the carbohydrate coverage.

[0035] Example 28 is a method of using a continuous glucose sensor to manage a recipient's therapy, the method including: accessing bolus dose instructions provided to the recipient by a bolus application running on a computing device; receiving, by the bolus application, glucose concentration data from the continuous glucose sensor describing the recipient's glucose concentration; generating, by the bolus application, effect data using the glucose concentration data describing the effect of the bolus dose; and displaying, by the bolus application, the effect data to the recipient in a user interface.

[0036] In Example 29, the subject matter of Example 28 optionally includes receiving a bolus dose indication from an insulin delivery system.

[0037] In Example 30, the subject matter of any one or more of Examples 28-29 optionally includes, wherein the glucose concentration data includes a plurality of glucose concentrations of the recipient over a first period of time, and further includes determining a bolus dose indication using the plurality of glucose concentrations of the recipient over the first period of time.

[0038] In Example 31, the subject matter of any one or more of Examples 28-30 optionally includes, wherein the glucose concentration data indicates the recipient's current glucose concentration, and the method further includes determining a glucose correction for the bolus dose based at least in part on the current glucose concentration and the recipient's target glucose concentration, determining a correction component for the bolus dose based at least in part on the glucose correction and the bolus dose, and determining a meal component for the bolus dose based at least in part on the correction component, and wherein generating the effect data includes determining a carbohydrate coverage of the meal component.

[0039] In Example 32, the subject matter of any one or more of Examples 28-31 optionally includes accessing meal data describing a meal associated with the bolus dose, determining a meal component of the bolus dose based at least in part on the meal data, and determining a correction component of the bolus dose based at least in part on the meal component, and generating the effect data includes determining a glucose correction based at least in part on the correction component.

[0040] In Example 33, the subject matter of Example 32 optionally includes, wherein accessing the meal data includes determining a meal associated with the bolus dose and accessing a carbohydrate count associated with the meal.

[0041] In Example 34, the subject matter of any one or more of Examples 32-33 optionally includes where determining the meal associated with the bolus dose includes receiving an image of at least a portion of the meal associated with the bolus dose from the insulin delivery system.

[0042] In Example 35, the subject matter of any one or more of Examples 28 to 34 optionally includes, wherein the effect data includes carbohydrate coverage associated with the bolus dose, and displaying the effect data in the user interface includes displaying an indication of the carbohydrate coverage.

[0043] In Example 36, the subject matter of any one or more of Examples 28-35 optionally includes where the effect data includes a glucose correction, and where displaying the effect data in the user interface includes generating an estimated future glucose concentration trace based at least in part on the glucose correction, and displaying the estimated future glucose trace.

[0044] In Example 37, the subject matter of any one or more of Examples 28-36 optionally includes: accessing, by the bolus application, model data describing a physiological model associated with the recipient; accessing, by the bolus application, previous meal data describing meals previously ingested by the recipient; accessing, by the bolus application, previous bolus dose data describing previous bolus doses administered to the recipient; and determining, by the bolus application, carbohydrate coverage using the previous meal data, the previous bolus dose data, and the model data, wherein the effect data is based at least in part on the carbohydrate coverage.

[0045] Example 38 is a machine-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations including accessing instructions for a bolus dose to be provided to a recipient; receiving glucose concentration data from a continuous glucose sensor that describes the recipient's glucose concentration; using the glucose concentration data to generate effect data that describes the effect of the bolus dose; and displaying the effect data to the recipient at a user interface.

[0046] Example 39 is a system for generating a bolus dose for a recipient, the system including at least one processor programmed to perform operations including receiving current case parameter data describing a current bolus case, the current case parameter data including at least a current time and current glucose concentration data describing the recipient's current glucose concentration received from a continuous glucose sensor system; comparing the current case parameter data to a plurality of reference cases to select a closest reference case, the closest reference case being associated with the reference case parameter data and the reference case treatment data, the reference case parameter data including at least the reference case time and the reference case glucose concentration; determining a therapy modification factor using difference data describing a difference between the current case parameter data and the closest reference case parameter data; applying the therapy modification factor to the parameter data of the reference case treatment to generate current case therapy data; and determining a current case bolus dose using the current case therapy data.

[0047] In Example 40, the subject matter of Example 39 optionally includes, wherein applying the treatment modification factor includes applying a multiplier to a bolus configuration parameter associated with the closest reference case.

[0048] In Example 41, the subject matter of any one or more of Examples 39-40 optionally includes operations further including receiving second current case parameter data describing a second current bolus case; comparing the second current case parameter data to a plurality of reference cases to select a second closest reference case; and determining that a difference between the second current bolus case and the second closest reference case is greater than a threshold value.

[0049] In Example 42, the subject matter of Example 41 optionally includes an operation further including determining a bolus dose for the second current case using an alternative bolus method in response to a difference between the second current bolus case and the second closest reference case being greater than a threshold value.

[0050] In Example 43, the subject matter of any one or more of Examples 41-42 optionally includes an operation further including receiving outcome data describing the outcome of a second current bolus case, and generating a new reference case using the second current case parameter data and outcome data.

[0051] In Example 44, the subject matter of any one or more of Examples 41-43 optionally includes operations further including monitoring outcome data describing the results of a second current bolus case, determining that an intervening event occurred before monitoring was completed, and generating supplemental outcome data using the second closest reference case.

[0052] In Example 45, the subject matter of any one or more of Examples 39-44 optionally includes operations further including monitoring outcome data describing the results of the bolus case and modifying at least one of the reference case treatment data or treatment modification parameters based at least in part on the outcome data.

[0053] Example 46 is a system for generating a bolus dose for a recipient, the system comprising at least one processor programmed to perform operations including receiving current case parameter data describing a current bolus case, the current case parameter data including at least a current time and current glucose concentration data describing the recipient's current glucose concentration received from a continuous glucose sensor system; comparing the current case parameter data to a plurality of stored cases to select a closest stored case, the closest stored case being associated with the stored case parameter data and stored case treatment data, the stored case parameter data including at least a stored case time and a stored case glucose concentration; determining a current case bolus dose using the stored case treatment parameter data to generate current case treatment data; monitoring outcome data describing an outcome of the current bolus case; determining that an intervening event occurred before monitoring was completed; generating supplemental outcome data using the closest stored case; and generating a new stored case using the current case parameter data, the closest stored case treatment data, and the supplemental outcome data.

[0054] Example 47 is a bolus calculator method including: receiving current case parameter data describing a current bolus case, the current case parameter data including at least a current time and current glucose concentration data describing a recipient's current glucose concentration received from a continuous glucose sensor system; comparing the current case parameter data to a plurality of reference cases to select a closest reference case, the closest reference case being associated with reference case parameter data and reference case treatment data, the reference case parameter data including at least a reference case time and a reference case glucose concentration; determining a therapy modification factor using difference data describing a difference between the current case parameter data and the closest reference case parameter data; applying the therapy modification factor to the parameter data of the reference case treatment to generate current case therapy data; and determining a current case bolus dose using the current case therapy data.

[0055] In Example 48, the subject matter of Example 47 optionally includes, wherein applying the treatment modification factor includes applying a multiplier to a bolus configuration parameter associated with the closest reference case.

[0056] In Example 49, the subject matter of any one or more of Examples 47-48 optionally includes receiving second current case parameter data describing a second current bolus case, comparing the second current case parameter data to a plurality of reference cases to select a second closest reference case, and determining that a difference between the second current bolus case and the second closest reference case is greater than a threshold value.

[0057] In Example 50, the subject matter of Example 49 optionally includes determining a bolus dose for the second current case using an alternative bolus method in response to a difference between the second current bolus case and a second closest reference case that is greater than a threshold value.

[0058] In Example 51, the subject matter of any one or more of Examples 49-50 optionally includes receiving outcome data describing the outcome of a second current bolus case, and generating a new reference case using the second current case parameter data and outcome data.

[0059] In Example 52, the subject matter of any one or more of Examples 49-51 optionally includes monitoring outcome data describing the results of a second current bolus case, determining that an intervening event occurred before monitoring was completed, and generating supplemental outcome data using the second closest reference case.

[0060] In Example 53, the subject matter of any one or more of Examples 47-52 optionally includes monitoring outcome data describing the results of the bolus case and modifying at least one of the reference case treatment data or treatment modification parameters based at least in part on the outcome data.

[0061] Example 54 is a method for generating a bolus dose for a recipient, the method including: receiving current case parameter data describing a current bolus case, the current case parameter data including at least a current time and current glucose concentration data describing the recipient's current glucose concentration received from a continuous glucose sensor system; comparing the current case parameter data to a plurality of stored cases to select a closest stored case, the closest stored case being associated with stored case parameter data and stored case treatment data, the stored case parameter data including at least a stored case time and a stored case glucose concentration; determining a current case bolus dose using the stored case treatment parameter data to generate current case treatment data; monitoring outcome data describing an outcome of the current bolus case; determining that an intervening event occurred before monitoring was completed; generating supplemental outcome data using the closest stored case; and generating a new stored case using the current case parameter data, the closest stored case treatment data, and the supplemental outcome data.

[0062] Example 55 is a machine-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations including receiving current case parameter data describing a current bolus case, the current case parameter data including at least a current time and current glucose concentration data describing a recipient's current glucose concentration received from a continuous glucose sensor system; comparing the current case parameter data to a plurality of reference cases to select a closest reference case, the closest reference case being associated with reference case parameter data and reference case treatment data, the reference case parameter data including at least a reference case time and a reference case glucose concentration; determining a therapy modification factor using difference data describing a difference between the current case parameter data and the closest reference case parameter data; applying the therapy modification factor to the parameter data of the reference case treatment to generate current case therapy data; and determining a current case bolus dose using the current case therapy data.

[0063] Example 56 is a system for determining and providing a diabetes treatment, the system comprising at least one processor programmed to perform operations including accessing training data, training a classification model, receiving test bolus data describing a test bolus dose for a recipient, receiving glucose concentration data describing the recipient's glucose concentration from a continuous glucose sensor, applying the classification model to determine that the test bolus dose belongs to a first bolus category, where applying the classification model uses the test bolus data and the glucose concentration data, selecting a recipient action based at least in part on the test bolus data and the first bolus category, and providing a recipient action prompt on a user interface of a bolus application, where the bolus application prompt encourages the recipient to take the recipient action.

[0064] In Example 57, the subject matter of Example 56 optionally includes operations further including comparing the test bolus data with first bolus category data describing multiple bolus doses within a first bolus category, determining a difference between the test bolus data and the first bolus category data, and selecting a recipient action based on the difference between the test bolus data and the first bolus category data.

[0065] In Example 58, the subject matter of Example 57 optionally includes, wherein the recipient behavior includes a modification to the recipient's basal dose.

[0066] In Example 59, the subject matter of any one or more of Examples 57-58 optionally includes, wherein the recipient action includes a modification to the recipient's bolus configuration parameters.

[0067] In Example 60, the subject matter of any one or more of Examples 56 to 59 optionally includes an operation further including determining changes to insulin pump parameters based at least in part on the test bolus data and the first bolus category, and transmitting insulin pump change data indicating the changes to the insulin pump parameters.

[0068] In Example 61, the subject matter of any one or more of Examples 56 to 60 optionally includes operations further including: using the glucose concentration data to generate a glucose concentration trace for the recipient; generating a user interface screen showing the glucose concentration trace; and displaying a test bolus indicator at a location on the user interface screen corresponding to the time of the test bolus, the test bolus indicator also indicating the first bolus category.

[0069] In Example 62, the subject matter of any one or more of Examples 56-61 optionally includes an operation further including using the glucose concentration data and the first bolus category to determine that the recipient exceeds a threshold risk of hypoglycemia, and the recipient action is to treat the hypoglycemia.

[0070] In Example 63, the subject matter of any one or more of Examples 56-62 optionally includes, wherein the classification model includes a logistic regression model.

[0071] Example 64 is a method for determining and providing diabetes care using a computing device, the method including: accessing, by a bolus application, training data executed on the computing device; training a classification model; receiving, by the bolus application, test bolus data describing a test bolus dose for a recipient; receiving, by the bolus application, glucose concentration data describing the recipient's glucose concentration from a continuous glucose sensor; applying, by the bolus application, a classification model to determine that the test bolus dose belongs to a first bolus category, wherein applying the classification model uses the test bolus data and the glucose concentration data; selecting, by the bolus application, a recipient action based at least in part on the test bolus data and the first bolus category; and providing, by the bolus application, a recipient action prompt on a user interface of the bolus application, wherein the bolus application prompts the recipient to take the recipient action.

[0072] In Example 65, the subject matter of Example 64 optionally includes comparing the test bolus data with first bolus category data describing multiple bolus doses within a first bolus category, determining a difference between the test bolus data and the first bolus category data, and selecting a recipient action based on the difference between the test bolus data and the first bolus category data.

[0073] In Example 66, the subject matter of Example 65 optionally includes, wherein the recipient behavior includes a modification to the recipient's basal dose.

[0074] In Example 67, the subject matter of any one or more of Examples 65-66 optionally includes, wherein the recipient action includes a modification to the recipient's bolus configuration parameters.

[0075] In Example 68, the subject matter of any one or more of Examples 64 to 67 optionally includes determining, by the bolus application, changes to insulin pump parameters based at least in part on the test bolus data and the first bolus category, and transmitting, by the bolus application, insulin pump change data indicating the changes to the insulin pump changes.

[0076] In Example 69, the subject matter of any one or more of Examples 64 to 68 optionally includes using the glucose concentration data to generate a glucose concentration trace for the recipient, generating a user interface screen showing the glucose concentration trace, and displaying a test bolus indicator at a location on the user interface screen corresponding to the time of the test bolus, the test bolus indicator also indicating a first bolus category.

[0077] In Example 70, the subject matter of any one or more of Examples 64-69 optionally includes using the glucose concentration data and the first bolus category to determine that the recipient exceeds a threshold risk of hypoglycemia, and the recipient action is to treat the hypoglycemia.

[0078] In Example 71, the subject matter of any one or more of Examples 64-70 optionally includes, wherein the classification model includes a logistic regression model.

[0079] Example 72 is a machine-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations including accessing training data; training a classification model; receiving test bolus data describing a test bolus dosage for a recipient; receiving glucose concentration data describing a glucose concentration of the recipient from a continuous glucose sensor; applying the classification model to determine that the test bolus dosage belongs to a first bolus category, wherein applying the classification model uses the test bolus data and the glucose concentration data; selecting a recipient action based at least in part on the test bolus data and the first bolus category; and providing a recipient action prompt on a user interface of a bolus application, wherein the prompt of the bolus application encourages the recipient to take the recipient action.

[0080] Example 73 is a system for managing diabetes therapy, the system comprising at least one processor programmed to perform operations including accessing correction bolus data describing a correction bolus dose received by a recipient at a first time; receiving glucose concentration data for the recipient from a glucose sensor describing a first period including the first time; using the correction bolus data and the glucose concentration data to determine recommended changes to insulin onboard parameters for the recipient; and providing instructions to the recipient of the recommended changes to the insulin onboard parameters.

[0081] In Example 74, the subject matter of Example 73 optionally includes an operation further including accessing meal bolus data describing a meal bolus dose received by the recipient at a second time prior to the first time, and determining the recommended changes to the insulin onboard parameters is based at least in part on the meal bolus data.

[0082] In Example 75, the subject matter of Example 74 optionally includes an operation further including determining that the time between the second time and the first time was less than a threshold time.

[0083] In Example 76, the subject matter of any one or more of Examples 73-75 optionally includes an operation further including determining an actual insulin on-board value at a first time and comparing the actual insulin on-board value to a calculated insulin on-board value determined using insulin on-board parameters for the recipient, wherein the recommended change to the insulin on-board parameters is based at least in part on the comparison.

[0084] In Example 77, the subject matter of Example 76 optionally includes an operation further including determining predicted insulin onboard parameters that result in a second calculated insulin onboard value that is substantially the same as the actual insulin onboard value, and the recommended changes to the insulin onboard parameters are changes to the predicted insulin onboard parameters.

[0085] In Example 78, the subject matter of any one or more of Examples 73-77 optionally includes operations further including accessing historical correction bolus data describing multiple correction bolus administrations received by the recipient prior to the first time, and identifying a post-bolus pattern in the recipient's glucose concentration after the multiple correction bolus administrations, wherein changes to the insulin onboard parameters are based at least in part on the post-bolus pattern.

[0086] In Example 79, the subject matter of Example 78 optionally includes the post-bolus pattern describing a glucose concentration for the recipient that is lower than a target glucose concentration, and the change to the insulin onboard parameter is to decrease the estimated insulin onboard for the meal bolus.

[0087] In Example 80, the subject matter of any one or more of Examples 78-79 optionally includes the post-bolus pattern describing a glucose concentration for the recipient that is higher than a target glucose concentration, and the change to the insulin onboard parameter is to increase the estimated insulin onboard for the meal bolus.

[0088] Example 81 is a method of managing diabetes therapy using a computing device, the method including: accessing correction bolus data describing a correction bolus dose received by a recipient at a first time; receiving glucose concentration data for the recipient from a glucose sensor describing a first period including the first time; using the correction bolus data and the glucose concentration data to determine recommended changes to insulin onboard parameters for the recipient; and providing instructions to the recipient of the recommended changes to the insulin onboard parameters.

[0089] In Example 82, the subject matter of Example 81 optionally includes accessing meal bolus data describing a meal bolus dose received by the recipient at a second time prior to the first time, and determining the recommended changes to the insulin onboard parameters is based at least in part on the meal bolus data.

[0090] In Example 83, the subject matter of Example 82 optionally includes determining that the second time and the first time were less than a threshold time.

[0091] In Example 84, the subject matter of any one or more of Examples 81-83 optionally includes determining an actual insulin on-board value at a first time and comparing the actual insulin on-board value to a calculated insulin on-board value determined using insulin on-board parameters for the recipient, wherein recommended changes to the insulin on-board parameters are based at least in part on the comparison.

[0092] In Example 85, the subject matter of Example 84 optionally includes determining predicted insulin onboard parameters that result in a second calculated insulin onboard value that is substantially the same as the actual insulin onboard value, and the recommended changes to the insulin onboard parameters are changes to the predicted insulin onboard parameters.

[0093] In Example 86, the subject matter of any one or more of Examples 81-85 optionally includes accessing historical correction bolus data describing multiple correction bolus administrations received by the recipient prior to the first time, and identifying a post-bolus pattern in the recipient's glucose concentration after the multiple correction bolus administrations, wherein changes to the insulin onboard parameters are based at least in part on the post-bolus pattern.

[0094] In Example 87, the subject matter of Example 86 optionally includes that the post-bolus pattern describes a glucose concentration for the recipient that is lower than a target glucose concentration, and the change to the insulin onboard parameter is to decrease the estimated insulin onboard for the meal bolus.

[0095] In Example 88, the subject matter of any one or more of Examples 86-87 optionally includes the post-bolus pattern describing a glucose concentration for the recipient that is higher than a target glucose concentration, and the change to the insulin onboard parameter is to increase the estimated insulin onboard for the meal bolus.

[0096] Example 89 is a machine-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations including accessing correction bolus data describing a correction bolus dose received by a recipient at a first time; receiving glucose concentration data for the recipient from a glucose sensor describing a first period of time that includes the first time; using the correction bolus data and the glucose concentration data to determine recommended changes to insulin on-board parameters for the recipient; and providing instructions to the recipient of the recommended changes to the insulin on-board parameters.

[0097] Example 90 is a system for managing a recipient's diabetes using a continuous glucose sensor, the system comprising at least one processor programmed to perform operations including receiving, from the continuous glucose sensor, glucose concentration data describing at least a first glucose concentration of the recipient at a first time and a second glucose concentration of the recipient at a second time; determining a glucose concentration rate of change for the recipient using the glucose concentration data; determining a predicted glucose concentration for the recipient at a future time using the glucose rate of change; and determining a bolus dose for the recipient using the predicted glucose concentration at the future time and the recipient's current glucose concentration at the current time.

[0098] In Example 91, the subject matter of Example 90 optionally includes an operation further including determining a trend component of the bolus dose using the predicted glucose concentration and an insulin sensitivity value (ISF) for the recipient, wherein the bolus dose is based at least in part on the trend component.

[0099] In Example 92, the subject matter of any one or more of Examples 90-91 optionally includes a few minutes from the current time.

[0100] In Example 93, the subject matter of any one or more of Examples 90-92 optionally includes an operation further including selecting, by the bolus application, a future time based at least in part on the recipient's age.

[0101] In Example 94, the subject matter of any one or more of Examples 90 to 93 optionally includes operations further including receiving, by the bolus application, second glucose concentration data from the continuous glucose sensor describing at least a third glucose concentration of the recipient at a third time and a fourth glucose concentration of the recipient at a fourth time; determining, by the bolus application, a second glucose concentration rate of change for the recipient using the glucose concentration data; determining, by the bolus application, that the second glucose concentration rate of change is negative; determining to omit a trend component of the second bolus dose for the recipient; and determining a second bolus dose for the recipient using the second glucose concentration.

[0102] In Example 95, the subject matter of any one or more of Examples 90 to 94 optionally includes operations further including: receiving, by the bolus application, second glucose concentration data from the continuous glucose sensor describing at least a third glucose concentration of the recipient at a third time and a fourth glucose concentration of the recipient at a fourth time; determining, by the bolus application, a second glucose concentration rate of change for the recipient using the glucose concentration data; determining, by the bolus application, a second predicted glucose concentration for the recipient at a second future time using the second glucose rate of change; determining, by the bolus application, that the second predicted glucose concentration for the recipient is higher than a threshold; determining to omit a trend component of a second bolus dose for the recipient; and using the second glucose concentration to determine a second bolus dose for the recipient.

[0103] In Example 96, the subject matter of Example 95 optionally includes an operation further including selecting, by the bolus application, the threshold value based at least in part on the age of the recipient.

[0104] In Example 97, the subject matter of any one or more of Examples 90 to 96 optionally includes operations further including receiving, by a bolus application, a request to determine a second bolus dose for the recipient; determining that the request to determine the second bolus is received within a threshold time of a meal bolus for the recipient; determining to omit a trend component of the second bolus dose for the recipient; and determining the second bolus dose for the recipient using second glucose concentration data received from the continuous glucose sensor.

[0105] In Example 98, the subject matter of any one or more of Examples 90 to 97 optionally includes operations further including receiving, by a bolus application, a request to determine a second bolus dose for the recipient, the request including meal data describing a meal associated with the second bolus dose; determining that the request to determine the second bolus is received within a threshold time of a previous meal bolus for the recipient; determining to omit a trend component of the second bolus dose for the recipient; and determining the second bolus dose for the recipient using second glucose concentration data received from the continuous glucose sensor.

[0106] Example 99 is a method for managing a recipient's diabetes using a continuous glucose sensor and a bolus application running on a computing device, the method including: receiving, by the bolus application, glucose concentration data from the continuous glucose sensor describing at least a first glucose concentration of the recipient at a first time and a second glucose concentration of the recipient at a second time; determining, by the bolus application, a glucose concentration rate of change for the recipient using the glucose concentration data; determining, by the bolus application, a predicted glucose concentration for the recipient at a future time using the glucose rate of change; and determining, by the bolus application, a bolus dose for the recipient using the predicted glucose concentration at the future time and the recipient's current glucose concentration at the current time.

[0107] In Example 100, the subject matter of Example 99 optionally includes determining a trend component of the bolus dose using the predicted glucose concentration and an insulin sensitivity value (ISF) for the recipient, and the bolus dose is based at least in part on the trend component.

[0108] In Example 101, the subject matter of any one or more of Examples 99-100 optionally includes a few minutes from the current time.

[0109] In Example 102, the subject matter of any one or more of Examples 99-101 optionally includes, by bolus application, selecting a future time based at least in part on the age of the recipient.

[0110] In Example 103, the subject matter of any one or more of Examples 99 to 102 optionally includes receiving, by a bolus application, second glucose concentration data from the continuous glucose sensor describing at least a third glucose concentration of the recipient at a third time and a fourth glucose concentration of the recipient at a fourth time; determining, by the bolus application, a second glucose concentration rate of change for the recipient using the glucose concentration data; determining, by the bolus application, that the second glucose concentration rate of change is negative; determining to omit a trend component of a second bolus dose for the recipient; and determining a second bolus dose for the recipient using the second glucose concentration data.

[0111] In Example 104, the subject matter of any one or more of Examples 99 to 103 optionally includes receiving, by a bolus application, second glucose concentration data from the continuous glucose sensor describing at least a third glucose concentration of the recipient at a third time and a fourth glucose concentration of the recipient at a fourth time; determining, by the bolus application, a second glucose concentration rate of change for the recipient using the glucose concentration data; determining, by the bolus application, a second predicted glucose concentration for the recipient at a second future time using the second glucose rate of change; determining, by the bolus application, that the second predicted glucose concentration for the recipient is higher than a threshold; determining to omit a trend component of a second bolus dose for the recipient; and using the second glucose concentration data to determine a second bolus dose for the recipient.

[0112] In Example 105, the subject matter of Example 104 optionally includes selecting, by bolus application, a threshold value based at least in part on the age of the recipient.

[0113] In Example 106, the subject matter of any one or more of Examples 99 to 105 optionally includes receiving, by a bolus application, a request to determine a second bolus dose for the recipient; determining that the request to determine the second bolus is received within a threshold time of a meal bolus for the recipient; determining to omit a trend component of the second bolus dose for the recipient; and determining the second bolus dose for the recipient using second glucose concentration data received from the continuous glucose sensor.

[0114] In Example 107, the subject matter of any one or more of Examples 99 to 106 optionally includes receiving, by a bolus application, a request to determine a second bolus dose for a recipient, the request including meal data describing a meal associated with the second bolus dose; determining that the request to determine the second bolus is received within a threshold time of a previous meal bolus for the recipient; determining to omit a trend component of the second bolus dose for the recipient; and determining the second bolus dose for the recipient using second glucose concentration data received from the continuous glucose sensor.

[0115] Example 108 is a machine-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations including receiving glucose concentration data from a continuous glucose sensor describing at least a first glucose concentration of a recipient at a first time and a second glucose concentration of the recipient at a second time; determining a glucose concentration rate of change for the recipient using the glucose concentration data; determining a predicted glucose concentration for the recipient at a future time using the glucose rate of change; and determining a bolus dose for the recipient using the predicted glucose concentration at the future time and the recipient's current glucose concentration at the current time.

[0116] Example 109 is a system for managing diabetes in a recipient using a continuous glucose sensor, the system comprising at least one processor programmed to perform operations including accessing glucose concentration data from the continuous glucose sensor, the glucose concentration data indicating a current glucose concentration for the recipient; accessing bolus data indicating a bolus dose received by the recipient; selecting a hyperglycemia warning threshold based at least in part on the bolus data; determining that the current glucose concentration meets the hyperglycemia warning threshold; and providing a glucose warning to the recipient.

[0117] In Example 110, the subject matter of Example 109 optionally includes an operation further including determining an insulin on-board value for the recipient, and determining the hyperglycemia warning threshold is based at least in part on the insulin on-board value.

[0118] In Example 111, the subject matter of Example 110 optionally includes an operation further including determining that the insulin on-board value is lower than a threshold value, and selecting a hyperglycemia warning threshold includes lowering the hyperglycemia warning threshold based at least in part on determining that the insulin on-board value is lower than the threshold value.

[0119] In Example 112, the subject matter of any one or more of Examples 110-111 optionally includes an operation further including determining that the insulin on-board value is higher than a threshold value, and selecting a hyperglycemia warning threshold includes raising the hyperglycemia warning threshold based at least in part on determining that the insulin on-board value is higher than the threshold value.

[0120] In Example 113, the subject matter of any one or more of Examples 109-112 optionally includes an operation further including determining that more than a threshold time has elapsed since the recipient received the bolus dose, and determining the hyperglycemia warning threshold is based at least in part on determining that more than a threshold time has elapsed since the recipient received the bolus dose.

[0121] In Example 114, the subject matter of Example 113 optionally includes, wherein selecting the hyperglycemia warning threshold includes lowering the hyperglycemia warning threshold based at least in part on determining that more than a threshold time has elapsed since the recipient received the bolus dose.

[0122] In Example 115, the subject matter of any one or more of Examples 109-114 optionally includes an operation further including determining that less than a threshold time has elapsed since the recipient received the bolus dose, and selecting the hyperglycemia warning threshold includes increasing the hyperglycemia warning threshold based at least in part on determining that less than a threshold time has elapsed since the recipient received the bolus dose.

[0123] Example 116 is a method for managing diabetes of a recipient using a continuous glucose sensor and a bolus application running on a computing device, the method including: accessing, by the bolus application, glucose concentration data from the continuous glucose sensor, wherein the glucose concentration data indicates a current glucose concentration for the recipient; accessing, by the bolus application, bolus data indicating a bolus dose received by the recipient; selecting, by the bolus application, a hyperglycemia warning threshold based at least in part on the bolus data; determining, by the bolus application, that the current glucose concentration meets the hyperglycemia warning threshold; and providing, by the bolus application, a glucose warning to the recipient.

[0124] In Example 117, the subject matter of Example 116 optionally includes determining an insulin on-board value for the recipient by bolus application, and determining the hyperglycemia warning threshold is based at least in part on the insulin on-board value.

[0125] In Example 118, the subject matter of Example 117 optionally includes determining that the insulin on-board value is lower than a threshold value, and selecting a hyperglycemia warning threshold includes lowering the hyperglycemia warning threshold based at least in part on determining that the insulin on-board value is lower than the threshold value.

[0126] In Example 119, the subject matter of any one or more of Examples 117-118 optionally includes determining that the insulin on-board value is higher than a threshold value, and selecting a hyperglycemia warning threshold includes raising the hyperglycemia warning threshold based at least in part on determining that the insulin on-board value is higher than the threshold value.

[0127] In Example 120, the subject matter of any one or more of Examples 116-119 optionally includes determining, by the bolus application, that more than a threshold time has elapsed since the recipient received the bolus administration, and the determination of the hyperglycemia warning threshold is based at least in part on the determination that more than the threshold time has elapsed since the recipient received the bolus administration.

[0128] In Example 121, the subject matter of Example 120 optionally includes selecting the hyperglycemia warning threshold including lowering the hyperglycemia warning threshold based at least in part on determining that more than a threshold time has elapsed since the recipient received the bolus dose.

[0129] In Example 122, the subject matter of any one or more of Examples 116-121 optionally includes determining, by the bolus application, that less than a threshold time has elapsed since the recipient received the bolus dose, and selecting the hyperglycemia warning threshold includes increasing the hyperglycemia warning threshold based at least in part on determining that less than the threshold time has elapsed since the recipient received the bolus dose.

[0130] Example 123 is a machine-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to perform operations including accessing glucose concentration data from a continuous glucose sensor, wherein the glucose concentration data indicates a current glucose concentration for the recipient; accessing bolus data indicative of a bolus dose received by the recipient; selecting a hyperglycemia warning threshold based at least in part on the bolus data; determining that the current glucose concentration meets the hyperglycemia warning threshold; and providing a glucose warning to the recipient.

[0131] This Summary is intended to provide an overview of the subject matter of this patent application. It is not intended to provide an exclusive or exhaustive description of the disclosure. The Detailed Description is included to provide further information regarding this patent application. Other aspects of the present disclosure will be apparent to those skilled in the art upon reading and understanding the following Detailed Description and viewing the Drawings that form a part hereof, each of which should not be construed in a limiting sense. [Brief explanation of the drawings]

[0132] In the drawings, which are not necessarily drawn to scale, like numerals may describe like components in different views. Like numerals with different letter suffixes may represent different instances of like components. The drawings illustrate generally, by way of example, but not by way of limitation, various embodiments discussed in the present document.

[0133] [Figure 1] FIG. 1 illustrates an example of an environment including an analyte sensor system. [Figure 2] FIG. 2 illustrates an example of a medical device system including the analyte sensor system of FIG. 1. [Figure 3] FIG. 1 is a diagram of an exemplary analyte sensor. [Figure 4] FIG. 4 is an expanded view of an exemplary analyte sensor portion of the analyte sensor system shown in FIG. 3. [Figure 5] FIG. 5 is a cross-sectional view of the analyte sensor of FIGS. 3 and 4. [Figure 6] FIG. 1 is a schematic diagram of a circuit illustrating the behavior of an exemplary analyte sensor. [Figure 7] FIG. 10 illustrates an example environment demonstrating the use of a bolus application to determine and use a set of at least one bolus configuration parameter for a recipient. [Figure 8] 1 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to determine a set of one or more bolus configuration parameters, as described herein. [Figure 9] 10 is a flowchart illustrating an example of a query workflow that may be performed by a bolus application to determine bolus configuration parameters. [Figure 10] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to determine one or more bolus configuration parameters using a model. [Figure 11] FIG. 1 illustrates an example environment that includes demonstrating the use of a bolus application to determine and utilize bolus effect data. [Figure 12] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to determine and display bolus effect data. [Figure 13] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to determine bolus effect data for a bolus dose. [Figure 14] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to determine bolus effect data for a bolus dose. [Figure 15] 10A-10C illustrate example screens of a bolus application user interface showing bolus effect data. [Figure 16] FIG. 1 illustrates an example environment demonstrating the use of a bolus application to apply an example case-based reasoning technique. [Figure 17] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to determine a bolus dose for a recipient. [Figure 18] 10 is a flowchart illustrating an example of a process flow that may be performed by the bolus application when the difference between the current case and the closest reference case is too great to determine a suitably accurate bolus dose. [Figure 19] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application when an intervening event occurs during the monitoring of outcome data for a potential new reference case or a stored case. [Figure 20] FIG. 1 illustrates an example environment demonstrating the use of a bolus application to implement a classification model for classifying bolus doses. [Figure 21] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to utilize a classification model to determine a bolus dose category. [Figure 22] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to determine a recommended recipient action based on the category of the test bolus determined using a classification model. [Figure 23] FIG. 1 illustrates an example environment demonstrating the use of a bolus application to modify insulin on-board (IOB) parameters. [Figure 24] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to generate recommended changes to IOB parameters. [Figure 25] FIG. 1 illustrates an example environment demonstrating the use of a bolus application to determine a recipient's bolus dose using trend adjustment, as described herein. [Figure 26] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to determine a recipient's bolus dose using a trend component. [Figure 27] FIG. 27 illustrates another example of the process flow of FIG. 26 with an additional operation to optionally omit the bolus trend component. [Figure 28] FIG. 28 illustrates an example environment 2800 showing a bolus application 2834 configured to take bolus data into account and generate glucose concentration alerts. [Figure 29] 10 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to generate an alert based on bolus information for a recipient. [Figure 30] 1 is a flowchart illustrating an example of a process flow that may be performed by a bolus application to perform various techniques described herein. [Figure 31] FIG. 1 is a block diagram illustrating the hardware architecture of a computing device in which a set of instructions or sequences of instructions can be executed to cause the machine to perform any one of the example methodologies discussed herein. DETAILED DESCRIPTION OF THE INVENTION

[0134] Various embodiments described herein are directed to analyte sensors and methods for using the analyte sensors to administer a bolus dose of insulin to a recipient. The analyte sensor is placed in contact with the recipient's bodily fluid to measure the concentration of an analyte, such as glucose, in the bodily fluid. In some examples, the analyte sensor is inserted under the recipient's skin and placed in contact with interstitial fluid under the skin to measure the concentration of the analyte in the interstitial fluid.

[0135] Diabetic patients receiving insulin may receive basal insulin doses and bolus insulin doses. Basal insulin doses, also referred to herein as basal doses, are used to manage resting glucose levels, while bolus insulin doses are used to correct or compensate for events, such as meals, that elevate glucose levels. The basal dose is delivered to achieve a desired background or resting glucose level. In patients using insulin pumps or similar delivery devices, the basal dose can be delivered constant or semi-constantly according to a profile over time. In some instances, a long-acting insulin drug is used for the basal dose. For example, some patients who do not use insulin pumps receive a basal dose of long-acting insulin one or more times daily, often in a fixed amount.

[0136] Bolus insulin administration, also referred to herein as bolus administration, typically utilizes short-acting insulin medications, which have a potent but often short-lived effect on glucose levels. Thus, bolus administration is used to compensate for food eaten by the patient (meal bolus) and / or to correct deviations from target glucose levels (correction bolus). In some instances, the bolus dose is determined and / or administered in conjunction with a basal dose. For example, any suitable embodiment described herein can be used to generate a combined dose that includes a bolus component and a basal component.

[0137] Many factors are relevant to determining a patient's bolus dose, including, for example, the amount of food the recipient intends to eat, the recipient's current glucose level, how the recipient's body is responding to the food, the recipient's activity level, the recipient's alcohol intake, etc. Various embodiments herein are directed to configurations for assisting a recipient in receiving a bolus dose, for example, utilizing analyte sensors and / or analyte data detected by the analyte sensors.

[0138] 1 illustrates an example environment 100 that includes an analyte sensor system 102. The analyte sensor system 102 is coupled to a recipient 101, which may be a human patient. In some examples, the recipient 101 is a diabetic patient who has a temporary or permanent diabetic condition or other health condition that makes analyte monitoring useful. It will be understood that the environment 100 includes various components that can be used in a variety of different combinations to implement the systems and methods described herein.

[0139] The analyte sensor system 102 includes an analyte sensor 104. In some examples, the analyte sensor 104 is or includes a glucose sensor configured to measure a glucose concentration in the recipient 101. The analyte sensor 104 can be exposed to the analyte in the recipient 101 in any suitable manner. In some examples, the analyte sensor 104 is fully implantable under the skin of the recipient 101. In other examples, the analyte sensor 104 is wearable on the body of the recipient 101 (e.g., wearable on the body but not under the skin). Also, in some examples, the analyte sensor 104 is a transcutaneous device (e.g., the sensor is at least partially under or in the skin of the recipient). It should be understood that the devices and methods described herein are applicable to any device capable of detecting the concentration of an analyte, such as glucose, and providing an output signal representative of the concentration of the analyte.

[0140] According to various embodiments, the glucose detected can be D-glucose. However, it is possible to detect any stereoisomer or mixture of stereoisomers of glucose, as well as any glucose in its open-chain, cyclic, or mixture of open-chain and cyclic forms. In the example of FIG. 1, the analyte sensor system 102 also includes sensor electronics 106. In some examples, the sensor electronics 106 and the analyte sensor 104 are provided in a single, integrated package. In other examples, the analyte sensor 104 and the sensor electronics 106 are provided as separate components or modules. For example, the analyte sensor system 102 can include a disposable (e.g., single-use) sensor mounting unit ( FIG. 3 ), which can include a mounting structure configured to receive a sensor electronics unit containing the analyte sensor 104, components for attaching the sensor 104 to a recipient (e.g., adhesive pads), and / or some or all of the sensor electronics 106 shown in FIG. 2 . The sensor electronics unit can be reusable.

[0141] The analyte sensor 104 can use any known method, including invasive, minimally invasive, or non-invasive sensing techniques (e.g., optically excited fluorescence, microneedles, transcutaneous monitoring of glucose), to provide a raw sensor signal indicative of the concentration of the analyte within the recipient 101. The raw sensor signal can be converted into calibrated and / or filtered analyte concentration data, which is used to provide a useful value of the analyte concentration (e.g., an estimated blood glucose concentration level) to a user, such as the recipient or a caregiver (e.g., a parent, relative, guardian, teacher, doctor, nurse, or other individual interested in the health status of the recipient 101).

[0142] In some examples, the analyte sensor 104 is or includes a continuous glucose sensor. The continuous glucose sensor may be or include a subcutaneous device, a transcutaneous device (e.g., a transdermal device), and / or an intravascular device. In some embodiments, such a sensor or device may analyze sensor data repeatedly (e.g., periodically or intermittently). The glucose sensor may use any method of glucose measurement, including enzymatic, chemical, physical, electrochemical, spectrophotometric, polarimetric, calorimetric, iontophoretic, radiometric, immunochemical, etc. In various examples, the analyte sensor system 102 may be or may include a continuous glucose sensor available from DexCom, Inc., San Diego, California (e.g., a DexCom G5™ sensor or a Dexcom G6™ sensor or any variant thereof), available from Abbott™ (e.g., a Libre™ sensor), or available from Medtronic™ (e.g., an Enlite™ sensor).

[0143] In some examples, the analyte sensor 104 includes an implantable glucose sensor, such as those described with reference to U.S. Patent No. 6,001,067 and U.S. Patent Publication No. 2005 / 0027463(A1), which are incorporated by reference. In some examples, the analyte sensor 104 includes a transcutaneous glucose sensor, such as those described with reference to U.S. Patent Publication No. 2006 / 0020187(A1), which are incorporated by reference. In some examples, the analyte sensor 104 may be configured to be implanted in a blood vessel or externally to a recipient, such as those described in U.S. Patent Publication No. 2007 / 0027385(A1), co-pending U.S. Patent Publication No. 2008 / 0119703(A1), filed October 4, 2006, U.S. Patent Publication No. 2008 / 0108942(A1), filed March 26, 2007, and U.S. Patent Application No. 2007 / 0197890(A1), filed February 14, 2007. In some examples, the continuous glucose sensor may include a transcutaneous sensor, such as those described in U.S. Patent No. 6,565,509 to Say et al., which is incorporated by reference. In some examples, the analyte sensor 104 may include a continuous glucose sensor including a subcutaneous sensor, such as those described with reference to U.S. Pat. No. 6,579,690 to Bonnecaze et al. or U.S. Pat. No. 6,484,046 to Say et al., which are incorporated by reference. In some examples, the continuous glucose sensor may include a refillable subcutaneous sensor, such as those described with reference to U.S. Pat. No. 6,512,939 to Colvin et al., which are incorporated by reference. The continuous glucose sensor may include an intravascular sensor, such as those described with reference to U.S. Pat. No. 6,477,395 to Schulman et al., which are incorporated by reference. The continuous glucose sensor may include an intravascular sensor, such as those described with reference to U.S. Pat. No. 6,424,847 to Mastrototaro et al., which are incorporated by reference.

[0144] The environment 100 may also include a second medical device 108. The second medical device 108 may be or may include a drug delivery device such as an insulin pump or insulin pen. In some examples, the medical device 108 includes one or more sensors, such as another analyte sensor, a heart rate sensor, a respiration sensor, a motion sensor (e.g., an accelerometer), a posture sensor (e.g., a three-axis accelerometer), an acoustic sensor (e.g., to capture ambient or internal sounds), etc. The medical device 108 may be wearable, for example, on a watch, glasses, contact lenses, a patch, a wristband, an ankle band, or other wearable item, or may be incorporated into a handheld device (e.g., a smartphone). In some examples, the medical device 108 includes a multi-sensor patch that can detect, for example, one or more of an analyte level (e.g., glucose, lactate, insulin, or other substance), heart rate, respiration (e.g., using impedance), activity (e.g., using an accelerometer), posture (e.g., using an accelerometer), galvanic skin response, tissue fluid level (e.g., using impedance or pressure).

[0145] In some examples, the analyte sensor system 102 and the second medical device 108 are in communication with each other. Communication between the analyte sensor system 102 and the medical device 108 can occur via any suitable wired connection and / or via wireless communication signals 110. For example, the analyte sensor system 102 can be configured to communicate using radio frequency (e.g., Bluetooth, Medical Implant Communication System (MICS), Wi-Fi, near field communication (NFC), radio frequency identification (RFID), Zigbee, Z-Wave, or other communication protocols), optical (e.g., infrared), acoustic (e.g., ultrasound), or cellular protocols (e.g., code division multiple access (CDMA) or global system for mobile (GSM)), or via a wired connection (e.g., serial connection, parallel connection, etc.).

[0146] In some examples, the environment 100 also includes a wearable sensor 130. The wearable sensor 130 may include sensor circuitry (e.g., a sensor circuitry configured to detect a glucose concentration or other analyte concentration) and communication circuitry, which may be, for example, an NFC circuitry. In some examples, information from the wearable sensor 130 may be retrieved from the wearable sensor 130 using a user computing device 132, such as a smartphone, configured to communicate with the wearable sensor 130 via the wearable sensor's communication circuitry when the user device 132 is placed near the wearable sensor 130. For example, sensor data may be retrieved from the wearable sensor 130 using NFC or other suitable wireless communication by swiping the user device 132 over the sensor 130. The use of NFC communication may reduce power consumption by the wearable sensor 130, thereby reducing the size of or extending the usable life of a power source (e.g., a battery or capacitor) within the wearable sensor 130. In some examples, the wearable sensor 130 may be wearable on the upper arm, as shown. In some examples, wearable sensors 130 may additionally or alternatively be located on the patient's upper torso (e.g., over the heart or lungs), which may facilitate detecting, for example, heart rate, breathing, or posture. Wearable sensors 136 may also be located on the lower body (e.g., legs).

[0147] In some examples, environment 100 also includes a wearable device 120, such as a watch. Wearable device 120 may include an activity sensor, a heart rate monitor (e.g., an optical-based sensor or an electrode-based sensor), a respiration sensor (e.g., an acoustic-based or electrode-based sensor), a location sensor (e.g., GPS), or other sensors. Wearable device 120 can communicate with user device 132, smart device 112, tablet computing device 114, or other suitable computing device. For example, user device 132, smart device 112, or other suitable computing device can execute an application that communicates with wearable device 120 and provides data captured by and / or derived from one or more sensors of wearable device 120 to recipient 101.

[0148] In some examples, an array or network of sensors may be associated with the patient. For example, one or more of the analyte sensor system 102, medical device 108, wearable device 120, and / or additional wearable sensor 130 may communicate with each other via wired or wireless (e.g., Bluetooth, MICS, NFC, or any of the other options described above) communication. The additional wearable sensor 130 may be any of the examples described above with respect to the medical device 108. The analyte sensor system 102, medical device 108, and additional sensor 130 on the recipient 101 are provided for purposes of illustration and explanation and are not necessarily drawn to scale.

[0149] The environment 100 may also include one or more computing devices, such as a handheld smart device (e.g., smart device) 112, a tablet computing device 114, a smart pen 116 (e.g., an insulin delivery pen having processing and communication capabilities), a computing device 118, a wearable device 120, or a peripheral medical device 122 (which may be a proprietary device such as a proprietary user device available from DexCom, Inc., San Diego, California), any of which may communicate with the analyte sensor system 102 via wireless communication signals 110 and may also communicate with a server system (e.g., a remote data center) or a remote terminal 128 via a network 124 to facilitate communication with a remote user (not shown), such as a technical support staff member or a clinician.

[0150] In some examples, environment 100 includes a server system 126. Server system 126 can include one or more computing devices, such as one or more server computing devices. In some examples, server system 126 is used to collect analyte data from analyte sensor system 102 and / or analyte or other data from multiple other devices, and is used to perform analyses on the collected data, generate or apply universal or individualized models of glucose concentrations, and communicate such analytes, models, or information based thereon back to one or more of the devices in environment 100. In some examples, server system 126 aggregates inter-recipient and / or intra-recipient intrusion data to generate one or more intrusion characteristics, as described herein.

[0151] The environment 100 may also include a wireless access point (WAP) 138 used to communicatively couple one or more of the analyte sensor system 102, the network 124, the server system 126, the medical device 108, or any of the peripheral devices described above. For example, the WAP 138 may provide Wi-Fi and / or cellular connectivity within the environment 100. Other communication protocols, such as NFC or Bluetooth, may also be used between devices in the environment 100.

[0152] Various devices within environment 100 can execute bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H. Bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H perform functions related to administering one or more bolus doses of insulin to recipient 101, as described herein. In some examples, this includes determining a bolus dose for recipient 101. For example, bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H can receive bolus input parameters, such as the recipient's glucose concentration, the number of carbohydrates ingested, and the like, and output a bolus dose, for example, in units of insulin. In some examples, the bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H can also detect and / or characterize bolus insulin administration, for example, to determine and / or optimize future treatment options for the recipient 101.

[0153] The bolus dose of insulin determined by the bolus application 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H may be provided to a drug delivery device, such as, for example, an insulin pump or other suitable drug delivery device included in the medical device 108 and / or smart pen 116. The drug delivery device may provide the prescribed bolus dose to the recipient 101 directly (e.g., by way of an insulin pump) and / or indirectly (e.g., by setting the dose on an insulin pen 116, which the recipient or other suitable human user can then use to inject the bolus insulin dose into the recipient).

[0154] 1, the various bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H are executed by different computing devices, including the medical device 108 (bolus application 134A), the user computing device 132 (bolus application 134B), the tablet computing device 114 (bolus application 134C), the smart device 112 (bolus application 134D), the computing device 118 (bolus application 134E), the medical device 122 (bolus application 134F), and the server system (bolus application 134H). In some examples, the bolus applications 134A, 134B, 134C, 132D, 132E, 134F, 134G, 134H execute on only one of them and provide some or all of the functionality described herein. For example, the recipient 101 can utilize a bolus application 134A executing on the medical device 108 to determine a bolus dose of insulin or to provide other functionality described herein. In other examples, the bolus applications 134A, 134B, 134C, 132D, 132E, 134F, 134G, 134H executing on different devices can operate independently or in conjunction with each other to perform the functionality described herein.

[0155] The bolus dose determined by the bolus application 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H can include a correction component, a meal component, or a correction component and a meal component. A bolus dose that includes only a correction component is referred to herein as a correction bolus. A bolus dose that includes a meal component is referred to herein as a meal bolus. A meal bolus may or may not include a correction component.

[0156] The correction component of the bolus dose can be used to correct for deviations from the target glucose concentration of the recipient 101. An example of a formula that can be used by the bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H to determine the correction component is given by equation [1].

number

[0157] In equation [1], CC is the correction component. GC M is the measured glucose concentration of the recipient 101 and indicates the glucose concentration of the recipient 101 at or around the time the bolus dose is scheduled to be received. The measured glucose concentration, in some examples, indicates a value expressed in units of milligrams per deciliter (mg / dL). In some examples, the measured glucose concentration GC M is or is based on a measurement made by the analyte sensor 104. Tis the target glucose concentration for the recipient 101. The target glucose concentration is a desired glucose concentration. The target glucose concentration may be selected for the recipient 101, for example, by or with the input of a physician or medical professional. In some examples, the target glucose concentration is selected according to the recipient's age, sex, weight, or other characteristics. In equation [1], ISF is the insulin sensitivity value for the recipient 101. The ISF for the recipient 101 indicates the amount by which the glucose concentration is lowered per unit of insulin. For example, ISF may be expressed in mg / dL per unit of insulin. CC in equation [1] refers to a correction factor and is expressed in units of insulin.

[0158] The meal component of the bolus dose is used to supplement the food eaten by the recipient 101. When the recipient 101 eats food, the recipient's 101 body converts the food into glucose. This increases the recipient's glucose concentration. The recipient's 101 body uses insulin to process the glucose for use as energy or for storage as fat. The meal component of the bolus is intended to provide some or all of the insulin the recipient 101 needs to process the meal. An example formula for determining the meal component of a bolus dose is given by the following formula [2]:

number

[0159] In equation [2], MC is the meal component, expressed as units of insulin. C is a measure of the carbohydrate content of the ingested meal. C can be expressed in various suitable units, but is often expressed as the mass of carbohydrate ingested in grams. A gram of carbohydrate is sometimes referred to as a "carb." In practice, the body can convert other components of a meal (e.g., protein, fat, etc.) into glucose. However, in many applications, the glucose effect of protein and other food types is smaller and delayed than that of carbohydrates, so the suitable meal component can be determined by considering only carbohydrate. Nevertheless, in some instances, the meal component of a bolus is determined by considering carbohydrate as well as other components of the meal (e.g., protein, fat, etc.).

[0160] The ICR is the insulin-to-carbohydrate ratio for the recipient 101. The ICR indicates the number of units of insulin the recipient's 101 body requires to process a unit of food. In equation [2], grams of carbohydrate are used to represent a unit of food, and the ICR is expressed as grams of carbohydrate per unit of insulin. The ICR varies from patient to patient, and sometimes even for the same patient / recipient 101. The ICR can also be affected by environmental or behavioral factors. For example, if the recipient 101 is exercising or planning to exercise, the recipient's ICR can be effectively reduced (lowered dietary components). Other behavioral factors, such as alcohol intake, also affect the ICR.

[0161] As described herein, the bolus dose can include a meal component, a correction component, or both. Also, in some examples, the bolus application 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H can consider factors other than Equation 1 and Equation 2. For example, the bolus application 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H can also consider insulin on board (IOB), trend adjustment, carbohydrate on board (COB), and / or other factors. IOB indicates the amount of insulin present and active in the recipient 101's body. An increase in IOB can tend to decrease the recipient's 101 bolus dose.

[0162] Trend adjustment affects the insulin bolus dose based on how the recipient's measured glucose concentration is changing. Consider a first example in which the recipient's glucose concentration is 120 mg / dL and decreasing at 10 mg / dL per minute, and a second example in which the recipient's glucose concentration remains stable at 120 mg / dL. It will be understood that the same bolus dose may not be indicated for both examples. All else being equal, applying trend adjustment may tend to result in a lower bolus dose for the first example than for the second example. Various techniques can be used to incorporate trend adjustment when determining bolus doses, including, for example, the Scheiner method, the Pettus / Edelman method, the Klonoff / Kerr method, the Endocrine Society method, etc.

[0163] COB is an indication of carbohydrates that the recipient 101 has previously eaten but that have not yet been processed by the body. All else being equal, the presence of COB may tend to increase the bolus dose. Further details of bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H programmed to utilize IOB, COB, and / or trend adjustments are described herein.

[0164] Figure 2 is a diagram illustrating an example of a medical device system 200 that includes the analyte sensor system 102 of Figure 1. In the example of Figure 2, the analyte sensor system 102 includes sensor electronics 106 and a sensor mounting unit 290. While a particular example of the division of components between the sensor mounting unit 290 and the sensor electronics 106 is shown, it will be understood that in some examples, additional components may be included in the sensor mounting unit 290 and in the sensor electronics 106, and that some of the components shown in the sensor electronics 106 (e.g., a battery or supercapacitor) may be alternatively or additionally (e.g., redundantly) provided in the sensor mounting unit 290.

[0165] 2, the sensor mounting unit 290 includes the analyte sensor 104 and a battery 292. In some examples, the sensor mounting unit 290 may be replaceable, and the sensor electronics 106 may include debouncing circuitry (e.g., a gate with hysteresis or delay) to, for example, avoid repeated power-up or power-down processes when the battery is repeatedly connected and disconnected, or to avoid processing noise signals associated with removing or replacing the battery.

[0166] The sensor electronics 106 may include electronic components configured to process sensor information, such as a raw sensor signal, and generate a corresponding analyte concentration value. The sensor electronics 106 may include electronic circuitry associated with measuring, processing, storing, or communicating continuous analyte sensor data, including, for example, predictive algorithms associated with processing and calibrating the raw sensor signal. The sensor electronics 106 may include hardware, firmware, and / or software that enable the measurement of analyte levels via the glucose sensor. The electronic components may be affixed to a printed circuit board (PCB), or the like, and may take various forms. For example, the electronic components may take the form of an integrated circuit (IC), such as an application-specific integrated circuit (ASIC), a microcontroller, and / or a processor.

[0167] 2, the sensor electronics 106 includes a measurement circuit 202 (e.g., a potentiostat) coupled to the analyte sensor 104 and configured to repeatedly obtain analyte sensor readings using the analyte sensor 104. For example, the measurement circuit 202 can continuously or repeatedly measure a raw sensor signal indicative of current flow in the analyte sensor 104 between a working electrode and a counter or reference electrode (e.g., a counter reference electrode). The sensor electronics 106 can include a gating circuit 294 that can be used to gate the connection between the measurement circuit 202 and the analyte sensor 104. For example, the analyte sensor 104 can accumulate charge over an accumulation period. After the accumulation period, the gating circuit 294 is opened, allowing the measurement circuit 202 to measure the accumulated charge. Gating the analyte sensor 104 can improve the performance of the sensor system 102 by generating a greater signal-to-noise or signal-to-interference ratio (e.g., because charge accumulates from the analyte reaction, but interference sources such as the presence of acetaminophen near the glucose sensor do not accumulate or accumulate less charge than from the analyte reaction).

[0168] The sensor electronics 106 may also include a processor 204. The processor 204 is configured to retrieve instructions 206 from a memory 208 and execute the instructions 206 to control various operations in the analyte sensor system 102. For example, the processor 204 may be programmed to control the application of a bias potential to the analyte sensor 104 via a potentiostat in the measurement circuit 202, interpret the raw sensor signal from the analyte sensor 104, and / or compensate for environmental factors.

[0169] The processor 204 can also store information in or retrieve information from the data storage memory 210. In various examples, the data storage memory 210 may be integrated with the memory 208 or may be a separate memory circuit, such as a non-volatile memory circuit (e.g., flash RAM). Examples of systems and methods for processing sensor analyte data are described in more detail herein and in U.S. Patent Nos. 7,310,544 and 6,931,327.

[0170] The sensor electronics 106 may also include a sensor 212, which may be coupled to the processor 204. The sensor 212 may be a temperature sensor, an accelerometer, or another suitable sensor. The sensor electronics 106 may also include a power source, such as a capacitor or battery 214, which may be integrated into the sensor electronics 106, removable, or part of a separate electronics unit. The battery 214 (or other power storage component, e.g., a capacitor) may optionally be rechargeable via a wired or wireless (e.g., inductive or ultrasonic) recharging system 216. The recharging system 216 may recover energy or may receive energy from an external or built-in source. In various examples, the recharging circuit may include a triboelectric charging circuit, a piezoelectric charging circuit, an RF charging circuit, an optical charging circuit, an ultrasonic charging circuit, a thermal charging circuit, a heat recovery circuit, or a circuit that recovers energy from a communications circuit. In some examples, the recharging circuit may recharge a rechargeable battery using power provided from a replaceable battery (e.g., a battery supplied with the base component).

[0171] The sensor electronics 106 may also include one or more supercapacitors in the sensor electronics unit (as shown) or in the sensor mounting unit 290. For example, the supercapacitor can allow energy to be drawn from the battery 214 in a very consistent manner to extend the life of the battery 214. The battery 214 can recharge the supercapacitor after it delivers energy to the communications circuitry or processor 204, thereby preparing the supercapacitor to deliver energy during subsequent periods of high load. In some examples, the supercapacitor can be configured in parallel with the battery 214. The device can be configured to preferentially draw energy from the supercapacitor as opposed to the battery 214. In some examples, the supercapacitor can be configured to receive energy from a rechargeable battery for short-term storage and transfer energy to the rechargeable battery for long-term storage. The supercapacitor can extend the operating life of the battery 214 by reducing strain on the battery 214 during periods of high load.

[0172] The sensor electronics 106 may also include wireless communication circuitry 218, which may include, for example, a wireless transceiver operably coupled to an antenna. The wireless communication circuitry 218 may be operably coupled to the processor 204 and may be configured to wirelessly communicate with one or more peripheral devices or other medical devices, such as an insulin pump or smart insulin pen.

[0173] 2, medical device system 200 also includes optional peripheral device 250. Peripheral device 250 may be a suitable computing device such as, for example, a wearable device (e.g., an activity monitor), such as wearable device 120. In other examples, peripheral device 250 may be a handheld smart device (e.g., a smartphone or other device such as a proprietary handheld device available from Dexcom), tablet computing device 114 shown in FIG. 1, smart pen 116, or computing device 118.

[0174] The peripheral device 250 may include a UI 252, a memory circuit 254, a processor 256, a wireless communication circuit 258, a sensor 260, or any combination thereof. The peripheral device 250 may not necessarily include all of the components shown in Figure 2. The peripheral device 250 may also include a power source, such as a battery.

[0175] The UI 252 may be provided using, for example, any suitable input / output device or devices of the peripheral device 250, such as, for example, a touch screen interface, a microphone (e.g., for receiving voice commands), or a speaker, a vibrating circuit, or any combination thereof. The UI 252 may receive information (e.g., instructions, glucose values) from the recipient or another user. The UI 252 may also deliver information to the recipient or other user, for example, by displaying UI elements on the UI 252. For example, the UI elements may show glucose or other analyte concentration values, glucose or other analyte trends, glucose or other analyte alerts, etc. Trends may be shown by UI elements such as arrows, graphs, charts, etc.

[0176] The processor 256 may be configured to present information to or receive input from a user via the UI 252. The processor 256 may also be configured to store and retrieve information in the memory circuit 254, such as communication information (e.g., pairing information or data center access information), user information, sensor data or trends, or other information. The wireless communication circuit 258 may include a transceiver and antenna configured to communicate via a wireless protocol, such as any of the wireless protocols described herein. The sensors 260 may include, for example, an accelerometer, a temperature sensor, a location sensor, a biometric sensor, or a blood glucose sensor, a blood pressure sensor, a heart rate sensor, a respiration sensor, or other physiological sensor.

[0177] The peripheral device 250 may be configured to receive and display sensor information that may be transmitted by the sensor electronics 106 (e.g., in a customized data package transmitted to a display device based on respective preferences). The sensor information (e.g., blood glucose concentration level) or alerts or notifications (e.g., “high glucose level,” “low glucose level,” or “decline rate alert”) may be communicated via the UI 252 (e.g., via a visual display, sound, or vibration). In some examples, the peripheral device 250 may be configured to display or otherwise communicate the sensor information (e.g., in a data package transmitted to a respective display device) as it is communicated from the sensor electronics 106. For example, the peripheral device 250 may transmit processed data (e.g., an estimated analyte concentration level that may be determined by processing raw sensor data), such that the device receiving the data may not need to further process the data to determine usable information (such as an estimated analyte concentration level). In other examples, the peripheral device 250 may process or interpret the received information (e.g., to declare an alert based on glucose values ​​or glucose trends). In various examples, the peripheral device 250 may receive information directly from the sensor electronics 106 or over a network (e.g., over a cellular or Wi-Fi network that receives information from the sensor electronics 106 or from a device communicatively coupled to the sensor electronics 106).

[0178] 2, medical device system 200 includes optional medical device 270. For example, medical device 270 may be used in addition to or instead of peripheral device 250. Medical device 270 may be or include any suitable type of medical device or other computing device, including, for example, medical device 108, peripheral medical device 122, wearable device 120, wearable sensor 130, or wearable sensor 136 shown in FIG. 1. Medical device 270 may include a UI 272, a memory circuit 274, a processor 276, a wireless communication circuit 278, a sensor 280, a therapy circuit 282, or any combination thereof.

[0179] Like UI 252, UI 272 may be provided using any suitable input / output device or devices of medical device 270, such as, for example, a touch screen interface, a microphone, or a speaker, a vibrating circuit, or any combination thereof. UI 272 may receive information (e.g., glucose values, alert preferences, calibration coding) from the recipient or another user. UI 272 may also deliver information to the recipient or other user, for example, by displaying UI elements on UI 252. For example, UI elements may show glucose or other analyte concentration values, glucose or other analyte trends, glucose or other analyte alerts, etc. Trends may be shown by UI elements such as arrows, graphs, charts, etc.

[0180] The processor 276 may be configured to present information to or receive input from a user via the UI 272. The processor 276 may also be configured to store and retrieve information in the memory circuit 274, such as communication information (e.g., pairing information or data center access information), user information, sensor data or trends, or other information. The wireless communication circuit 278 may include a transceiver and antenna configured to communicate via a wireless protocol, such as any of the wireless protocols described herein.

[0181] The sensor 280 may include, for example, an accelerometer, a temperature sensor, a location sensor, a biometric sensor, or a blood glucose sensor, a blood pressure sensor, a heart rate sensor, a respiration sensor, or other physiological sensor. Although only one sensor 280 is shown in the example of Figure 2, the medical device 270 may include two or more sensors (or memory or other components). In various examples, the medical device 270 may be a smart handheld glucose sensor (e.g., a blood glucose meter), a drug pump (e.g., an insulin pump), or other physiological sensor device, a therapy device, or a combination thereof.

[0182] In examples where medical device 270 is or includes an insulin pump, the pump and analyte sensor system 102 may be in bidirectional communication (e.g., so the pump may request a change to the analyte transmission protocol, e.g., request data points or data on a more frequent schedule), or the pump and analyte sensor system 102 may communicate using one-way communication (e.g., the pump may receive analyte concentration level information from the analyte sensor system). In one-way communication, glucose values ​​may be incorporated into announcement messages that may be encrypted with a pre-shared key. In two-way communication, the pump may request values ​​that the analyte sensor system 102 shares or obtains and shares in response to a request from the pump, and any or all of these communications may be encrypted using one or more pre-shared keys. The insulin pump may receive and track analyte (e.g., glucose) values ​​transmitted from analyte sensor system 102 using one-way communication to the pump for one or more of a variety of reasons. For example, the insulin pump may pause or activate insulin delivery based on glucose values ​​that fall below or above a threshold.

[0183] In some examples, the medical device system 200 includes two or more peripheral devices and / or medical devices, each receiving information directly or indirectly from the analyte sensor system 102. Because different display devices may provide different user interfaces, the content of the data package (e.g., the amount, format, and / or type of data to be displayed, alarms, etc.) may be customized to each particular device (e.g., programmed differently by the manufacturer and / or end user). For example, referring now to the example of FIG. 1 , multiple different peripheral devices may wirelessly communicate directly with the sensor electronics 106 (e.g., skin-mounted sensor electronics 106 physically connected to the continuous analyte sensor 104) during a sensor session to enable multiple different types and / or levels of display and / or functionality associated with the displayable sensor information or to conserve battery power of the sensor system 102, and one or more designated devices may communicate with the analyte sensor system 102 and relay (i.e., share) information to other devices directly or via the server system 126 (e.g., a networked data center).

[0184] 3 is a side view of an exemplary analyte sensor 334 that may be implanted in a recipient. The mounting unit 314 may be adhered to the recipient's skin using an adhesive pad 308. The adhesive pad 308 may be formed from a stretchable material that may be removably attached to the skin using an adhesive. The electronics unit 318 may be mechanically coupled to the mounting unit 314. In some examples, the electronics unit 318 and the mounting unit 314 are arranged in a manner similar to the sensor electronics 106 and the sensor mounting unit 290 shown in FIGS. 1 and 2.

[0185] FIG. 4 is an enlarged view of a distal portion of the analyte sensor 334. The analyte sensor 334 can be adapted for insertion under the skin of a recipient and can be mechanically coupled to the mounting unit 314 and electrically coupled to the electronics unit 318. The exemplary analyte sensor 334 shown in FIG. 4 includes an elongated conductor 341. The elongated conductor 341 can include a core with various layers positioned thereon. A first layer 338 at least partially surrounds the core and includes, for example, a working electrode located in a window 339. In some examples, the core and first layer 338 are made of a single material (e.g., platinum, etc.). In some examples, the elongated conductor 341 is a composite of two conductive materials or a composite of at least one conductive material and at least one non-conductive material. A membrane system 332 is located on the working electrode and can cover other layers and / or electrodes of the sensor 334, as described herein.

[0186] First layer 338 may be formed of an electrically conductive material. The working electrode (of window 339) is the exposed portion of the surface of first layer 338. Thus, first layer 338 is formed of a material configured to provide a suitable electroactive surface for the working electrode. Examples of suitable materials include, but are not limited to, platinum, platinum-iridium, gold, palladium, iridium, graphite, carbon, conductive polymers, alloys thereof, and the like.

[0187] The second layer 340 surrounds at least a portion of the first layer 338, thereby defining the boundary of the working electrode. In some examples, the second layer 340 functions as an insulator and is formed of an insulating material such as polyimide, polyurethane, parylene, or any other suitable insulating material or materials.

[0188] The analyte sensor 334 may include two (or more) electrodes, e.g., a working electrode in layer 338 and exposed at window 339, and at least one additional electrode, such as a reference (e.g., counter-reference) electrode in layer 343. In the exemplary configurations of FIGS. 3-5, the reference electrode also functions as the counter electrode, although other configurations may include a separate counter electrode. The analyte sensor 334 may be used with a mounting unit in some examples, while in other examples, the analyte sensor 334 may be used with other types of sensor systems. For example, the analyte sensor 334 may be part of a system that includes a battery and sensor in a single package and may optionally include, for example, near-field communication (NFC) circuitry.

[0189] 5 is a cross-sectional view of the sensor 334 of FIG. 4 on plane 2-2, showing the membrane system 332. The membrane system 332 may include several domains (e.g., layers). In one example, the membrane system 332 may include an enzyme domain 342, a diffusion resistance domain 344, and a bioprotection domain 346 positioned around the working electrode. In some examples, a combined diffusion resistance domain and bioprotection domain may be included in the membrane system 332 (e.g., where the functionality of both the diffusion resistance domain and the bioprotection domain is incorporated into one domain).

[0190] The membrane system 332, in some examples, also includes an electrode layer 347. The electrode layer 347 can be positioned to provide an environment between the surface of the working electrode and a reference (e.g., counter) electrode that promotes an electrochemical reaction between the electrodes. For example, the electrode layer 347 can include a coating that maintains a layer of water on the electrochemically reactive surface of the sensor 334.

[0191] In some examples, the sensor 334 may be configured for short-term implantation (e.g., about 1 to 30 days). However, it will be understood that the membrane system 332 may be modified for use in other devices, e.g., by including only one or more domains or additional domains. For example, the membrane system 332 may include multiple resistive layers or multiple enzyme layers. In some examples, the resistive domain 344 may include multiple resistive layers, or the enzyme domain 342 may include multiple enzyme layers.

[0192] The diffusion resistance domain 344 may include a semipermeable membrane that controls the flow of oxygen and glucose to the underlying enzyme domain 342. As a result, the upper linearity limit of the glucose measurement is extended to values ​​much higher than that achieved without the diffusion resistance domain 344.

[0193] In some examples, the membrane system 332 may include a bioprotective domain 346, also referred to as a domain or biointerface domain, that includes a base polymer. However, some example membrane systems 332 may also include multiple domains or layers, including, for example, an electrode domain, an interference domain, or a cell disruption domain, as described in further detail elsewhere herein and in, for example, U.S. Patent Nos. 7,494,465, 8,682,608, and 9,044,199, which are incorporated herein by reference in their entireties.

[0194] For example, it should be understood that sensing membranes modified for other sensors may include fewer or additional layers. For example, in some examples, the membrane system 332 may include one electrode layer, one enzyme layer, and two bio-protection layers, while in other examples, the membrane system 332 may include one electrode layer, two enzyme layers, and one bio-protection layer. In some examples, the bio-protection layer may be configured to function as a diffusion resistance domain 344 and control the flow of an analyte (e.g., glucose) to the underlying membrane layer.

[0195] Although the examples illustrated in Figures 4-5 involve circumferentially extending membrane systems, the membranes described herein can be applied to any planar or non-planar surface, for example, the substrate-based sensor structures of U.S. Pat. No. 6,565,509 to Say et al., which is incorporated by reference.

[0196] In examples where the analyte sensor 334 is a glucose sensor, the glucose analyte may be detected utilizing glucose oxidase or another suitable enzyme, as described in more detail elsewhere herein. For example, glucose oxidase may react with glucose to produce hydrogen peroxide (HO). A pair of oxidation / redox reactions with the working and reference electrodes generates a sensor current. The magnitude of the sensor current indicates the concentration of hydrogen peroxide, and thereby the concentration of glucose.

[0197] The calibration curve can be used to generate an estimated glucose concentration level based on the measured sensor current. However, the magnitude of the sensor current also depends on other factors, such as the diffusion coefficient of glucose through the sensor membrane system and the working potential at the reference electrode. The glucose diffusion coefficient of the membrane system can change over time, which can cause the glucose sensitivity of the sensor to change or "drift" over time. Sensor drift can be compensated for, for example, by modeling the sensor drift and adjusting the calibration curve appropriately. Changes in the working potential at the reference (e.g., counter reference) electrode, which are described in more detail elsewhere herein, can be mitigated and / or compensated for, for example, using the techniques described herein.

[0198] 6 is a schematic diagram of a circuit 600 representing the behavior of an exemplary analyte sensor, such as the analyte sensor 334 shown in FIGS. 3-5. As described herein, the interaction of hydrogen peroxide (produced from the interaction between a glucose analyte and glucose oxidase) with a working electrode (WE) 604 produces a voltage difference between the working electrode (WE) 604 and a reference (e.g., counter reference) electrode (RE) 606, which drives a current. The current is measured by sensor electronics, such as the sensor electronics 106 of FIGS. 1-2, and may constitute all or a portion of the raw sensor signal used to estimate the analyte concentration (e.g., glucose concentration).

[0199] The circuit 600 also includes a double-layer capacitance (Cdl) 608 that occurs at the interface between the working electrode (WE) 604 and an adjacent membrane (not shown in FIG. 6; see, e.g., FIGS. 3-5 above). The double-layer capacitance (Cdl) may occur at the interface between the working electrode 604 and an adjacent membrane due to the presence of two layers of ions with opposite polarities, as may occur during application of an applied voltage between the working electrode 604 and a reference (e.g., counter-reference) electrode. The equivalent circuit 600 may also include a polarization resistance (Rpol) 610, which may be relatively large and may be modeled, for example, as a static value (e.g., 100 megaohms) or as a variable quantity that changes as a function of glucose concentration level.

[0200] An estimated analyte concentration may be determined from the raw sensor signal based on the measured current (or charge flow) through the analyte sensor membrane 612 when a bias potential is applied to the sensor circuit 600. For example, a sensor electronics device or another suitable computing device can use the raw sensor signal and the sensitivity of the sensor, which correlates the detected current flow to a glucose concentration level to generate an estimated analyte concentration. In some examples, the device also uses the invasive characteristics, as described herein.

[0201] Changes in the glucose diffusion coefficient over time present a problem in that two unknown variables exist in the system: the glucose concentration around the membrane 612 and the glucose diffusion coefficient of the membrane 612. For example, frequent blood glucose meter calibration can be used to account for drift, but the need for this glucose meter calibration may be undesirable for a variety of reasons (e.g., inconvenience to the patient, cost, potential inaccuracy of blood glucose meter data, etc.).

[0202] Referring to the equivalent circuit 600, when a voltage is applied across the working electrode 604 and the reference (e.g., counter-reference) electrode 606, current can be considered to flow (forward or reverse, depending on polarity) through the transmitter's internal electronics 611 (represented by R_Tx_internal), through the reference (e.g., counter-reference) electrode (RE) 606 and working electrode (WE) 604, which may be designed to have relatively low resistance, and through the sensor membrane 612 (relatively small, Rmembr). Depending on the state of the circuit, current may also pass through or into the relatively large polarization resistance 610 (which is shown as a fixed resistance, but may be a variable resistance that changes depending on the body's glucose level, with higher glucose levels resulting in a smaller polarization resistance), or into the double-layer capacitance 608 (i.e., to charge the double-layer membrane capacitor formed at the working electrode 604), or both.

[0203] The impedance (or conductance) of the membrane (Rmembr) 612 is related to the mobility of electrolytes within the membrane, which in turn is related to the glucose diffusion coefficient within the membrane. As the impedance decreases (i.e., conductance increases as the mobility of electrolytes within the membrane 612 increases), the glucose sensitivity increases (i.e., higher glucose sensitivity means that a particular glucose concentration generates a larger signal in the form of more current or charge flow). Impedance, glucose diffusion coefficient, and glucose sensitivity are further described in U.S. Patent Publication No. 2012 / 0262298, which is incorporated by reference in its entirety.

[0204] Various arrangements described herein are directed to arrangements for setting bolus configuration parameters for determining a recipient's bolus insulin dose. The bolus configuration parameters are input parameters used to generate a recipient's bolus dose. Examples of bolus configuration parameters include an insulin sensitivity factor (ISF), an insulin-to-carbohydrate ratio (ICR), and a target glucose concentration (GC), as described herein with respect to, for example, Equation [1] and Equation [2]. T ) Other bolus configuration parameters include, for example, parameters for utilizing insulin onboard, carbohydrate onboard, trend adjustment, or other features, as described herein. As described herein, the bolus configuration parameters depend on the individual physiology of the recipient 101 and may even change over time.

[0205] When the recipient 101 begins using a new bolus calculator, such as the bolus calculator implemented by the bolus application 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H, the recipient 101 must enter the ISF, ICR, and GC values ​​that can be entered into the bolus application 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H. T For example, the recipient 101 may have previously used a different bolus calculator to manually calculate bolus doses and / or a healthcare provider may have recommended certain configuration parameters. This may allow the recipient 101 to copy the previously used bolus configuration parameters into the new bolus calculator.

[0206] However, in some instances, the recipient 101 begins using a bolus calculator without knowledge of the bolus configuration parameters previously used. The recipient 101 may simply not be aware of the bolus configuration parameters used with a previous technique. Also, the recipient 101 may have previously used a different method of determining bolus doses that does not use the same bolus configuration parameters as the desired bolus calculator.

[0207] For example, some patients use bolus techniques based on simple heuristics that do not translate well to bolus calculators. For example, some patients receive the same bolus dose (e.g., by meal) regardless of the specific food ingested with the meal. Other patients receive a bolus dose that includes a rough adjustment for the patient's current glucose concentration rather than for the meal ingested. Still other patients receive a bolus dose that is fixed for a specific meal size (e.g., a small meal corresponds to X units of insulin, a medium meal corresponds to Y units of insulin, and a large meal corresponds to Z units of insulin).

[0208] Various examples described herein address these and other issues by implementing a bolus application configured to determine a set of at least one bolus configuration parameter for a recipient 101. Figure 7 is a diagram illustrating an example environment 700 demonstrating the use of a bolus application 734 to determine and use a set of at least one bolus configuration parameter for a recipient 701. In this example, the recipient 701 utilizes a computing device 702 to execute the bolus application 734. The computing device 702 can be any suitable computing device, such as, for example, a medical device 108, a user computing device 132, a tablet computing device 114, a smart pen 116, a smart device 112, a medical device 122, a computing device 118, a remote terminal 128, and / or a server system 126.

[0209] The computing device 702 can include and / or be in communication with an analyte sensor system 712 and a delivery system 714. The analyte sensor system 712, similar to the analyte sensor system 102, can detect an analyte at the recipient 701, such as the recipient's 701 glucose concentration. The delivery system 714 is configured to deliver a bolus dose to the recipient 701. For example, the delivery system 714 can be or include an insulin pen, an insulin pump, or other suitable delivery system. The bolus application 734 generates a bolus application user interface 703 that is provided to the recipient 701. The bolus application user interface 703 can include visual and / or audio elements to provide information to and / or receive information from the recipient 701. In the arrangement of FIG. 7, the bolus application 734 is configured to generate at least one set of bolus configuration parameters for use in generating a bolus dose for the recipient 701. The set of at least one bolus configuration parameter may include one bolus configuration parameter and / or two or more bolus configuration parameters.

[0210] 7, the bolus application 734 utilizes a set of questions, which may include adaptive questions, for determining bolus configuration parameters. The bolus application 734 may determine the bolus configuration parameters, for example, at setup time. According to an adaptive set of questions, questions are selected based on answers provided by the recipient 701 to previous questions. For example, a first question may ask the recipient 701 to provide a description of the bolus determination technique the recipient 701 is currently using. Subsequent questions may be selected based on the recipient's current bolus determination technique.

[0211] In the example of FIG. 7, several exemplary screens 704, 706, 708 of a bolus application user interface 703 are shown. A first screen 704 of the bolus application user interface 703 can provide a first question to the recipient 701. For example, the first question can query the recipient 701 for information regarding the recipient's previous bolus determination techniques. The first question can be configured in a format that is easy for the recipient 701 to understand and answer. For example, the first question can ask the recipient 701, "Do you use a formula or equation to calculate your insulin bolus dose?" The recipient 701 provides an answer to the first question via the bolus application user interface 703 using an input device of the computing device 702, such as a microphone, keyboard, or touchpad. In another example, the first question can be about a characteristic of the recipient 701, such as, "How much do you weigh?"

[0212] Upon receiving a response to the first question, the bolus application 734 selects a second bolus configuration parameter question and provides the recipient 701 with a second screen 706 showing the second bolus configuration parameter question. The second bolus configuration parameter question is based on the answer provided to the first bolus configuration parameter question. For example, if the recipient 701 provides a first answer indicating that the recipient 701 will calculate the bolus using a formula, the second question will be based on the ISF, ICR, or GC parameter currently being used by the recipient 701. TThe recipient 701 may be specifically asked, "What is the formula for calculating the insulin bolus dose?" If the recipient 701 provides a first answer indicating that the recipient 701 is not using a formula to calculate the insulin bolus dose, a second question may be asked that provides a rough indication of the bolus configuration parameters. For example, the second question may ask the recipient 701 to provide an indication of an example meal and an example bolus that would have been used to cover the meal under the recipient's previous bolus determination technique. In some examples, the recipient 701 is prompted to provide an image of the example meal. From that image, the bolus application 734 can derive nutritional information (e.g., carbohydrate count). In some examples, the image is captured by a camera or other image sensor integrated into the delivery system 714. While two questions are described in FIG. 7, in some examples, additional adaptive questions may be provided, and answers to the additional questions provided by the recipient 701. Upon receiving answers to one or more bolus configuration parameter questions, the bolus application 734 may then determine the ISF, ICR, or GC values. T and determining a set of one or more bolus configuration parameters, such as:

[0213] Upon determining the set of one or more bolus configuration parameters, the bolus application 734 can provide a bolus calculator UI screen 708. The bolus calculator UI screen 708 is provided to the recipient 701, for example, when a bolus dose is requested by the recipient 701 and / or the bolus application 734 (e.g., in response to detecting an uncovered meal or a desired correction). The recipient 701 can provide bolus input parameters, such as the number of carbohydrates ingested or to be ingested. In some examples, the bolus application 734 receives the recipient's 701 glucose concentration from the analyte sensor system 712. Based on the bolus input parameters and the bolus configuration parameters, the bolus application 734 determines a bolus dose for the recipient 701 using any suitable technique, including, for example, the techniques described herein.

[0214] An indication of the determined bolus dose can be provided to the recipient 701 via the bolus application's user interface 703. In this manner, the recipient 701 can utilize a syringe, insulin pen, insulin pump, or other suitable delivery system to receive the determined insulin bolus dose. In some examples, the bolus application 734 provides an indication of the determined bolus dose directed to the delivery system 714. In response, the delivery system 714 can deliver the bolus dose and / or can configure itself to deliver the bolus dose. In examples where the delivery system 714 is or includes an insulin pen, the insulin pen can configure itself to provide the determined bolus dose. The recipient 701 can utilize the pen to provide the bolus dose as determined. In some examples where the delivery system 714 is or includes an insulin pump, the insulin pump can provide the determined bolus with or without further input from the recipient 701.

[0215] In some examples, the bolus application 734 requests, via the UI 703, that the recipient 701 provide data describing a previous meal (e.g., the number of carbohydrates in the previous meal) and the associated bolus dose received by the recipient 701 for the previous meal. The bolus application 734 can use this data, alone or in combination with answers to other questions, to derive bolus configuration parameters.

[0216] 8 is a flowchart illustrating an example of a process flow 800 that may be performed by the bolus application 734 to determine a set of one or more bolus configuration parameters, as described herein. In operation 802, the bolus application 734 queries the recipient 701 to provide data describing the current bolus technology used by the recipient 701. Based on the answers provided by the recipient 701, the bolus application 734 selects a question set for further questioning. The selected question set includes one or more questions based on the answers the recipient 701 provides to the questions of operation 802. The selected question set may include questions related to the current bolus technology, characteristics of the recipient 701 (e.g., weight, height, etc.), or other suitable topics for determining bolus calculator parameters. In operation 806, the bolus application 734 executes one or more questions from the set of questions selected in operation 804.

[0217] In operation 808, the bolus application 734 determines whether the responses it received from the recipient 701 are sufficient to determine all of the bolus configuration parameters necessary to determine a bolus dose for the recipient 701. If the bolus application 734 determines that it can determine all of the bolus configuration parameters, it does so and performs operation 810 and can use the determined parameters to calculate a bolus dose for the recipient 701, for example, as described herein.

[0218] If the bolus application 734 does not have sufficient answers to determine the bolus configuration parameters, the bolus application 734 may jump to operation 816 or, optionally, determine at operation 812 whether there are additional sets of questions that can be presented to the recipient 701. If the bolus application 734 has sufficient answers to determine the bolus configuration parameters, the bolus application 734 may run a bolus parameter model (described herein) at operation 816, or, at optional operation 812, the bolus application 734 determines whether there are additional sets of questions. If there are additional sets of questions, the bolus application 734 selects the next set of questions at operation 814 and then performs one or more questions from the set selected at operation 806. The additional set of questions selected at operation 814 may be selected based on one or more answers received from the recipient 701 to the previous set of questions.

[0219] If there are no additional question sets at operation 812 (or in configurations where operation 812 is omitted), the bolus application 734 may execute a bolus configuration parameter model at operation 816. The bolus configuration parameter model may be any suitable type of model that associates characteristics of the recipient 701 with bolus configuration parameters. The model may also, in some examples, associate answers to the questions provided to the recipient at operation 806 with bolus configuration parameters in combination with or instead of recipient characteristics. Examples of recipient characteristics that the model may utilize include weight, body mass index (BMI), diabetes diagnosis (e.g., type I or type II), other medications taken, type of insulin used, etc. The bolus application 734 may query the recipient 701 to provide one or more characteristics, for example, if the characteristics were not previously provided in response to other queries. In some examples, the recipient characteristics may be received in response to a question from the question set executed at operation 806. Further details regarding exemplary models are described herein with respect to FIGS. 9 and 10.

[0220] 9 is a flow chart illustrating an example of a query workflow 900 that may be executed by the bolus application 734 to determine bolus configuration parameters for the recipient 701. For example, the workflow 900 demonstrates one configuration of queries that may be presented to the recipient 701 to determine bolus configuration parameters.

[0221] At 902, the bolus application 734 queries the recipient 701 (e.g., via the bolus application user interface 703) to indicate information regarding previous bolus determination techniques used by the recipient 701. In some examples, the bolus application 734 queries the recipient 701 to indicate what the recipient 701 considered to determine the bolus dose under the previous bolus determination technique. For example, the recipient 701 may determine the bolus insulin dose based on a meal eaten at or near the time of the bolus (e.g., a bolus-related meal) and / or based on a glucose concentration. An exemplary question for implementing 902 is shown by example question 1. Sample Question 1: What is the amount of insulin you should take with each meal? (A) Based on my glucose levels and food intake (B) Based solely on food intake (C) It's the same every time you eat breakfast, lunch, or dinner. (D) It is the same for all meals. In some instances, the query in 902 may include more than one question, such as Example Question 2 and Example Question 3 below. Sample Question 2: Are you using glucose concentrations to determine your bolus? Sample Question 3: Are you using meal size to determine your bolus?

[0222] Based on one or more answers provided by the recipient 701 to the queries in 902, the bolus application 734 selects a next set of one or more questions. If the recipient 701 indicates that the previous bolus determination technique uses both the glucose concentration and meal size of the bolus-related meal to determine the bolus, the bolus application 734 queries the recipient 701 using question set 904. For example, in 912, the bolus application 734 queries the recipient 701 to indicate whether the previous bolus determination technique included the use of a formula. Using a formula may indicate that the recipient 701 already knows or may be able to find direct values ​​for one or more bolus configuration parameters. If the recipient 701 indicates that the previous bolus determination technique used a formula, the bolus application 734 queries the recipient 701 with one or more direct questions in 920. The direct questions may include the ISF, ICR, GC, and the like. T The direct query may include a query prompting the recipient 701 to directly provide one or more bolus configuration parameters, such as: At 924, the bolus application 734 determines whether the response provided by the recipient 701 to the direct query at 920 provides all of the bolus configuration parameters for determining a bolus dose of insulin for the recipient 701. If all of the bolus configuration parameters are received, the bolus application 734 may determine one or more bolus doses of insulin for the recipient 701 at operation 934.

[0223] If the recipient 701 indicates at 912 that the recipient 701 will not use a formula for determining a bolus in the previous bolus determination technique (or if the direct questions at 920 did not provide all of the bolus configuration parameters), the bolus application 734 selects a set of questions that includes indirect questions regarding meal and correction bolus components. The bolus application 734 queries the recipient 701 with the selected indirect questions at 922. The indirect questions may not directly ask the recipient 701 to provide bolus input parameters, but may instead ask the recipient 701 for other information that can be used to derive the bolus configuration parameters. Examples of indirect questions related to meal bolus components are provided below. Sample Question 4: What is your typical lunch? Sample Question 5: If your glucose is on target, how much insulin would you expect to take for the typical lunch mentioned above? From the answers to these questions, the bolus application 734 may be able to determine an ICR for the recipient 701. For example, the bolus application 734 can estimate the number of carbohydrates (e.g., grams of carbohydrates) in a typical lunch. From the insulin taken by the recipient 701, the bolus application 734 determines the ICR. For example, the ICR for the recipient 701 may be or be based on the estimated carbohydrates for the meal multiplied by the indicated intake of insulin. In some examples, versions of example question 4 and example question 5 are asked for each meal of the day to determine meal-specific bolus configuration parameters.

[0224] Also, in some examples, the bolus application 734 requests information about different example meals to check the validity of the answers provided by the recipient 701. For example, the recipient 701 may be queried for information about multiple commonly eaten lunches. If the ICRs derived from the different lunches are the same or within a threshold, the bolus application 734 may determine that the derived ICRs are valid. (If the ICRs from different example meals are different but within a threshold, the bolus application 734, in some examples, uses an average or other aggregation of the different ICRs.) If the ICRs determined from different meals are sufficiently different from each other, the bolus application 734 may discard all of the determined ICRs as unreliable.

[0225] The bolus application 734 can determine whether the ICRs derived from different example meals are reliable in any suitable manner. For example, the bolus application 734 can receive and / or be programmed with a maximum acceptable error threshold in the ICR, which may be, for example, a constant. An example of a constant maximum acceptable error is when the ICR generated from an example meal does not differ from any other ICR by more than 2 grams / unit. In some examples, the maximum acceptable error threshold varies for different age ranges. For example, 2 grams / unit for recipients under 8 years old, 5 grams / unit for recipients 9-18 years old, and 10 grams / unit for recipients over 18 years old. In other examples, the maximum acceptable error threshold is a multiple of the ISF (e.g., 1 / 3 to 2 / 3 of the ISF, or approximately 1 / 2 of the ISF).

[0226] An exemplary indirect query for determining the bolus configuration parameters associated with the correction bolus components is given by the following example. Sample Question 6: How would you modify your mealtime insulin dose if your blood glucose is 20 mg / dL above target? Sample Question 7: How would you modify your mealtime insulin dose if your blood glucose is 50 mg / dL above target? The bolus application 734 can determine the ISF using answers to questions similar to, for example, example question 6 and example question 7. In some examples, the bolus application 734 checks the determined ISF by comparing the ISF indicated by answers to multiple questions similar to, for example, example question 6 and example question 7. If the determined ISFs are within a threshold of each other, the bolus application 734 can use the determined ISF (or an average or other aggregation of similar ISFs) as an ISF bolus configuration parameter. If the ISFs determined based on different questions differ sufficiently from each other, the bolus application 734 can discard all of the determined ISFs as unreliable.

[0227] Upon asking the indirect meal and glucose questions at 922, the bolus application 734 determines whether it has successfully determined the bolus configuration parameters for determining the insulin bolus dose for the recipient 701 at operation 926. If yes, the bolus application 734 may determine the insulin bolus dose at operation 934. If no, the bolus application 734 may run a model at operation 932, as described in more detail herein.

[0228] Referring back to 902, if the recipient 701 indicates that they want to determine a bolus based solely on the amount of a bolus-related meal, the bolus application 734 selects the meal-only question set 906 and queries the recipient 701 with one or more indirect questions about meal amount at 914. The indirect questions about meal amount may, for example, ask the recipient 701 to provide an example meal description and corresponding insulin dose, similar to example questions 4 and 5 above. At 928, the bolus application 734 determines whether the answers to the indirect questions at 914 provided sufficient bolus configuration parameters to determine the recipient's 701's insulin bolus dose. If yes, the bolus application 734 may determine the insulin bolus dose at operation 934. If no, the bolus application 734 may execute a model at operation 932, as described in more detail herein.

[0229] Referring back to 902, if the recipient 701 indicates that they want to determine a bolus based solely on glucose concentration, the bolus application 734 may select the glucose-only question set 908 and query the recipient 701 with one or more indirect glucose questions at operation 916. The indirect glucose questions may ask the recipient 701 to provide example insulin boluses provided at different glucose concentrations and / or different deviations from a target glucose concentration, such as example question 6 and example question 7 above. At 930, the bolus application 734 determines whether the answers to the indirect questions at 916 provided sufficient bolus configuration parameters to determine the recipient's 701 insulin bolus dose. If yes, the bolus application 734 may determine the insulin bolus dose at operation 934. If no, the bolus application 734 may execute a model at operation 932, as described in more detail herein.

[0230] If the recipient 701 indicates at 902 that they will use a constant bolus dose that is independent of meal size or blood glucose, then in some examples, the bolus application 734 executes 932 a model to generate bolus configuration parameters for the recipient 701. The model may be a trained model, which may be trained, for example, as described below with respect to FIG. 10. In other examples, the model may be a manually designed model, heuristic, or set of heuristics. For example, the bolus application 734 may apply a rule or set of rules to the answers received in the workflow 900.

[0231] FIG. 10 is a flowchart illustrating an example of a process flow 1000 that may be performed by the bolus application 734 to determine one or more bolus configuration parameters using a model. At operation 1002, the bolus application 734 trains a model using training data. Any suitable type of model may be trained, including, for example, a regression model such as a linear regression model, a polynomial regression model, a logistic regression model, a quantum regression model, a support vector regression model, a regression tree model, a principal component regression model, or the like. The training data may associate various recipient characteristics with different values ​​of the bolus configuration parameters. The training data may describe the recipient 701 and / or may describe multiple different recipients. In some examples, operation 1002 occurs prior to other operations in the process flow 1000. For example, the model may be trained and stored on the computing device 702. In some examples, the model may be trained on another computing device (e.g., the server system 126) and provided to the computing device 702 executing the bolus application 734.

[0232] At act 1004, the bolus application 734 queries the recipient 701 using a question set including one or more questions to query model inputs. Any suitable model inputs may be queried, including, for example, the recipient's weight, the recipient's BMI, the recipient's type of diabetes diagnosis, other medications being taken by the recipient 701, etc. At act 1006, the bolus application 734 runs the trained model using the received model inputs to generate one or more bolus configuration parameters. At act 1008, the bolus application 734 determines a bolus insulin dose for the recipient 701 using the bolus configuration parameters determined at act 1006.

[0233] In some examples, the bolus application is used to monitor and / or manage a recipient's bolus dose in addition to, or instead of, determining the bolus dose itself. The bolus application can be configured to determine the effect of the bolus, such as, for example, glucose concentration correction, the amount of meal (e.g., number of carbohydrates) covered by the bolus, etc. This effect data can be displayed to the recipient or other user. The recipient or other user can use the bolus effect data as a check. For example, if the recipient intends the bolus dose to cover a specific meal, the recipient will expect the bolus effect data to match the meal. Similarly, if the recipient intends the bolus dose to correctly provide a given glucose concentration, the recipient will expect the displayed bolus effect data to match the desired correction.

[0234] Although the techniques for determining bolus configuration parameters are described with respect to Figures 7-10 in the context of determining a bolus dose for a recipient, some or all of the examples herein can be used for basal doses. For example, the bolus and basal doses can be determined together in a single calculation using the bolus configuration parameters described herein to calculate a combined basal / bolus insulin dose that includes both a bolus and a basal component. Also, in some examples, some or all of the bolus configuration parameters described herein are relevant to determining a basal dose for a recipient. Thus, the bolus application 1134 (or another suitable application) can determine the bolus configuration parameters described herein and use the bolus configuration parameters to, at least in part, determine a basal dose of insulin.

[0235] 11 is a diagram illustrating an example environment 1100 demonstrating the use of a bolus application 1134 to determine and utilize bolus effect data. In this example, a recipient 1101 utilizes a computing device 1102 to execute the bolus application 1134. The computing device 1102 can be any suitable computing device, such as, for example, a medical device 108, a user computing device 132, a tablet computing device 114, a smart pen 116, a smart device 112, a medical device 122, a computing device 118, a remote terminal 128, and / or a server system 126.

[0236] The computing device 1102 can include and / or be in communication with an analyte sensor system 1112 and a delivery system 1114. The analyte sensor system 1112, like the analyte sensor system 102, can detect an analyte at the recipient 1101, such as the recipient's glucose concentration. The delivery system 1114 is configured to deliver a bolus dose to the recipient 1101. For example, the delivery system 1114 can be or include an insulin pen, an insulin pump, or other suitable delivery system. The bolus application 1134 generates a bolus application user interface 1103 that is provided to the recipient 1101. The bolus application user interface 1103 can include visual and / or audio elements to provide information to and / or receive information from the recipient 1101.

[0237] 11 , the bolus application 1134 is configured to generate bolus effect data describing a bolus dose that has been administered or is scheduled to be administered to the recipient 1101. The bolus effect data may include, for example, a glucose concentration correction associated with the bolus dose, a carbohydrate coverage associated with the bolus dose, etc. FIG. 11 shows an example screen 1104 of the bolus application user interface 1103 that provides example bolus effect information. In this example, the displayed bolus effect information indicates that a planned or recently administered bolus dose covers 124 grams of carbohydrates.

[0238] FIG. 12 is a flowchart illustrating an example of a process flow 1200 that may be performed by the bolus application 1134 to determine and display bolus effect data. In operation 1202, the bolus application 1134 receives a bolus dose instruction. The bolus dose instruction can be received in any suitable manner. In some examples, the bolus dose instruction is received from a delivery system 1114. Consider an example in which the delivery system 1114 is or includes an insulin pen, such as the smart pen 116 of FIG. 1. The recipient 1101 can configure the insulin pen to provide a desired bolus dose. The insulin pen provides the bolus application 1134 with bolus dose instructions via the computing device 1102. The insulin pen can provide the bolus dose instruction before or after the bolus dose is administered to the recipient 1101. Consider another example in which the delivery system 1114 is or includes an insulin pump. The insulin pump can similarly provide an indication of the bolus dose to be delivered or has been delivered to the bolus application 1134. In some examples described in more detail herein, the bolus application 1134 is configured to detect a bolus using data received from the analyte sensor system 1112. Examples for detecting a bolus dose and / or data related to a bolus dose are described herein, for example, with respect to Figures 20-22.

[0239] In act 1204, the bolus application 1134 determines bolus effect data. The bolus effect data can be determined in a variety of different ways. Examples for determining bolus effect data are provided herein with respect to Figures 13-15. The bolus application 1134 displays the bolus effect data in the bolus application user interface 1103 in act 1206.

[0240] 13 is a flowchart illustrating an example of a process flow 1300 that may be performed by the bolus application 1134 to determine bolus effect data for a bolus dose. In the example of FIG. 13, the bolus application 1134 receives an indication of a bolus dose in operation 1302, for example, as described herein.

[0241] At operation 1304, the bolus application 1134 determines a glucose correction associated with the bolus dose. The glucose correction may be determined in any suitable manner. In some examples, the bolus application 1134 receives glucose concentration data from the analyte sensor system 1112, where the glucose concentration data is indicative of a glucose concentration for the recipient 1101. The bolus application 1134 calculates the glucose concentration to a target glucose concentration (GC) for the recipient 1101. T ) to determine the glucose correction. For example, if the recipient's 1101 glucose concentration is 130 mg / dL and the target glucose concentration is 100 mg / dL, the glucose correction would be 30 mg / dL. In some instances, the glucose correction is allowed to be negative. For example, if the recipient's current glucose concentration is below the target glucose concentration, the glucose correction is negative.

[0242] In act 1306, the bolus application 1134 determines a correction component for the bolus dose. In some examples, this involves using an equation relating a glucose correction and a corresponding correction component, such as equation [1] above. In this example, the glucose correction determined in act 1304 is calculated as follows: M -GC T If the glucose correction is negative, the correction component may also be negative. As described herein below, the negative correction component may be taken into account when determining the meal components. In some examples, the negative correction component is not shown to the recipient 1101 via the user interface 1103 of the bolus application.

[0243] At act 1308, the bolus application 1134 determines the meal component of the bolus dose using the correction component determined at act 1306. The meal component may be the total bolus dose minus the correction component. In instances where the correction component is negative, the meal component is more than the total bolus dose. At act 1310, the bolus application 1134 determines the carbohydrate coverage of the meal bolus. This may be determined using a formula relating meal components to carbohydrates (e.g., grams of carbohydrates).

[0244] 14 is a flowchart illustrating an example of a process flow 1400 that may be performed by the bolus application 1134 to determine bolus effect data for a bolus dose. In operation 1402, the bolus application 1134 receives an indication of a bolus dose, for example, as described herein.

[0245] At operation 1404, the bolus application 1134 accesses meal data. The meal data can be received and / or determined in any suitable manner. In some examples, the meal data is received from the recipient 1101. For example, the recipient 1101 can provide a meal, such as a carbohydrate count for the meal. The recipient 1101 can input the meal data via the bolus application user interface 1103. In other examples, the bolus application 1134 receives an image of the meal. The image can be captured using a camera or other suitable image sensor of the computing device 1102. In some examples, the delivery system 1114 includes an insulin pen that includes an image sensor. The recipient 1101 captures an image of the meal using the insulin pen, and the image is transmitted from the delivery system 1114 to the computing device 1102. The bolus application 1134 analyzes the image to determine data about the meal, such as, for example, an estimated carbohydrate count for the meal (e.g., the number of grams of carbohydrates in the meal).

[0246] Any suitable technique can be used to determine an estimated carbohydrate count or other data about a meal from an image of the meal. For example, the bolus application 1134 (or other suitable application in communication with the bolus application 1134) can execute image recognition and / or image classification algorithms to identify one or more foods depicted in the image. The bolus application 1134 or other suitable application can estimate the quantity of one or more foods, for example, from the size of the food depiction (e.g., relative to the size of other object depictions in the image). The bolus application 1134 or other suitable application can access a database indicating the nutritional content of detected foods, e.g., in detected quantities.

[0247] In act 1406, the bolus application 1134 determines the meal component of the bolus dose. For example, the bolus application 1134 determines the amount of insulin that will cover the meal described by the meal data in any suitable manner, including those described herein. In some examples, the bolus application 1134 utilizes an equation such as equation [2] above.

[0248] In some examples, the bolus application utilizes a physiological model of the recipient 1101 to determine the dietary components of a bolus dose. For example, the bolus application 1134 can train the physiological model using previous glucose concentration data describing the recipient 1101 and previous meal data describing one or more meals ingested by the recipient 1101 when the previous glucose concentration data was collected. Other training data that can be used by the bolus application 1134 to train the physiological model can include bolus dose data indicating past bolus doses received by the recipient, as well as other data describing the recipient 1101, such as blood parameters, anthropometric (e.g., body size) values, the recipient's gut flora type, etc.

[0249] In operation 1408, the bolus application 1134 determines a correction component for the bolus dose. The correction component can be the bolus dose minus the meal component. Consider an example where the bolus dose is 8 units and the meal component is 6 units. In this case, the correction component is 2 units. In an example where the meal component is equal to the bolus dose, the correction component is zero. In an example where the meal component is greater than the bolus dose, the correction component is negative.

[0250] In operation 1410, the bolus application 1134 determines a glucose correction for the bolus dose. The glucose correction is the reduction to the recipient's 1101 glucose concentration due to the bolus dose. The glucose correction may be determined using a formula such as equation [1] above, or in any other suitable manner. In instances where the correction component is negative, the glucose correction may indicate that the recipient's glucose concentration will increase rather than decrease after the bolus dose.

[0251] In some examples, process flows 1300 and / or 1400 can be performed while also taking into account basal insulin in the recipient. For example, bolus application 1134 can receive basal dose data describing one or more basal doses received by the recipient. The bolus application 1134 can, for example, modify the meal component and / or correction component of the determined bolus effect data in light of the basal dose data.

[0252] FIG. 15 illustrates an exemplary screen 1500 of the bolus application user interface 1103 showing bolus effect data. In the example of FIG. 15, the bolus application 1134 is configured to determine bolus effect data including an estimated future glucose value and an estimated glucose trace. The estimated future glucose value is determined in any suitable manner. In some examples, the bolus application 1134 determines the estimated future glucose value by considering a meal component and a correction component of the bolus dose and the recipient's current glucose concentration, as provided by the analyte sensor system 1112. For example, the bolus application 1134 may predict the estimated future glucose value as the current glucose concentration minus the correction component. The screen 1500 includes a display 1502 of the estimated future glucose value, where the exemplary display 1502 is a text statement of the estimated future glucose value. In this example, the display 1502 also indicates the time (e.g., one hour from now) of the estimated future glucose value. This time may be determined, for example, based on the insulin action time of the bolus dose and / or an estimate of how long it will take the recipient 1101 to eat a meal.

[0253] In some examples, the bolus application 1134 determines an estimated future glucose trace. The estimated future glucose trace can be determined, for example, based on an estimate of the insulin action time of the bolus dose and / or the time it will take the recipient 1101 to eat a meal. In the example of FIG. 15, the actual glucose concentration trace 1504 shows the past glucose concentration (e.g., previously measured) for the recipient 1101, and the estimated future glucose concentration trace 1506, shown as a dashed line.

[0254] In some examples, the bolus application uses a case-based reasoning technique to determine one or more bolus doses for a recipient. Case-based reasoning techniques, such as the Advanced Bolus Calculator for Diabetes by Imperial College of London or the ABC4D method, determine bolus configuration parameters for a bolus dose by comparing the recipient's current condition, referred to as case parameters, to a set of stored cases, where the stored cases describe previously administered bolus doses. The stored cases include parameter data describing the conditions of the previously administered bolus doses, treatment data describing the previously administered bolus doses, and outcome data describing the recipient's condition after the previously administered bolus doses.

[0255] According to the case-based reasoning approach, the recipient provides current case parameter data indicating the parameters of the desired bolus dose. The current case parameters can include data regarding the recipient's glucose concentration, other data regarding the recipient, and (if the bolus includes a meal component) data regarding the meal associated with the bolus dose. The data regarding the recipient's glucose concentration can be determined using the analyte sensor system described herein and can include the current glucose concentration as well as previous glucose concentrations (e.g., glucose concentration from 30 minutes prior, glucose concentration from one hour prior, etc.). The other data regarding the recipient can include other physiological descriptors of the recipient that may affect the recipient's physiological response to insulin, including, for example, data regarding recent exercise, data regarding recent alcohol consumption, data regarding the recipient's menstrual cycle, etc. The data regarding the relevant meal can include, for example, the carbohydrate content of the meal (e.g., grams of carbohydrates) and other nutritional information regarding the meal, including the content of non-carbohydrate nutritional elements such as protein, fat, and salt.

[0256] The current case parameter data is compared with the parameter data for the stored case to select the closest previous case. For example, Manhattan distance, weighted arithmetic mean, Euclidean distance, Mahalanobis distance, dynamic time warping distance change, or other suitable method for determining the difference between the current case parameter data and the case parameter data of the stored case. In some instances, the calculated bolus is selected to match the treatment data from the closest previous case. Once the bolus dose is administered, the recipient can be monitored to generate outcome data for the current case. The current case, including the case parameters, treatment data, and outcome, can then be stored as a new stored case.

[0257] While case-based reasoning can produce positive results, challenges remain. For example, because case-based reasoning relies on stored cases, its accuracy and, in some cases, even operability, depend on having a large and diverse set of stored cases. Furthermore, due to different recipient physiologies, different recipients respond differently to different physiological or contextual factors, such as stress, alcohol, and exercise. Therefore, it may be desirable to generate stored cases from a single recipient. As a result, case-based reasoning approaches may produce inferior results or even fail entirely until a large and diverse set of stored cases is generated. Furthermore, even with a large stored case set, case-based reasoning techniques may perform poorly or fail if a recipient encounters a new or unusual case that does not perfectly match the stored cases.

[0258] Another challenge associated with case-based reasoning is that it is often desirable for stored cases to include outcome data showing a recipient's glucose concentration and / or other factors over an extended period of time, often several hours. However, in practice, it is common for a recipient to eat a meal and / or receive a subsequent bolus dose within hours of a previous bolus dose. When such intervening events occur, the outcome data for the previous bolus dose may be corrupted, preventing the previous bolus dose from forming the basis for a new stored case. This can make the process of generating a large, diverse set of stored cases longer and more difficult.

[0259] 16 is a diagram illustrating an example environment 1600 demonstrating the use of a bolus application 1634 to apply an example case-based reasoning technique. In the example of FIG. 16, the bolus application 1634 is programmed to modify the bolus configuration parameters of the closest reference case to generate a bolus dose for a recipient 1601.

[0260] In this example, a recipient 1601 utilizes a computing device 1602 to execute a bolus application 1634. The computing device 1602 can be any suitable computing device, such as, for example, a medical device 108, a user computing device 132, a tablet computing device 114, a smart pen 116, a smart device 112, a medical device 122, a computing device 118, a remote terminal 128, and / or a server system 126.

[0261] Computing device 1602 can include and / or be in communication with analyte sensor system 1612 and delivery system 1614. Analyte sensor system 1612, similar to analyte sensor system 102, can detect an analyte at recipient 1601, such as the recipient's 1601 glucose concentration. Delivery system 1614 is configured to deliver a bolus dose to recipient 1601. For example, delivery system 1614 can be or include an insulin pen, an insulin pump, or other suitable delivery system.

[0262] 16, the bolus application 1634 accesses current case parameter data 1622. The current case parameter data 1622 can include data describing the recipient 1601 and, optionally, data about the meal associated with the requested bolus. The data about the recipient 1601 can include current and / or historical glucose data received from the analyte sensor system 1612. The data about the recipient 1601 can also include physiological descriptors, such as, for example, data about recent exercise, data about recent alcohol consumption, data about the recipient's menstrual cycle, etc. Other data about the recipient 1601 can include data about the recipient's weight, age, height, body mass index (BMI), etc. The data about the associated meal can include, for example, the carbohydrate content of the meal (e.g., grams of carbohydrates) and may also include other nutritional information about the meal.

[0263] The bolus application 1634 compares the current case parameter data 1622 to the set of reference cases 1620. This may include, for example, finding the closest reference case 1622, where the closest reference case 1622 is the reference case 1622 having reference case parameter data that has the shortest distance to or least difference from the current case parameter data 1622. The distance or difference between the current case parameter data 1622 and the closest reference case 1622 parameter data may be found using any suitable method, including, for example, Manhattan distance, weighted arithmetic mean, Euclidean distance, Mahalanobis distance, dynamic time warp distance, etc.

[0264] The bolus application 1634 can also generate a therapy modification factor 1624 based on the distance or difference between the current case parameter data and the parameter data of the closest reference case. The therapy modification factor 1624 includes one or more modifications applied to the therapy data of the closest reference case 1622. For example, the therapy data of the closest reference case can include various bolus configuration parameters, such as ISF, ICR, etc. The therapy modification factor 1624 includes data describing how to modify one or more of the bolus configuration parameters. For example, the therapy modification factor 1624 can include one or more multipliers applied to each bolus configuration parameter of the closest reference case 1622. The bolus application 1634 applies the therapy modification factor to the bolus configuration parameters of the closest reference case to determine therapy data 1626 for the current case. The therapy data 1626 for the current case can be used to generate a bolus dose for the recipient 1601. The generated bolus dose can be provided to the recipient via a user interface of the computing device 1602. In some examples, the generated bolus dose is provided directly to a delivery system 1614 that provides the bolus dose to the recipient 1601 .

[0265] 17 is a flowchart illustrating an example of a process flow 1700 that may be performed by the bolus application 1634 to determine a bolus dosage for the recipient 1601. At operation 1702, the bolus application 1634 receives current case parameter data. As described herein, this may include information about the recipient 1601, including current and / or previous glucose concentration data received from the analyte sensor system 1612, as well as data indicating recent exercise, recent alcohol intake, etc. In some examples, the bolus application accesses previously received and stored data describing the recipient 1601, such as weight, BMI, menstrual cycle status, etc. Additionally, in some examples, the bolus application 1634 is configured to receive an image of a meal associated with the bolus and derive nutritional information about the meal from the image. The image may be captured, for example, using a camera or other image sensor in the delivery system 1614.

[0266] In operation 1704, the bolus application 1634 selects the closest reference case. This may include comparing the current case parameter data to case parameter data of one or more reference cases describing bolus doses previously administered to the recipient 1601. The closest reference case may be the reference case having case parameter data that differs least from the current case parameter data. Difference may be measured in any suitable manner, including, for example, Manhattan distance, weighted arithmetic mean, Euclidean distance, Mahalanobis distance, change in dynamic time warping distance, etc.

[0267] In operation 1706, the bolus application 1634 determines a therapy modification factor that is applied to the therapy data of the closest reference case to generate the current case therapy data. In some examples, the therapy modification factor is generated using Bayesian estimation techniques. In other examples, the bolus application 1634 trains a model, such as a regression model, to relate therapy data, including bolus configuration parameters, from the closest reference case to the corresponding therapy data of the current case.

[0268] At operation 1708, the bolus application 1634 applies the therapy modification factor determined in operation 1706 to the therapy data of the most recent reference case to determine therapy data for the current case. In some examples, the therapy modification factor includes a multiplier or set of multipliers applied to the bolus configuration data included in the most recent reference case therapy data. Thus, generating therapy data for the current case may include applying a multiplier to the bolus configuration data of the reference case therapy data, such as the ISF or ICR. The bolus application 1634 may apply the current case therapy data to determine a current case bolus dose, as described herein, including, for example, with respect to Equations [1] and [2]. The current case bolus dose may be displayed to the recipient 1601, for example, on a screen of the computing device 1602. In other examples, the bolus application 1634 may provide the current case therapy data to the delivery system 1614 to configure the delivery system 1614 to provide a bolus dose to the recipient 1601.

[0269] At optional operation 1710, the bolus application 1634 monitors the outcome of the current bolus case. This may include, for example, receiving additional glucose concentration data from the analyte sensor system 1612 after the current case bolus dose has been applied. The monitored outcome data, in some examples, may be used to generate a new reference case, which may be added to a set of reference cases for future bolus determinations. Also, in some examples, the monitored outcome data may be used to change the treatment modifier and / or change the way the treatment modifier is generated. For example, if a machine learning model is used to determine the treatment modification factor, the monitored outcome data may be used as training data for retraining the model or to supplement the training data for retraining the model.

[0270] It will be appreciated that generating current case treatment data in this manner reduces the technique's reliance on a large and diverse set of stored cases. For example, process flow 1700 can provide suitably accurate results even when there are significant differences between the current case and the closest stored or reference case.

[0271] 18 is a flowchart illustrating an example of a process flow 1800 that may be performed by the bolus application 1634 when the difference between the current case and the closest reference case is too great to determine a suitably accurate bolus dose. For example, process flow 1800 illustrates an exemplary way in which the bolus application 1634 may perform operation 1704 of process flow 1700.

[0272] At operation 1802, the bolus application 1634 determines the reference case that has the smallest difference from the current case. This can be determined, for example, as described herein. At operation 1804, the bolus application 1634 determines whether the difference between the current case and the closest reference case is greater than a threshold. If no, the bolus application 1634 returns the determined closest reference case and can proceed as described at operations 1706, 1708, etc., of the process flow 1700.

[0273] A difference between the current case and the most recent reference case greater than a threshold value may indicate that a suitable therapy modification factor may not have occurred. In operation 1808, the bolus application 1634 determines a safe bolus dose for the recipient 1601 by applying an alternative bolus method. An alternative bolus method may include, for example, applying the therapy data of the most recent reference case and then reducing the determined bolus dose by a safety factor (e.g., 10%, 20%, etc.). In this way, the bolus application 1634 determines a bolus dose that, if the bolus dose is incorrect, tends to increase rather than decrease the recipient's glucose concentration. This is because high glucose concentrations can cause long-term health problems, while the adverse effects of low glucose concentrations are more immediately severe. In some examples, the alternative bolus method may include using any other bolus technique described herein, including, for example, the techniques described herein with respect to Equations [1] and [2]. In some examples, the safe bolus dose is provided to the recipient 1601 via the computing device 1602 and / or to the delivery system 1614 so that the bolus dose is delivered to the recipient 1601.

[0274] At act 1810, the bolus application 1634 monitors outcome data for the bolus dose determined at act 1808, for example, as described herein. At act 1812, the bolus application 1634 uses the current case parameter data, outcome data. The treatment data for the new reference case can be based on the bolus configuration parameters used to determine the safe bolus at act 1808. For example, if the monitored data indicates an acceptable outcome, the bolus configuration parameters that would produce the same safe bolus can be accessed or determined and stored as the treatment data for the new reference case. If the monitored data indicates an unacceptable outcome, the bolus application 1634 modifies the bolus configuration parameters used to generate the safe bolus.

[0275] As mentioned above, one challenge in implementing case-based reasoning in bolus calculations is that an intervening event may prevent a new stored case from occurring. For example, referring to FIG. 18, if an intervening event (e.g., a new meal or a new bolus administration) occurs during monitoring in operation 1810, the bolus application 1634 may not obtain a complete set of outcome data.

[0276] 19 is a flowchart illustrating an example of a process flow 1900 that may be performed by the bolus application 1634 when an intervening event occurs during the monitoring of outcome data for a potential new reference case or a stored case. Process flow 1900 may be performed in case-based techniques such as those described with respect to FIGS. 16 and 17, where a treatment modification factor is used to modify the treatment data of the reference case to more closely match the current case. Process flow 1900 may also be utilized in other case-based reasoning techniques, where, in some instances, the treatment data of the closest stored case is not modified.

[0277] At act 1902, the bolus application 1634 monitors outcome data for potential new stored cases. The potential new stored cases may be reference cases for use in configurations similar to those described herein in FIGS. 16-18 and / or new stored cases for other implementations of case-based bolus technology. At act 1904, the bolus application 1634 determines whether an intervening event occurs before sufficient outcome data is collected. An intervening event may occur, for example, if the recipient 1601 receives a subsequent bolus dose (e.g., a correction bolus dose and / or a subsequent meal bolus dose). If no intervening event occurs, the bolus application 1634 generates a new stored case at act 1910, for example, as described herein.

[0278] If an intervening event occurs in operation 1904, the bolus application 1634 identifies the closest stored case. The closest stored case is the stored case that is closest to the potential new stored case. The closest stored case can be found, for example, by comparing the potential new stored case to previously stored cases, as described herein. In some examples, the closest stored case is determined using case parameter data, case treatment data, and incomplete case outcome data (e.g., incomplete due to an intervening event). For example, case definition data such as mealtime glucose levels and trends, meal volume, and mealtime IOB can be considered to determine the closest. Also, in some examples, glucose level data can be used to determine the closest stored case, and the glucose level data considered is limited to the data available in both the currently considered case and the stored case. For example, if the current glucose level data is similar to the stored case up to the time of the intervening event, data gap, or data artifact, the stored case can be considered a close case. In some examples, distance methods that can be used to identify the closest stored case taking into account intervening events include Manhattan distance, weighted arithmetic mean, Euclidean distance, Mahalanobis distance, dynamic time warping distance variation, etc.

[0279] At operation 1908, the bolus application 1634 supplements the incomplete outcome data of the potential new stored case with the most recent stored case. In some examples, this includes copying outcome data from the most recent stored case to the potential new stored case. For example, if an intervening event occurs one hour after the bolus administration of the potential new stored case and the total monitoring period of the new stored case is two hours, the outcome data from the most recent stored case, beginning one hour after the bolus administration and extending through two hours after the bolus administration, may be added to the outcome data of the potential new stored case that was captured before the intervening event. This may generate a complete set of outcome data for the potential new stored case, which can be used as the stored case.

[0280] In some examples, outcome data from the closest stored case is modified before being added to the outcome data of the potential new stored case. For example, the outcome data may be scaled, smoothed, and / or otherwise modified to more closely match the potential new stored case. For example, the bolus application 1634 may utilize interpolation to fill in gaps in the data between the closest stored case and the potential new stored case. Also, in some examples, the bolus application 1634 may remove continuous glucose sensor artifacts (e.g., resulting from erroneous glucose readings).

[0281] In some examples, the techniques and devices described herein with respect to Figures 16-19 may take into account one or more basal dosages for a recipient. For example, information regarding one or more recent basal dosages may be part of the parameter data describing one or more cases. Also, in some examples, treatment data associated with a case may specify changes to a basal dosage for a recipient.

[0282] In some examples, the bolus application can be programmed to analyze the glucose concentration data in light of the bolus dose to determine a recommended action for the recipient, also referred to herein as a recipient action. For example, the bolus application can be programmed to use the glucose concentration data and the bolus dose data to predict a hypoglycemic or hyperglycemic episode for the recipient. When this occurs, the bolus application can be programmed to recommend a recipient action to treat the episode (e.g., a correction bolus to treat the hyperglycemic episode or a snack to treat the hypoglycemic episode). In some examples, the bolus application is programmed to use the glucose concentration data and the bolus dose data to determine optimizations for the recipient's bolus configuration parameters and / or optimizations for the recipient's basal dose. Also, in some examples, the bolus application is programmed to provide a graphical user interface to the recipient that includes a trace of the recipient's glucose concentration and an indication of when meal and / or correction bolus doses were received.

[0283] In many of these instances, however, it is desirable for the bolus application to determine when a bolus dose is administered and to distinguish between a meal bolus, a correction bolus, and a mixed meal and correction bolus. For example, if the bolus application recommends a change in the bolus configuration parameters used by the recipient at lunch, it is desirable for the bolus application to identify the meal or mixed bolus doses received by the recipient at lunch and correlate the bolus doses with the glucose concentration data. Whether a change in glucose concentration indicates an impending hyperglycemic or hypoglycemic episode depends on whether the change in glucose concentration occurs close in time to the bolus administration.

[0284] When a bolus application calculates a bolus dose for a recipient, for example, as described herein, the bolus application may have a priori information regarding the bolus dose to be administered to the recipient, including the approximate time of the bolus dose, the type of bolus dose, etc. However, if the recipient does not use the bolus application to calculate the bolus dose, the bolus application may lack this a priori knowledge regarding the bolus dose, which may limit the ability and / or effectiveness of the bolus application in determining recipient behavior or providing a graphical user interface, as described herein.

[0285] Various examples address these and other issues, for example, by implementing a classification model to derive bolus dose data from glucose concentration data. Figure 20 is a diagram illustrating an example environment 2000 demonstrating the use of a bolus application 2034 that executes a classification model 2020 to classify bolus doses. In this example, a recipient 2001 utilizes a computing device 2002 to execute the bolus application 2034. The computing device 2002 can be any suitable computing device, such as, for example, a medical device 108, a user computing device 132, a tablet computing device 114, a smart pen 116, a smart device 112, a medical device 122, a computing device 118, a remote terminal 128, and / or a server system 126.

[0286] The computing device 2002 can include and / or be in communication with an analyte sensor system 2012 and a delivery system 2014. The analyte sensor system 2012, similar to the analyte sensor system 102, can detect an analyte at the recipient 2001, such as the recipient's 2001 glucose concentration. The delivery system 2014 is configured to deliver a bolus dose to the recipient 2001. For example, the delivery system 2014 can be or include an insulin pen, an insulin pump, or other suitable delivery system. The bolus application 2034 generates a bolus application user interface 2003 that is provided to the recipient 2001. The bolus application user interface 2003 can include visual and / or auditory elements to provide information to and / or receive information from the recipient 2001.

[0287] In the configuration of FIG. 20 , the bolus application 2034 receives glucose concentration data from the analyte sensor system 2012 and uses the glucose concentration data to implement the classification model 2020. The classification model can be trained to classify a bolus dose, for example, as a meal bolus, a correction bolus, or a combination of a meal bolus and a correction bolus. In some examples, the bolus application 2034 receives an indication that a bolus dose has been administered to the recipient 2001. For example, the delivery system 2014 can provide an indication that a bolus dose has been administered, and in some examples, can indicate the size of the bolus dose. Also, in some examples, the recipient 2001 can indicate to the bolus application 2034 that a bolus dose has been administered, and optionally the size of the bolus dose. In other examples, the bolus application 2034 detects a bolus dose without receiving an indication of the bolus dose from the recipient 2001 or the delivery system 2014.

[0288] The classification model 2020 can be any suitable type of machine learning model configured to provide a classification of things or events. For example, the classification model can be or include a logistic regression model or a linear classifier model such as a naive Bayes classifier, a nearest neighbor model, a support vector machine (SVM) model, a decision tree model, a boosted tree model, a random forest model, a neural network model, etc. In some examples, the classification model 2020 is a logistic regression model with an L2 penalty.

[0289] Glucose concentration data describing the glucose concentration at the recipient 2001 can be input into the classification model 2020. The glucose concentration data can be received directly from and / or derived from the analyte sensor system 2012. Exemplary glucose concentration data can include the rate of change of the recipient's glucose concentration at various intervals before and / or after the bolus administration, including, for example, 120 minutes before the bolus administration, 60 minutes before the bolus administration, 30 minutes before the bolus administration, at the time of the bolus administration, 30 minutes after the bolus administration, 60 minutes after the bolus administration, 90 minutes after the bolus administration, etc.

[0290] Other inputs to the classification model 2020 can include data regarding current and / or past bolus doses for the recipient 2001, such as the size of the bolus divided by the glucose concentration at that time, the size of the bolus divided by the smallest bolus dose in a recent period (e.g., the last 14 days), the size of the bolus divided by the largest amount of insulin taken in a recent period (e.g., the last 7 days), the size of the bolus minus the average or mean bolus dose in a recent period (e.g., the last 7 days), and / or the difference between the glucose concentration at the time of the bolus and the average or median glucose concentration in a recent period (e.g., the last 24 hours, the last 72 hours, the last 3 days, etc.), etc. In some examples, the difference can have a positive or negative sign, with the signed distance indicating the direction relative to the median glucose concentration. For example, if the sign of the distance is positive, the glucose concentration at the time of the bolus is greater than the mean or median glucose concentration, making the bolus more likely to be a correction dose. In some examples, the greater the positive difference between the glucose concentration and the mean or median glucose concentration, the more likely the bolus is a correction bolus. Also, in some examples, the time period over which the mean or median glucose concentration is obtained can be adjusted.

[0291] Another example of an input for the classification model 2020 is a two-coefficient polynomial quadratic equation that is fit to a period (eg, 30 minutes) of glucose concentration data around the time of the bolus administration.

[0292] The output of the classification model 2020 is an indication of the bolus category, which can be a correction bolus or a meal bolus. In some examples, the classification model 2020 is trained to also indicate a mixed bolus category for bolus doses that include both a meal component and a correction component. In other examples, the model 2020 is trained to classify mixed bolus doses typically as meal boluses.

[0293] The bolus application 2034 is programmed to determine recipient behavior based on one or more bolus dose categories as indicated by the classification model 2020. In some examples, the bolus application 2034 is programmed to determine recommended modifications to insulin administration (e.g., basal and / or bolus) for the recipient 2001. For example, if the recipient's meal bolus doses consistently cause the recipient's glucose concentration to be lower than a target glucose concentration, the bolus application 2034 may recommend that the recipient 2001 modify bolus configuration parameters, such as, for example, decreasing the ICR used to generate the bolus dose. In another example, if the recipient's glucose concentration is consistently above or below a target glucose concentration before a meal bolus or mixed bolus dose is administered, the bolus application 2034 may be programmed to recommend that the recipient 2001 modify the basal dose. If the recipient 2001 receives insulin by multiple injections daily, this may include increasing or decreasing the regular basal dose. If the recipient 2001 receives insulin from an insulin pump, this may include modifying the basal delivery profile of the insulin pump. Figure 20 shows an example screen 2024 of the bolus application user interface 2003, including a prompt to the recipient 2001 to take a recipient action involving changing an insulin administration configuration parameter. In this example, the recommended recipient action is to increase the recipient's basal dose by one unit.

[0294] In some examples, the bolus application 2034 is programmed to predict a hyperglycemic or hypoglycemic episode using one or more bolus dosage categories determined using the classification model 2020. For example, if the recipient 2001 receives a correction bolus but the recipient's glucose concentration continues to rise after the correction bolus (e.g., one hour after the correction bolus), the bolus application 2034 can detect a current or predicted hyperglycemic episode and instruct the recipient 2001 to take recipient action to treat the hyperglycemic episode. Similarly, if the recipient 2001 receives a meal bolus but the recipient's glucose concentration drops after the meal bolus (e.g., one hour after the meal bolus), the bolus application 2034 may detect a hypoglycemic episode. The bolus application 2034 can instruct the recipient 2001 to treat the hypoglycemic episode. FIG. 20 shows an exemplary screen 2026 of the bolus application user interface 2003 that may be displayed to the recipient 2001 to instruct the recipient 2001 to treat a predicted hypoglycemic episode.

[0295] The bolus application 2034 is also programmed to, in some examples, provide the recipient 2001 with a graphical user interface showing different categories of bolus doses in conjunction with glucose concentration data. For example, FIG. 20 also includes an exemplary screen 2028 of the bolus application user interface 2003, which includes a trace of the recipient's 2001 glucose concentration. In screen 2028, glucose concentration is shown on the vertical axis and time is shown on the horizontal axis. As shown, an exemplary meal bolus ("Meal") and an exemplary correction bolus ("Correction") are shown on the trace as each bolus dose was administered.

[0296] 21 is a flowchart illustrating an example of a process flow 2100 that may be performed by the bolus application 2034 to utilize the classification model 2020 to determine a bolus dose category. At operation 2102, the bolus application 2034 accesses training data. The training data is data that includes at least glucose concentration data that is labeled to indicate whether the glucose concentration data corresponds to a bolus dose, when the bolus dose was administered, and, in some examples, which category of bolus dose was administered. In some examples, the training data also includes basal dose information that describes one or more basal doses received by the recipient or other subjects in the training data. The training data may describe only the recipient 2001, or, in some examples, may be collected from other subjects (e.g., different recipients). At operation 2104, the training data is used to train a classification model. The classification model 2020 can be trained in any suitable manner.

[0297] Acts 2102 and 2104 (shown in box 2101) may, in some examples, be performed on the same computing device 2002 that executes the classification model 2020, e.g., by performing the remainder of process flow 2100. However, in some examples, acts 2102 and 2104 in box 2101 may be performed by different computing devices. For example, training of the classification model 2020 (e.g., acts 2101) may be performed on the server system 126. The trained model may be provided to a computing device 2002 (e.g., a medical device 108, a user computing device 132, a tablet computing device 114, a smart pen 116, a smart device 112, a medical device 122, and / or a computing device 118), which can utilize the classification model 2020 trained as described herein.

[0298] In operation 2106, the bolus application 2034 receives test bolus data. The test bolus data includes at least glucose concentration data describing the recipient's 2001 glucose concentration at and / or around the time the recipient 2001 receives the bolus dose. The test bolus data, in some examples, also includes data indicating when the recipient 2001 received the bolus dose and / or, in some examples, the size of the bolus dose (e.g., the number of units of insulin delivered). The test bolus data may also include information regarding one or more basal doses received by the recipient 2001. In some examples, the bolus application 2034 is configured to determine when a bolus dose was administered from the glucose concentration data. For example, the bolus application 2034 can detect that a bolus dose was administered based on the rate of change (first derivative) and / or the change in rate of change (second derivative) of the glucose concentration data.

[0299] At act 2108, the bolus application 2034 applies the classification model to the test bolus data to determine a category of the test bolus. This may include, for example, providing the test bolus data as input to the classification model 2020 and receiving an output from the classification model 2020 indicating the category of the test bolus. In some examples where the classification model 2020 is or includes a logistic regression model with an L2 penalty, the classification model 2020 is configured such that a model output greater than 0.5 corresponds to a correction bolus and any other model output corresponds to a meal bolus. At act 2110, the bolus application 2034 selects a recipient action based on the bolus dose category determined at act 2108. At act 2112, the bolus application 2034 provides a prompt to the recipient 2001 for the recipient action determined at act 2110. Examples for determining a recipient action and providing a corresponding prompt are described herein, for example, with respect to FIG. 20.

[0300] 22 is a flowchart illustrating an example of a process flow 2200 that may be performed by the bolus application 2034 to determine a recommended recipient behavior based on the category of the test bolus determined using the classification model 2020. In operation 2202, the bolus application 2034 compares the test bolus data to the category data. The test bolus data includes data describing the test bolus, and in some examples, includes some or all of the data provided as input to the classification model 2020. The category data includes data describing the recipient 2001's response to the test bolus and other bolus doses in the same category.

[0301] At act 2204, the bolus application 2034 identifies differences between the test bolus data and the category data. For example, the bolus application 2034 may determine that the recipient's glucose concentration rose after a bolus of the same category or rose at a rate higher than typical. In another example, the bolus application 2034 may determine that the recipient's glucose concentration fell after a meal bolus if the recipient's glucose concentration typically rises (at least temporarily) after a meal bolus. At act 2206, the bolus application 2034 selects a recipient action based on the differences identified in act 2204. For example, if the recipient's glucose concentration is rising at a rate higher than typical for a bolus of the same category, the bolus application 2034 may recommend changes to bolus or basal configuration parameters that tend to lower the glucose concentration and / or actions recommended to treat the hyperglycemic episode. In another example, if the recipient's glucose concentration is declining at a rate greater than is typical for a bolus of the same category, the bolus application 2034 recommends changes to bolus or basal configuration parameters that tend to increase the glucose concentration and / or recommended actions to treat the hypoglycemic episode.

[0302] An exemplary bolus configuration parameter that may be modified by the bolus application based on one or more bolus dose categories is the insulin on board (IOB) parameter. IOB is the amount of active insulin present in the recipient's body when the bolus is administered. When a recipient receives a bolus in which IOB is present, it is desirable to reduce the bolus dose to account for the IOB. For example, bolus doses are often determined based on the recipient's current glucose concentration. However, when IOB is present, the IOB may tend to decrease the recipient's current glucose concentration. Therefore, it is desirable to reduce the bolus dose based on the recipient's current glucose concentration to account for the decrease in current glucose concentration caused by the IOB.

[0303] IOB can be taken into account by considering the IOB component when determining the bolus. The IOB component can be based on a model of insulin action (e.g., pharmacodynamics or pharmacokinetics), where the model of insulin action describes one or more previously administered insulin doses (e.g., bolus dose, basal dose, and / or combined basal / bolus dose). The insulin action time (IAT) can be a parameter of the model. The IAT is the amount of time insulin from a previous dose remains active in the body. In reality, insulin action may not be constant across the IAT. For example, after a recipient receives an insulin dose, the recipient's body may initially rapidly metabolize the received insulin and glucose in the recipient's blood, with the metabolic rate slowing over time. The IOB component can be based on a model of insulin action relative to the IAT. Such a model may represent the decline in IOB over time using a suitable curve, such as a linear curve, a cumulative lognormal curve, a linear-corrected lognormal curve, etc. In some examples, the IOB component is considered (e.g., subtracted from) both the meal component (if present) and the correction component (if present). In some instances, the IOB component is considered (eg, subtracted from) the correction component, but not the dietary component.

[0304] However, correctly modeling the IOB to generate the IOB components can be challenging. Different recipients process insulin and glucose in different ways. Moreover, even the same recipient's insulin and glucose processing can change over time and / or under different conditions. Various exemplary configurations address this and other issues by determining IOB parameter corrections using glucose concentration data and bolus data indicative of one or more bolus doses received by the recipient.

[0305] 23 is a diagram illustrating an example environment 2300 demonstrating the use of a bolus application 2334 to modify insulin on-board (IOB) parameters. In this example, a recipient 2301 utilizes a computing device 2302 to execute the bolus application 2334. The computing device 2302 can be any suitable computing device, such as, for example, a medical device 108, a user computing device 132, a tablet computing device 114, a smart pen 116, a smart device 112, a medical device 122, a computing device 118, a remote terminal 128, and / or a server system 126.

[0306] Computing device 2302 can include and / or be in communication with analyte sensor system 2312 and delivery system 2314. Analyte sensor system 2312, similar to analyte sensor system 102, can detect an analyte at recipient 2301, such as the glucose concentration of recipient 2301. Delivery system 2314 is configured to deliver a bolus dose to recipient 2301. For example, delivery system 2314 can be or include an insulin pen, an insulin pump, or other suitable delivery system.

[0307] In the example of FIG. 23 , the bolus application 2334 uses insulin dosage data and glucose concentration data to determine recommended changes to IOB parameters for the recipient 2301. The IOB parameters are parameters used to determine the IOB component of a bolus dose. For example, the IOB parameters may include parameters of an insulin action model, such as the type of model of insulin action, the shape of the curve modeling insulin action, or offset characteristics. The glucose concentration data describes the recipient's glucose concentration and may be received from the analyte sensor system 2312 as described herein. The insulin dosage data can include bolus data and / or basal data. The bolus data describes one or more bolus doses received by the recipient 2301, while the basal data describes one or more basal doses received by the recipient 2301. For example, the bolus data may indicate the time the recipient 2301 received a bolus dose, the type of bolus dose (e.g., correction, meal, mixed), and / or the size of the bolus dose (e.g., units of insulin).

[0308] The bolus application 2334 can receive and / or access insulin dosage data in any suitable manner. In some examples, the bolus application 2334 receives and / or derives insulin dosage data from a priori knowledge. For example, if the bolus application 2334 determines a bolus dose and / or a basal dose for the recipient 2301, the bolus application 2334 can store insulin dosage data describing the determined bolus dose. In some examples, the bolus application 2334 receives insulin dosage data from the delivery system 2314. For example, the delivery system 2314 can provide the bolus application 2334 with data describing the bolus dose delivered to the recipient 2301 by the delivery system 2314. In other examples, the bolus application 2334 derives some or all of the insulin dosage data from other data, such as glucose concentration data. For example, the bolus application 2334 can detect a bolus from glucose concentration data and can classify the bolus as described herein.

[0309] In some examples, the bolus application 2334 considers bolus data describing bolus doses affected by IOB. A bolus dose affected by IOB is a bolus dose affected by IOB, for example, from a previously received bolus dose and / or basal dose. The bolus application 2334 can identify a bolus dose affected by IOB by detecting a bolus dose received within a threshold time of another bolus dose. The threshold time can depend on the insulin action time (IAT). For example, a bolus dose received more than a threshold time (e.g., 1 hour or more, 3 hours or more, etc.) after a previous bolus may not or need not consider IOB because IOB may not have been present and therefore may not be considered by the bolus application 2334 when determining recommended changes to IOB parameters. Thus, when the bolus application 2334 considers bolus data, the bolus application 2334 may identify and utilize bolus data that describes a bolus dose that is within a threshold time of a previous bolus dose so that the correction bolus dose considered includes an IOB component.

[0310] In some examples, the bolus application 2334 takes into account correction bolus doses to determine recommended changes to IOB parameters. As described herein, a correction bolus is a bolus dose provided to correct a deviation between the recipient's current glucose concentration and a target glucose concentration. A correction bolus is typically taken after a meal, for example, if the recipient 2301 does not receive a meal bolus and / or if the recipient's blood glucose level unexpectedly rises after a meal bolus. Thus, correction boluses are typically affected by IOB. Thus, in some examples, the bolus application 2334 takes into account correction bolus doses selected from the bolus data to determine recommended changes to IOB parameters. In some examples, the bolus application 2334 takes into account correction bolus doses that are affected by IOB, for example, by identifying correction boluses received by the recipient 2301 within a threshold of previous bolus doses, to determine recommended changes to IOB parameters.

[0311] 23 includes a graphical display 2320 of insulin dosage data and glucose concentration data illustrating how the bolus application 2334 may determine recommended changes to IOB parameters. The graphical display 2320 is provided as an example. In some examples, the graphical display 2320 is shown to the recipient 2301 via the bolus application user interface. In other examples, the bolus application 2334 utilizes bolus data and glucose concentration data similar to that depicted numerically by the display 2320 (e.g., without rendering such a graphical display).

[0312] In the graphical display 2320, time is shown on the horizontal axis and glucose concentration is shown on the vertical axis. The dotted line shows a trace of glucose concentration over time. The graphical display 2320 shows a meal bolus (“Meal”) and a correction bolus (“Correction”). In this example, IOB from the meal bolus was present at the time of the correction bolus. The bolus application 2334 determines the behavior of the recipient's glucose concentration to determine the accuracy of the IOB component of the correction bolus. In the example shown in FIG. 23, the recipient's glucose concentration consistently drops after the bolus correction. If the drop is below the recipient's target glucose concentration, this may indicate that the IOB component is underestimating the IOB in the correction bolus, resulting in a higher correction bolus than necessary. To correct this, the bolus application 2334 can recommend modifying the IOB parameters to lower the IOB component.

[0313] 24 is a flowchart illustrating an example of a process flow 2400 that may be performed by the bolus application 2334 to generate recommended changes to IOB parameters. At act 2402, the bolus application 2334 accesses correction bolus data describing at least one correction bolus. At act 2404, the bolus application 2334 accesses meal bolus data describing at least one meal bolus dose received by the recipient 2301 prior to the correction bolus dose. In some examples, act 2404 is omitted, and the bolus application 2334 considers only the correction bolus data to determine the recommended changes to the IOB parameters. At act 2406, the bolus application 2334 accesses glucose concentration data describing the recipient's 2301 glucose concentration at or around the time of one or more boluses described in act 2402 and the data accessed in act 2404.

[0314] In act 2408, the bolus application 2334 determines changes to the IOB parameters based on the correction bolus data and glucose concentration data, and in some examples, the meal bolus data accessed in act 2404. Any suitable method can be used to generate the recommended changes to the IOB parameters. In some examples, the bolus application 2334 substitutes the actual glucose concentration into a correction bolus dose formula, such as equation [1] above. Holding the correction bolus dose equal to the actual correction bolus administered, the bolus application 2334 determines the actual IOB component. The actual IOB parameters can be found by determining changes to one or more IOB parameters that lead to an IOB component that matches or is similar to the actual IOB component. In some examples, a single IOB parameter or a limited set of IOB parameters may not produce a matching IOB component for all past bolus doses. If no match is found, the bolus application 2334 can be programmed to assign a cost to the difference between the actual IOB component (as observed by the recipient) and the IOB component determined with a particular IOB parameter in the set of IOB parameters. The distance can be determined using the squared difference between the IOB components or in any other suitable manner. The IOB parameters for use by the bolus application 2334 can be determined to minimize the total cost over the set of correction boluses considered.

[0315] In some examples, the bolus application 2334 determines changes to IOB parameters by, at least in part, identifying a post-bolus pattern of the recipient's 2301 glucose concentration over a set of considered bolus doses described by the bolus data. The set of considered bolus doses may include, for example, IOB-affected bolus doses, correction bolus doses, IOB-affected correction bolus doses, etc. A post-bolus pattern occurs when the recipient's glucose concentration behaves similarly over some or all of the considered bolus doses. A post-bolus pattern can be determined in any suitable manner. In some examples, the post-bolus pattern is determined by finding the mean, median, or other aggregation of the recipient's 2301 glucose concentration after the considered bolus dose. A post-bolus pattern may be observed at any suitable time after the considered bolus dose, including, for example, 30 minutes, 60 minutes, 90 minutes, etc.

[0316] Consider an example where the post-bolus pattern indicates that the recipient's 2301 glucose concentration is below the recipient's target glucose concentration (e.g., 20 minutes after the considered bolus delivery), which may indicate that the IOB component of the bolus delivery is underestimating the IOB for the recipient. In this example, the bolus application 2334 can recommend a change to the IOB parameters that tends to increase the IOB component of the determined bolus. Consider another example where the post-bolus pattern indicates that the recipient's 2301 glucose concentration is above the recipient's target glucose concentration 35 minutes after the considered bolus delivery. In this example, the bolus application 2334 can recommend a change to the IOB parameters that tends to decrease the IOB component of the determined bolus.

[0317] Exemplary IOB parameters include insulin action time (IAT) and various coefficients or other parameters that describe the shape of the IOB curve. For example, the bolus application 2334 may generate the IOB using a function that represents a curve, such as a cumulative lognormal distribution curve. The IOB parameters of such a function may include the mean and standard deviation of the normal distribution associated with the lognormal distribution.

[0318] Also, in some examples, the changes to the IOB parameters may depend on when the post-bolus pattern occurs (e.g., how long after the bolus administration) or the size of the bolus. These and other factors may affect the size of the change in one or more IOB parameters, the selection of one or more IOB parameters to change, etc.

[0319] Determining an accurate bolus dose for a recipient is a consistent challenge. For example, as described herein, the appropriate level of insulin for a bolus dose to achieve a target glucose concentration depends on many factors, including the recipient's current blood glucose, the meal (if any) planned to be eaten, the recipient's activity level, alcohol intake, etc. Additionally, the appropriate level of insulin for a bolus dose may depend on physiological factors that are difficult to measure directly. Various examples address these and other issues by utilizing a bolus application programmed to determine a bolus dose for a recipient while taking trend adjustment into account. According to trend adjustment, the bolus application uses glucose concentration data received from an analyte sensor system to determine a rate of change (ROC) of glucose concentration for the recipient. The bolus application uses the ROC of the glucose concentration to determine a predicted glucose concentration for a future time after a prediction period. The bolus application then determines a bolus dose for the recipient, including a trend component that corrects for the predicted glucose concentration, as described herein.

[0320] 25 is a diagram illustrating an example environment 2500 demonstrating the use of a bolus application 2534 to determine a bolus dosage for a recipient 2501 using trend adjustment, as described herein. In this example, the recipient 2501 utilizes a computing device 2502 to execute the bolus application 2534. The computing device 2502 can be any suitable computing device, such as, for example, a medical device 108, a user computing device 132, a tablet computing device 114, a smart pen 116, a smart device 112, a medical device 122, a computing device 118, a remote terminal 128, and / or a server system 126.

[0321] Computing device 2502 can include and / or be in communication with analyte sensor system 2512 and delivery system 2514. Analyte sensor system 2512, similar to analyte sensor system 102, can detect an analyte at recipient 2501, such as the glucose concentration of recipient 2501. Delivery system 2514 is configured to deliver a bolus dose to recipient 2501. For example, delivery system 2514 can be or include an insulin pen, an insulin pump, or other suitable delivery system.

[0322] In the example of FIG. 25 , the bolus application 2534 receives bolus request data describing a requested bolus dose. (In some examples, the bolus application 2534 determines a combined basal / bolus dose and / or determines a basal dose in addition to a requested bolus dose.) The bolus application 2534 adjusts for the glucose concentration trend by considering a trend component of the bolus dose, as described herein. As described elsewhere herein, the bolus dose can be determined taking into account a correction component and, if the bolus dose is associated with a meal component. An example for determining the correction component is provided by Equation [1] herein, and an example for determining the meal component is provided by Equation [2] herein. Also, as described herein, the total bolus dose can be found by summing the correction component and the meal component (if present).

[0323] 25 includes a graphical display 2520 to illustrate how the bolus application 2534 uses the trend component to determine a bolus dose. In some examples, the bolus application 2534 generates or renders a graphical display similar to the graphical display 2520, for example, to be displayed on the display of the computing device 2502. However, in other examples, the bolus application 2534 utilizes some or all of the concepts described herein without rendering a graphical display similar to the graphical display 2520.

[0324] Graphical display 2520 shows a glucose concentration trace plotted on a graph where the horizontal axis corresponds to time and the vertical axis corresponds to glucose concentration. The graph shows a target glucose concentration range ("Target Range") and a target glucose concentration value ("Target"). In this example, the glucose concentration trace starts below the target glucose concentration range and begins to rise.

[0325] At the indicated time ("BD Required"), the bolus application 2534 receives a request to determine a bolus dose for the recipient 2501. The request is accompanied by, in some examples, meal data describing the meal associated with the bolus dose (if the bolus dose includes a meal component). The meal data may include the number of carbohydrates in the meal, as described herein.

[0326] The bolus application 2534 receives glucose concentration data from the analyte sensor system 2512. The glucose concentration data may include glucose concentrations for the recipient 2501 at multiple different times. The bolus application 2534 utilizes the glucose concentration data to generate a glucose concentration rate of change (ROC) for the recipient 2501. The glucose concentration ROC indicates the change in glucose concentration per unit time (e.g., mg / dL / sec). A positive glucose concentration ROC may indicate that the recipient's 2501 glucose concentration is increasing, while a negative glucose concentration ROC may indicate that the recipient's 2501 glucose concentration is decreasing.

[0327] Using the glucose concentration ROC, the bolus application 2534 predicts from the recipient's 2501 current glucose concentration ("current GC") to generate a predicted glucose concentration for the recipient 2501 at a future time ("predicted GC"). The future time is after the current time, which is the time when a bolus dose is requested or scheduled to be administered. The future time is separated from the current time to become a prediction period ("prediction period"). The prediction period can be any suitable value. In some examples, the prediction period is between about 5 minutes and 60 minutes. In some examples, the prediction period is between about 10 minutes and about 40 minutes. In some examples, the prediction period varies depending on the characteristics of the recipient 2501. For example, the bolus application 2534 can use a first prediction period for recipients above a threshold age and a second, shorter prediction period for recipients below a threshold age. In some examples, a 20-minute prediction period is used for recipients 2501 under the age of 18, and a 30-minute prediction period is used for recipients 2501 18 or older.

[0328] The graphical representation 2520 shows the current glucose concentration (GC M ) and the target glucose concentration of the recipient 2501 (GC T 25 shows a correction ("Correction"), which is the difference between the correction and the insulin sensitivity value (ISF) for the recipient 2501. The correction may be used to generate a correction component of the bolus, for example, using the correction and an insulin sensitivity value (ISF) for the recipient 2501, for example, as shown in equation [1].

[0329] The glucose application 2534 can find the trend component, for example, as given by equation [3] below.

number

[0330] In equation [3], TC is the trend component. GC Mis the measured glucose concentration of the recipient 2501 (e.g., the current GC) and indicates the glucose concentration of the recipient 101 at or around the time the bolus dose is scheduled to be received. GC P is the predicted glucose concentration after the prediction period. Similar to equation [1], in equation [3], ISF is the insulin sensitivity value of the recipient 2501. The total bolus dose determined by the bolus application 2534 may be the sum or other suitable combination of the correction component, meal component (if present), and trend component.

[0331] 26 is a flowchart illustrating an example of a process flow 2600 that may be performed by the bolus application 2534 to determine a bolus dose for a recipient 2501 using a trend component. In operation 2602, the bolus application 2534 receives bolus dose request data describing a requested bolus dose. The bolus dose request data describes the bolus dose to be determined. For example, the bolus dose request data may include meal data describing a meal associated with the bolus dose. The bolus dose data may also indicate that a meal is not associated with the bolus dose (e.g., it is a correction bolus).

[0332] At operation 2604, the bolus application 2534 receives glucose concentration data from the analyte sensor system 2512. The glucose concentration data may be continuous glucose concentration data. For example, the glucose concentration data may include glucose concentration values ​​for the recipient 2501 over several times (e.g., at least two times). At operation 2606, the bolus application 2534 utilizes the glucose concentration data to determine a glucose concentration ROC for the recipient 1501. The glucose concentration ROC may be determined in any suitable manner. In some examples, the bolus application 2534 finds a best line between the glucose concentration values ​​for the recipient 2501 over two or more times. In other examples, the glucose concentration ROC is found by measuring two glucose concentration values ​​and taking the difference between the two glucose concentration values ​​over time. Other suitable techniques may also be used to find the glucose concentration ROC.

[0333] At act 2608, the bolus application 2534 determines a predicted glucose concentration at a future time, as described herein, where the future time is a prediction period after the current time. At act 2610, the bolus application 2534 determines a bolus dose using the predicted glucose concentration. For example, the bolus application 2534 can generate a trend component, e.g., as shown by equation [3]. The trend component can be summed with a correction component (e.g., determined according to equation [2]) and, if there is an associated meal, with a meal component (e.g., determined according to equation [1]).

[0334] In some examples, the bolus application 2534 is also configured to consider carbohydrate-on-board (COB) components. To utilize the carbohydrate-on-board components, the bolus application 2534 is configured to review bolus data describing previous bolus doses provided to the recipient 2501 and / or meals previously ingested by the recipient. The bolus data describing previous bolus doses can be received in any suitable manner, including those described herein. Also, in some examples, the recipient 2501 can provide meal data describing previously ingested meals. From the bolus data and / or meal data, the bolus application 2534 can determine a COB value, describing carbohydrates previously ingested but not covered by a previous bolus dose. The COB value can be converted to a COB component, for example, as shown in Equation [4] below.

number

[0335] In equation [4], COBC is the carbohydrate onboard component of the bolus dose. COB is the carbohydrate onboard value described above, which indicates carbohydrates previously consumed by the recipient 2501 but not covered by a previous bolus dose. ICR is the insulin to carbohydrate ratio for the recipient 2501. The COB component can be summed with other components (e.g., meal component, correction component, trend adjustment, insulin onboard, etc.) to generate the bolus dose.

[0336] In some instances, it may not be desirable to use trend adjustment in all circumstances to determine a bolus dose for the recipient 2501. Figure 27 illustrates another example of the process flow 2600 of Figure 26 with additional operations to omit the bolus trend component in some circumstances. For example, after determining the glucose concentration ROC in operation 2606, the bolus application 2534 may optionally determine whether the glucose concentration ROC is rising in operation 2702. If the glucose concentration ROC is rising, the bolus application may proceed to operation 2608, as described above. If the glucose concentration ROC is not rising, the bolus application 2534 may determine a bolus dose for the recipient 2501 in operation 2710, omitting the trend component (e.g., using only the correction component and meal component, if present).

[0337] Similarly, after determining the predicted glucose concentration in operation 2608, in optional operation 2704, the bolus application 2534 can determine whether the difference between the predicted glucose concentration and the current glucose concentration is less than a threshold amount. For example, if the predicted glucose concentration differs from the current glucose concentration by more than a threshold amount, it may indicate that the predicted glucose concentration is unreliable. Thus, the bolus application 2534 can determine a bolus dose for the recipient 2501 while omitting the trend component in operation 2710. In some examples, instead of omitting the trend component, the bolus application 2534 modifies the predicted glucose concentration to the maximum allowed value. For example, if the maximum difference between the current glucose concentration and the predicted glucose concentration is 50 mg / dL and the current glucose concentration is 150 mg / dL, the glucose application 2534 can set the predicted glucose concentration value to 200 mg / dL and determine the bolus using the trend component.

[0338] Another scenario in which it may not be desirable to use trend adjustment is when there has been a recent meal bolus or when the recipient has otherwise recently ingested food, for example, if they began eating a meal before receiving a bolus dose to cover the meal. In such a situation, all or part of the glucose concentration ROC may be due to meal fluctuations in glucose concentration, making the glucose concentration ROC less predictive of the recipient's future glucose concentrations. For example, the recipient's previous meal may cause the recipient's glucose concentration (and associated ROC) to be elevated.

[0339] Thus, in optional operation 2706, the bolus application 2534 may determine whether the recipient 2501 received a previous meal bolus within a threshold period (e.g., 30 minutes, 1 hour, 2 hours, etc.). For example, the bolus application 2534 may determine whether the bolus application 2534 provided a meal bolus determination within that time. In addition to, or instead of, determining whether a meal bolus determination has been provided within the threshold period, the bolus application 2534 may analyze the glucose concentration data to detect a previous bolus dose and / or characterize a previous bolus dose as a meal bolus, for example, as described herein. If a previous meal bolus is not detected within the threshold time, the bolus application 2534 proceeds to operation 2610.

[0340] In some examples, if act 2706 determines that there was a previous meal bolus within the threshold period, the bolus application may omit the trend component from the current bolus determination in act 2710. In other examples, the bolus application 2534 first determines whether the currently requested bolus dose includes a meal component in act 2708. If the currently requested bolus dose includes a meal component, the bolus application 2534 may omit the trend component in act 2710. If the currently requested bolus dose does not include a meal component, the bolus application 2534 may proceed to act 2610.

[0341] FIG. 28 illustrates an example environment 2800 showing a bolus application 2834 configured to generate glucose concentration alerts based on bolus data. For example, it may be desirable for a recipient 2801 to be alerted when their glucose concentration is outside a target range. For example, if the recipient's glucose concentration is above the target range, it may indicate a current or impending hyperglycemic episode. It may be desirable for the recipient 2801 to treat the hyperglycemic episode, for example, by receiving a correction bolus. Also, for example, if the recipient's glucose concentration is below the target range, it may indicate a current or impending hypoglycemic episode. It may be desirable for the recipient 2801 to treat the hypoglycemic episode, for example, by consuming food containing carbohydrates to increase the glucose concentration.

[0342] However, in various examples, the relationship between glucose concentration and the likelihood of a hyperglycemic or hypoglycemic episode depends on bolus data describing one or more recent bolus doses received by the recipient 2801. For example, it is common for a recipient's glucose concentration to rise when they eat a meal and then fall again after a meal bolus taken with the meal begins to take effect. Such a rise, in conjunction with the meal bolus, may not indicate a current or impending hyperglycemic event. Also, the recipient 2801 may sometimes forget to take a bolus before eating a meal. When this occurs, it may be desirable to catch the missed bolus dose early so that the recipient can take the bolus before their glucose concentration becomes dangerously high.

[0343] In various examples, these and other issues are addressed by configuring the bolus application 2834 to select a glucose concentration alert threshold for alerting the recipient 2801 based at least in part on the bolus data. The glucose concentration alert threshold is a glucose concentration level that, when exceeded, causes the bolus application 2834 to generate an alert 2820 to the recipient 2801 indicating a potential hypoglycemic or hyperglycemic episode. In some examples, the bolus application 2834 utilizes a hyperglycemic alert threshold and a hypoglycemic alert threshold. When the recipient's 2801 glucose concentration exceeds the hyperglycemic alert threshold, the bolus application 2834 generates an alert 2820 to the server indicating a current or impending hyperglycemic event. When the recipient's 2801 glucose concentration falls below the hypoglycemic alert threshold, the bolus application 2834 provides an alert 2820 indicating a current or impending hypoglycemic event.

[0344] 28, a recipient 2801 utilizes a computing device 2802 to execute a bolus application 2834. The computing device 2802 can be any suitable computing device, such as, for example, a medical device 108, a user computing device 132, a tablet computing device 114, a smart pen 116, a smart device 112, a medical device 122, a computing device 118, a remote terminal 128, and / or a server system 126.

[0345] Computing device 2802 can include and / or be in communication with analyte sensor system 2812 and delivery system 2814. Analyte sensor system 2812, similar to analyte sensor system 102, can detect an analyte at recipient 2801, such as the glucose concentration of recipient 2801. Delivery system 2814 is configured to deliver a bolus dose to recipient 2801. For example, delivery system 2814 can be or include an insulin pen, an insulin pump, or other suitable delivery system.

[0346] In the example of FIG. 28 , the bolus application 2834 receives glucose concentration data from the analyte sensor system 2812. The glucose concentration data indicates at least the current glucose concentration of the recipient 2801. The bolus application 2834 may also receive bolus data. The bolus data indicates at least one previous bolus dose provided to the recipient 2801. The bolus data may be received or accessed from any suitable source. In some examples, the bolus data is stored in a data storage device associated with the bolus application 2834, e.g., the computing device 2802. For example, the bolus data may include data regarding one or more previous bolus doses determined for the recipient 2801 by the bolus application 2834. In other examples, the bolus data is received from the recipient 2801, e.g., via a bolus application user interface. Also, in some examples, the bolus data is received from the delivery system 2814, e.g., based on a record of bolus doses provided to the recipient 2801 by the delivery system 2814.

[0347] Using the bolus data, the bolus application 2834 modifies the glucose concentration alert threshold. In some examples, the selected glucose concentration alert threshold is a hyperglycemia alert threshold. For example, if the recipient 2801 receives a meal bolus within a threshold period (e.g., hour, 2 hours, 4 hours, etc.), the bolus application 2834 may tend to increase the hyperglycemia alert threshold so that an alert 2820 is not sent to indicate a current or impending hyperglycemia episode until or unless the recipient's 2801 glucose concentration is higher than the level that would trigger the alert 2820.

[0348] Alternatively, if the recipient 2801 does not receive a meal bolus within a threshold period (e.g., 1 hour, 2 hours, 4 hours, etc.), this may indicate that the recipient 2801 is scheduled to eat a meal and has missed or is about to miss a meal bolus (e.g., eating a meal without receiving a corresponding bolus administration). Accordingly, the bolus application 2834 may lower the hyperglycemic alert threshold, such that an alert 2820 is sent to indicate a current or impending hyperglycemic episode at an earlier recipient's 2801 glucose concentration than would otherwise be the case.

[0349] In some examples, the bolus application 2834 utilizes insulin on-board (IOB) values ​​derived from the bolus data to determine one or more glucose concentration alert thresholds. The bolus application 2834 can determine the recipient's 2801 IOB value based on the bolus data. For example, the bolus application 2834 can consider the time the recipient 2801 received a recent bolus dose and the insulin action time (IAT) model described herein. The bolus application 2834 can set a hyperglycemic alert threshold based on the IOB. A higher IOB (e.g., above the IOB threshold) can cause the bolus application 2834 to increase the hyperglycemic alert threshold. For example, a higher IOB can indicate that the recipient's 2801 IOB is likely to lower the recipient's 2801 glucose concentration without further treatment, meaning that treatment of a current or impending hyperglycemic episode may not be advisable until a higher blood glucose level is received. Similarly, the absence of an IOB in the recipient 2801 may indicate a long time since the previous bolus, which may indicate that the recipient 2801 is about to eat a meal or may have already missed a meal bolus. Thus, a low IOB or lack of IOB may cause the bolus application 2834 to lower the hyperglycemia warning threshold. In some examples, the IOB may be utilized to modify the hypoglycemia warning threshold, which indicates when the recipient 2801 is at risk for a hypoglycemic event. For example, if there is a recent bolus or the current IOB is high (e.g., higher than the threshold), the hypoglycemia warning threshold may be increased because, in these conditions, residual insulin action would further lower glucose, putting the recipient at higher risk for a hypoglycemic episode.

[0350] Other factors that may be considered to determine the glucose concentration alert threshold may include past glucose patterns, contextual information, the recipient's food intake history or calculated carbohydrate onboard, and / or glucose change rate. For example, past glucose patterns may be considered to make the glucose concentration alert threshold more or less aggressive during times when an individual recipient is prone to high or low glucose levels. Contextual information, such as data describing the recipient's level of exercise or stress, may affect the likelihood of a hyperglycemic episode and may be considered accordingly. For example, if contextual information indicates that the recipient is at higher risk for a hyperglycemic episode, the bolus application 2834 may utilize a lower hypoglycemic alert threshold. The recipient's food intake history or calculated carbohydrate onboard may be used to raise the hypoglycemic alert threshold, for example, if the recipient has recently eaten or has carbohydrate onboard. The glucose change rate may be used to lower the hypoglycemic alert threshold, for example, when the current glucose change rate is high. In some examples, predicted glucose, which takes into account the current change rate, may be evaluated against the hypoglycemic alert threshold instead of the current glucose.

[0351] 29 is a flowchart illustrating an example of a process flow 2900 that may be performed by the bolus application 2834 to generate an alert based on bolus information for a recipient 2801. In operation 2902, the bolus application 2834 accesses glucose concentration data, for example, from the analyte sensor system 2812. In operation 2904, the bolus application accesses bolus data, for example, as described herein. For example, the bolus data may describe previous bolus doses and / or combined basal / bolus doses that the recipient 2801 has received.

[0352] In act 2906, the bolus application 2834 modifies the hyperglycemia warning threshold based on the bolus data. For example, if more than a threshold time has passed since the recipient 2801's last bolus administration and / or the IOB value is high, the bolus application 2834 may lower the hyperglycemia warning threshold. Alternatively, if less than a threshold time has passed since the recipient 2801's last bolus administration and / or the IOB value is high, the bolus application 2834 may raise the hyperglycemia warning threshold. Any suitable threshold may be used. In some examples, if less than a threshold time has passed since the last bolus administration and / or the IOB value is high, the hyperglycemia warning threshold may be between about 220 mg / dL and 280 mg / dL. In some examples, the threshold is about 250 mg / dL. In some examples, if more than a threshold time has passed since the last bolus administration and / or the IOB value is not high, the hyperglycemia warning threshold may be between about 160 mg / dL and about 200 mg / dL. In some instances, the threshold is about 180 mg / dL.

[0353] In act 2908, the bolus application 2834 determines whether the recipient's 2801 glucose concentration is higher than the hyperglycemia warning threshold determined in act 2906. If the glucose concentration is higher than the hyperglycemia warning threshold, the bolus application 2834 may provide a warning 2820 in act 2910. If the glucose concentration is not higher than the hyperglycemia warning threshold, the bolus application may not provide a warning 2820 in act 2912.

[0354] The various examples described herein for managing a bolus dose can be performed individually or, in some examples, together in any suitable combination. For example, FIG. 30 is a flowchart illustrating an example process flow 3000 that can be performed by a bolus application (e.g., bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H, 734, 1134, 1634, 2034, 2334, 2534, and / or 2834) to perform the various techniques described herein. It will be understood that any of the operations in process flow 3000 can be omitted and / or substituted, depending on the configuration. In other examples, the order of the operations in process flow 300 can be modified. For example, determining a bolus dose (operation 3004) and determining bolus dose effect data (3006) can be performed together or in reverse order. Other modifications are also contemplated.

[0355] In operation 3002, the bolus application determines bolus configuration parameters for determining a bolus dose for the recipient. This may be performed in any suitable manner, such as, for example, those described herein with respect to Figures 7-10. In some examples, the bolus application may directly query the recipient to provide the bolus configuration parameters. In some examples, the bolus application may start with a default set of bolus configuration parameters that are the same for all recipients and / or are based on the recipient's characteristics (e.g., size, weight, age, diabetes type, etc.).

[0356] In operation 3004, the bolus application determines a bolus dose for the recipient, for example, based on a request from the recipient. The determined bolus dose may be a correction bolus dose, a meal bolus dose, and / or a mixed bolus dose. A variety of different techniques may be used. In some examples, the bolus application implements the case-based reasoning techniques described herein with respect to FIGS. 16-19. In some examples, the bolus application implements the trend-adjusted techniques described herein with respect to FIGS. 25-27. In some examples, the bolus application implements a combination of the described techniques, for example, using a case-based reasoning technique that considers glucose concentration trends as a case parameter. In other examples, the bolus application can determine the bolus dose using application of a formula or set of formulas, such as Equation [1] and Equation [2] described herein. The determined bolus dose may be displayed to the recipient in a user interface and / or provided to a delivery device, as described herein.

[0357] In operation 3006, the bolus application determines bolus dose effect data, for example, as described herein with respect to Figures 11-15. As described herein, the bolus dose effect data can be provided to the recipient to allow the recipient to verify the correctness of the determined bolus dose before receiving the bolus dose.

[0358] In operation 3008, the bolus application corrects the bolus configuration parameters based on the glucose concentration data received after receiving the determined bolus dose. In some examples, this includes categorizing the bolus dose, as described herein with respect to Figures 20-22. In some examples, the bolus application also determines recipient behavior based on the categorization, as also described with respect to Figures 20-22. Examples illustrating modifying the bolus configuration parameters with respect to the IOB parameters are described herein with respect to Figures 23 and 24.

[0359] In operation 3010, the bolus application alerts the recipient of an event, for example, based on the glucose concentration data. The event can be a hyperglycemic or hypoglycemic episode and / or an indication for other recipient action, for example, as described herein with respect to FIGS. 28 and 29.

[0360] 31 is a block diagram illustrating a hardware architecture 3100 of a computing device in which a set of instructions or a sequence of instructions may be executed to cause a machine to perform any one of the example methodologies discussed herein. The hardware architecture 3100 may describe a variety of computing devices, including, for example, sensor electronics 106, peripheral medical devices 122, smart devices 112, tablet computing devices 114, etc.

[0361] The architecture 3100 may operate as a standalone device or may be connected (e.g., networked) to other machines. In a networked deployment, the architecture 3100 may operate in the capacity of either a server or a client machine in a server-client network environment, or may function as a peer machine in a peer-to-peer (or distributed) network environment. The architecture 3100 may be implemented in a personal computer (PC), a tablet PC, a hybrid tablet, a set-top box (STB), a personal digital assistant (PDA), a mobile phone, a web appliance, a network router, a network switch, a network bridge, or any machine capable of executing instructions (sequential or otherwise) that specify operations to be performed by the machine.

[0362] The exemplary architecture 3100 includes a processor unit 3102 including at least one processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both, a processor core, a compute node). The architecture 3100 may further comprise a main memory 3104 and a static memory 3106, which communicate with each other via a link 3108 (e.g., a bus). The architecture 3100 may further include a video display unit 3110, an input device 3112 (e.g., a keyboard), and a UI navigation device 3114 (e.g., a mouse). In some examples, the video display unit 3110, the input device 3112, and the UI navigation device 3114 are incorporated into a touch screen display. The architecture 3100 may further include a storage device 3116 (e.g., a drive unit), a signal generation device 3118 (e.g., a speaker), a network interface device 3120, and one or more sensors (not shown), such as a global positioning system (GPS) sensor, a compass, an accelerometer, or other sensors.

[0363] In some examples, the processor unit 3102 or another suitable hardware component may support hardware interrupts. In response to a hardware interrupt, the processor unit 3102 may, for example, pause its processing and execute an ISR, as described herein.

[0364] Storage device 3116 includes machine-readable medium 3122 having stored thereon one or more sets of data structures and instructions 3124 (e.g., software) that embody or are used by any one or more of the methodologies or functions described herein. The instructions 3124 may also reside, completely or at least partially, within main memory 3104, static memory 3106, and / or within processor unit 3102 during execution thereof by architecture 3100, with main memory 3104, static memory 3106, and processor unit 3102 also constituting machine-readable media.

[0365] Executable Instructions and Machine Storage Media Various memories (i.e., 3104, 3106, and / or memory of processor unit 3102) and / or storage devices 3116 may store a set of one or more instructions and data structures (e.g., instructions) 3124 embodied in or used by any one or more of the methodologies or functions described herein. These instructions, when executed by processor unit 3102, cause various operations to be performed to implement the disclosed examples.

[0366] As used herein, the terms “mechanical storage medium,” “device storage medium,” and “computer storage medium” (collectively referred to as “mechanical storage medium 3122”) mean the same thing and may be used interchangeably in this disclosure. These terms refer to a single or multiple storage devices and / or storage media (e.g., centralized or distributed databases and / or associated caches and servers) on which executable instructions and / or executable data are stored, as well as cloud-based storage systems or storage networks comprising multiple storage devices or storage devices. Accordingly, these terms shall be interpreted to include, but are not limited to, solid-state memory, and optical or magnetic media, including memory internal or external to a processor. Specific examples of mechanical storage medium, computer storage medium, and / or device storage medium 3122 include non-volatile memory, including, by way of example, semiconductor memory devices such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), FPGAs, and flash memory devices, magnetic disks such as internal hard disks and removable disks, magneto-optical disks, and CD-ROM and DVD-ROM disks. The terms mechanical storage media, computer storage media, and device storage media 3122 specifically exclude carrier waves, modulated data signals, and other such media, at least some of which are covered by the term "signal media" discussed below.

[0367] signal medium The terms "signal medium" or "transmission medium" shall be interpreted to include any form of modulated data signal, carrier wave, etc. The term "modulated data signal" means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal.

[0368] Computer-readable medium The terms "machine-readable medium," "computer-readable medium," and "device-readable medium" mean the same thing and may be used interchangeably in this disclosure. These terms are defined to include both mechanical storage media and signal media. Thus, these terms include both storage devices / storage media and carrier wave / modulated data signals.

[0369] The instructions 3124 may further be transmitted or received over a communications network 3126 using a transmission medium via the network interface device 3120 using any one of several well-known transfer protocols (e.g., HTTP). Examples of communications networks include a LAN, a WAN, the Internet, a cellular network, a Plain Old Telephone Service (POTS) network, and a wireless data network (such as a Wi-Fi, 3G, 4G LTE / LTE-A, 5G, or WiMAX network). The term "transmission medium" shall be interpreted to include any intangible medium capable of storing, encoding, or carrying instructions for execution by a machine, including digital or analog communications signals or other intangible media for facilitating communication of such software.

[0370] Throughout this specification, multiple instances may implement a component, operation, or structure described as a single instance. While individual operations of one or more methods are illustrated and described as separate operations, one or more individual operations may be performed simultaneously, and the operations need not be performed in the order shown. Structures and functions presented as separate components in exemplary configurations may be implemented as combined structures or components. Similarly, structures and functions presented as single components may be implemented as separate components. These and other variations, modifications, additions, and improvements are within the scope of the subject matter of this specification.

[0371] In this disclosure, various components are described as being configured in a particular manner. The components may be configured in any suitable manner. For example, a component that is or includes a computing device may be configured with suitable software instructions that program the computing device. The components may also be configured by their hardware configuration or in any other suitable manner.

[0372] The above description is intended to be illustrative, not limiting. For example, the above-described embodiments (or one or more aspects thereof) may be used in combination with each other. Upon reviewing the above description, for example, one of ordinary skill in the art may be able to use other embodiments. The Abstract is intended to enable the reader to quickly ascertain the nature of the technical disclosure, for example, pursuant to U.S. 37 C.F.R. §1.72(b). It is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims.

[0373] Also, in the above Detailed Description, various features may be grouped together to simplify the disclosure. However, because an embodiment may feature a subset of the features, the claims may not describe all of the features disclosed herein. Moreover, an embodiment may include fewer features than are disclosed in a particular embodiment. Accordingly, the scope of the appended claims is hereby incorporated into the Detailed Description, with each claim standing on its own as a separate embodiment. The scope of the embodiments disclosed herein should be determined with reference to the appended claims, along with the full range of equivalents to which such claims are entitled.

[0374] Each of these non-limiting examples in any part of the above description can stand alone by itself or can be combined in various permutations or combinations with one or more of the other examples.

[0375] 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 subject matter 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), either with respect to the particular example (or one or more aspects thereof) or with respect to other examples (or one or more aspects thereof) shown or described herein.

[0376] In the event of inconsistent usage between this document and any documents incorporated by reference, the usage in this document takes precedence.

[0377] In this document, the terms "a" or "an" are used to include one or more, as is common in patent documents, regardless of other instances or uses 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 "including" and "in which" are used as the plain-English equivalents of the respective terms "comprising" and "wherein." Also, in the following claims, the terms "comprising" and "comprising" are intended to be open-ended, i.e., systems, devices, articles, compositions, formulations, or processes that include elements in addition to those listed after such terms in a claim are still considered to be within the scope of that claim. Furthermore, in the appended claims, terms such as "first," "second," and "third" are used merely as labels and are not intended to impose numerical requirements on their objects.

[0378] Geometric terms such as "parallel," "perpendicular," "circular," or "square" do not require absolute mathematical precision unless the context dictates otherwise. Instead, such geometric terms allow for variations due to manufacturing or equivalent functions. For example, if an element is described as "circular" or "generally circular," components that are not exactly circular (e.g., somewhat rectangular or multi-sided polygonal) are also encompassed by this description.

[0379] The example methods described herein can be at least partially machine- or computer-implemented. Some examples 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 can include code, such as, for example, microcode, assembly language code, higher-level language code, etc. Such code can include computer-readable instructions for performing various methods. The code can form part of a computer program product. Furthermore, in one example, the code can be tangibly stored on one or more volatile, non-transitory, or non-volatile tangible computer-readable media during execution or at other times. Examples of these tangible computer-readable media can 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.

[0380] The above description is intended to be illustrative, not limiting. For example, the above-described examples (or one or more aspects thereof) may be used in combination with each other. Upon reviewing the above description, for example, one of ordinary skill in the art may utilize other embodiments. The Abstract is provided 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 scope of a 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 it is contemplated that such embodiments can be combined with each other in various combinations or permutations. The scope of the present subject matter should be determined with reference to the claims, along with the full range of equivalents to which such claims are entitled. [Explanation of symbols]

[0381] 104 Analyte Sensor 202 Measurement circuit 204 processors 206 Command 208 memory 210 Data storage device 212 Sensors 214 Battery 216 Recharging System 218 Wireless Communication 250 peripheral devices 252 User Interface 254 memory 256 processors 258 Wireless 260 sensors 270 Medical Devices 272 User Interface 274 memory 276 processors 278 Wireless 280 Sensors 282 Treatment 290 Sensor Mounting Unit 292 Battery Gate 294 3102 processor 3104 Main Memory 3106 Static Memory 3108 Bus 3110 Video Display 3112 Alphanumeric Input Device 3114 UI navigation device 3116 Storage Device 3118 Signal Generating Device 3120 Network Interface Device 3122 Machine-readable medium 3124 Instructions 3126 Network

Claims

1. 1. A system for generating a bolus dose for a recipient, the system comprising: at least one processor, Displaying a first bolus configuration parameter question on a user interface; receiving, via the user interface, a first answer to the first bolus configuration parameter question, the first answer describing a previous bolus determination technique of the recipient; using the first answer to select a second bolus configuration parameter question; providing the second bolus configuration parameter query to the user interface; determining a set of at least one bolus configuration parameter using the first answer and a second answer to the second bolus configuration parameter question; receiving a recipient glucose concentration from a continuous glucose sensor; determining a bolus dose for the recipient using the recipient glucose concentration and the set of at least one bolus configuration parameter; and displaying an indication of the bolus dose on the user interface; The system further includes, if all bolus configuration parameters of the set of bolus configuration parameters cannot be determined after receiving the second answer to the second bolus configuration parameter question via the user interface, providing the user interface with a third bolus configuration parameter question for deriving the undetermined bolus configuration parameters, and determining the set of the at least one bolus configuration parameter based on the first answer, the second answer, and the third answer to the third bolus configuration parameter question.

2. 2. The system of claim 1, wherein the operations further include using the first answers to select a second set of questions, and the second bolus configuration parameter questions are part of the second set of questions.

3. 2. The system of claim 1, wherein the first answer indicates that the recipient's previous bolus determination technique takes into account glucose concentration and meal amount indication, and the second answer to the second bolus configuration parameter question indicates that the recipient's previous bolus determination technique uses a formula.

4. 2. The system of claim 1, wherein the first response indicates that the recipient's previous bolus determination technique considers a bolus-related meal, and the second response to the second bolus configuration parameter question requests the recipient to provide an indication of a bolus insulin dose according to the previous bolus determination technique and an indication of a meal associated with the bolus insulin dose according to the previous bolus determination technique.

5. 2. The system of claim 1, wherein the first response indicates that the recipient's previous bolus determination technique takes into account the recipient's glucose concentration, and the second response to the second bolus configuration parameter question requests the recipient to provide an indication of a bolus insulin dose and an indication of a deviation between the recipient's glucose concentration and the recipient's target glucose concentration.

6. 2. The system of claim 1, wherein the first response indicates that the recipient's previous bolus determination technique uses a fixed bolus dose, and the operations further include executing a model based at least in part on the first response and the second response to generate a first bolus configuration parameter of the set of at least one bolus configuration parameter.

7. 10. The system of claim 1, wherein the actions further include transmitting data describing the bolus dose to an insulin delivery system, the data being for use in delivering the bolus dose to the recipient by the insulin delivery system.

8. 1. A method of generating a bolus insulin dose for a recipient using a bolus application, the method comprising: displaying, by the bolus application, a first bolus configuration parameter question on a bolus application user interface; receiving, by the bolus application via the bolus application user interface, a first answer to the first bolus configuration parameter question, the first answer describing a previous bolus determination technique of the recipient; selecting, by the bolus application, a second bolus configuration parameter question using the first answer; providing, by the bolus application, the second bolus configuration parameter question in the bolus application user interface; determining, by the bolus application, a set of at least one bolus configuration parameter using the first answer and a second answer to the second bolus configuration parameter question; receiving a recipient glucose concentration from a continuous glucose sensor by said bolus application; determining, by the bolus application, a bolus dose for the recipient using the recipient glucose concentration and the set of at least one bolus configuration parameter; and displaying an indication of the bolus dose on the bolus application user interface; The method includes, if all bolus configuration parameters of the set of bolus configuration parameters cannot be determined after receiving the second answer to the second bolus configuration parameter question via the bolus application user interface, providing the bolus application user interface with a third bolus configuration parameter question for deriving the undetermined bolus configuration parameters, and determining the set of the at least one bolus configuration parameter based on the first answer, the second answer, and the third answer to the third bolus configuration parameter question.

9. 9. The method of claim 8, further comprising using the first answer to select a second set of questions, the second bolus configuration parameter question being part of the second set of questions.

10. 9. The method of claim 8, wherein the first answer indicates that the recipient's previous bolus determination technique takes into account glucose concentration and meal amount indication, and the second answer to the second bolus configuration parameter question indicates that the recipient's previous bolus determination technique uses a formula.

11. 9. The method of claim 8, wherein the first response indicates that the recipient's previous bolus determination technique considers a bolus-related meal, and the second response to the second bolus configuration parameter question requests the recipient to provide an indication of a bolus insulin dose according to the previous bolus determination technique and an indication of a meal associated with the bolus insulin dose according to the previous bolus determination technique.

12. 9. The method of claim 8, wherein the first response indicates that the recipient's previous bolus determination technique takes into account the recipient's glucose concentration, and the second response to the second bolus configuration parameter question requests the recipient to provide an indication of a bolus insulin dose and an indication of a deviation between the recipient's glucose concentration and the recipient's target glucose concentration.

13. 9. The method of claim 8, wherein the first response indicates that the recipient's previous bolus determination technique uses a fixed bolus dose, and the method further comprises executing a model based at least in part on the first response and the second response to generate a first bolus configuration parameter of the set of at least one bolus configuration parameter.

14. 10. The method of claim 8, further comprising transmitting, by the bolus application, data describing the bolus dose to an insulin delivery system, the data for use in delivering the bolus dose to the recipient by the insulin delivery system.

15. 1. A machine-readable medium containing instructions that, when executed by at least one processor, cause the at least one processor to: Displaying a first bolus configuration parameter question on a user interface; receiving, via the user interface, a first answer to the first bolus configuration parameter question, the first answer describing a recipient's previous bolus determination technique; using the first answer to select a second bolus configuration parameter question; providing the second bolus configuration parameter query to the user interface; determining a set of at least one bolus configuration parameter using the first answer and a second answer to the second bolus configuration parameter question; receiving a recipient glucose concentration from a continuous glucose sensor; determining a bolus dose for the recipient using the recipient glucose concentration and the set of at least one bolus configuration parameter; causing the user interface to perform operations including: displaying an indication of the bolus dose; The machine-readable medium further includes, if all bolus configuration parameters of the set of bolus configuration parameters cannot be determined after receiving the second answer to the second bolus configuration parameter question via the user interface, providing the user interface with a third bolus configuration parameter question for deriving the undetermined bolus configuration parameters, and determining the set of the at least one bolus configuration parameter based on the first answer, the second answer, and the third answer to the third bolus configuration parameter question.

Images