Administration of bolus dose

Abstract

Various examples relate to systems and methods for generating bolus doses for a host. An bolus application may display a first bolus configuration parameter question at a user interface and receive a first answer to the first bolus configuration parameter question through the user interface. The first answer may describe the host's previous bolus determination technique. The bolus application may use the first answer to select a second bolus configuration parameter question and provide the second bolus configuration parameter question at the user interface. The bolus application may use the first answer and a second answer to the second bolus configuration parameter question to determine at least one set of bolus configuration parameters.

Description

[0001] By incorporating any priority claim

[0002] This application claims the benefit of priority to U.S. Provisional Patent Application No. 62 / 958,636, filed January 8, 2020, entitled “Managing Bollsides,” the contents of which are incorporated herein by reference in their entirety and are expressly part of this specification. Technical Field

[0003] This disclosure generally relates to medical devices, such as analyte sensors, and more specifically, by way of example and not limitation, to systems, apparatuses, and methods for managing insulin bolus doses in diabetic patients using analyte sensors. Background Technology

[0004] Diabetes is a metabolic disorder related to the body's production or use of insulin. Insulin is a hormone that allows the body to use glucose as energy or store glucose as fat.

[0005] When a person eats a diet containing carbohydrates, the food is processed by the digestive system, which produces glucose in the bloodstream. 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 when glucose levels are too high or too low. The regulation of blood glucose levels depends on the production and use of insulin, which regulates the movement of blood glucose into cells.

[0006] When the body cannot produce enough insulin, or when the body cannot effectively use the insulin it has, glucose levels rise above the normal range. This condition of having higher than normal glucose levels is called hyperglycemia. Chronic hyperglycemia can lead to many health problems, such as cardiovascular disease, cataracts and other eye problems, nerve damage (neuropathy), and kidney damage. Hyperglycemia can also cause acute problems, such as diabetic ketoacidosis—a condition where the body becomes excessively acidic due to the presence of blood sugar and ketones produced when the body cannot use glucose. A condition of having lower than normal glucose levels is called hypoglycemia. Severe hypoglycemia can lead to an acute crisis, potentially causing seizures or death.

[0007] Diabetes is sometimes referred to as "type 1" and "type 2." People with type 1 diabetes are usually able to use insulin when it's present, but due to a problem with the pancreas's beta cells that produce insulin, the body cannot produce enough. People with type 2 diabetes may produce some insulin, but due to decreased sensitivity to insulin, they have developed "insulin resistance." As a result, even when insulin is present, the amount in the patient's body is insufficient to effectively regulate glucose levels. People with diabetes can receive insulin to manage their glucose levels. For example, insulin can be administered manually with a needle. Wearable insulin pumps can also be used. Summary of the Invention

[0008] This disclosure particularly describes systems, apparatus, and methods for managing user injection doses, such as those from analyte sensors and related technologies.

[0009] Example 1 is a system for generating a bolus dose for a host, the method comprising: at least one processor programmed to perform operations including: displaying a first bolus configuration parameter question at a user interface; receiving a first answer to the first bolus configuration parameter question via the user interface, the first answer describing a previous bolus determination technique of the host; selecting a second bolus configuration parameter question using the first answer; providing the second bolus configuration parameter question at 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 host glucose concentration from a continuous glucose sensor; determining a bolus dose for the host using the host glucose concentration and the set of at least one bolus configuration parameter; and displaying an indication of the bolus dose at the user interface.

[0010] In Example 2, the topic of Example 1 optionally includes the operation further comprising using the first answer to select a second set of questions, wherein the second push configuration parameter question is part of the second set of questions.

[0011] In Example 3, the subject of any one or more of Examples 1 to 2 optionally includes the operation further comprising: receiving a second answer to the second betting configuration parameter question through the user interface; determining, after receiving the second answer, that it can compute all of less than one set of betting configuration parameters; and providing a third betting configuration parameter question at the user interface, wherein determining the set of the at least one betting configuration parameter is also based at least in part on the third answer to the third betting configuration parameter question.

[0012] In Example 4, the subject of any one or more of Examples 1 to 3 optionally includes, wherein the first answer indicates that the host’s previous injection determination technique takes into account indications of glucose concentration and dietary amount, and wherein the second answer to the second injection configuration parameter question indicates that the host’s previous injection determination technique uses a formula.

[0013] In Example 5, the subject of any one or more of Examples 1 to 4 optionally includes, wherein the first answer indicates that the host’s previous injection determination technique takes into account the injection-related diet, and wherein the second answer to the second injection configuration parameter question requests the host to provide an instruction on the injection insulin dose according to the previous injection determination technique and an instruction on the diet associated with the injection insulin dose according to the previous injection determination technique.

[0014] In Example 6, the subject matter of any one or more of Examples 1 to 5 optionally includes, wherein the first answer indicates that the host's previous injection determination technique took into account the host's glucose concentration, and wherein the second answer to the second injection configuration parameter question requests the host to provide an indication of the injection insulin dose and an indication of the deviation between the host's glucose concentration and the host's target glucose concentration.

[0015] In Example 7, the subject of any one or more of Examples 1 to 6 optionally includes, wherein the first answer indicates that the host’s previous injection determination technique uses a constant injection dose, and the operation of the system further includes performing a model at least in part based on the first answer and the second answer to generate a first injection configuration parameter from a set of at least one injection configuration parameters.

[0016] In Example 8, the subject matter of any one or more of Examples 1 to 7 optionally includes the operation further comprising sending data describing the bolus dose to an insulin delivery system for providing the bolus dose to the host by the insulin delivery system.

[0017] Example 9 is a method for generating an insulin bolus dose for a host using an injection application, the method comprising: displaying a first injection configuration parameter question via the injection application and at an injection application user interface; receiving a first answer to the first injection configuration parameter question via the injection application and at the injection application user interface, the first answer describing the host's previous injection determination technique; selecting a second injection configuration parameter question via the injection application using the first answer; providing the second injection configuration parameter question via the injection application and at the injection application user interface; determining a set of at least one injection configuration parameter via the injection application using the first answer and a second answer to the second injection configuration parameter question; receiving a host glucose concentration via the injection application and from a continuous glucose sensor; determining a bolus dose for the host via the injection application using the host glucose concentration and the set of at least one injection configuration parameter; and displaying an indication of the bolus dose at the injection application user interface.

[0018] In Example 10, the topic of Example 9 optionally includes using the first answer to select a second set of questions, wherein the second push configuration parameter question is part of the second set of questions.

[0019] In Example 11, the subject of any one or more of Examples 9 to 10 optionally includes receiving a second answer to a second betting configuration parameter question through the betting application and through the betting application user interface; after receiving the second answer, determining through the betting application that it can calculate all of less than one set of betting configuration parameters; and providing a third betting configuration parameter question through the betting application and at the betting application user interface, wherein the determination of the set of at least one betting configuration parameter is also based at least in part on a third answer to the third betting configuration parameter question.

[0020] In Example 12, the subject of any one or more of Examples 9 to 11 optionally includes, wherein the first answer indicates that the host's previous injection determination technique takes into account indications of glucose concentration and dietary amount, and wherein the second answer to the second injection configuration parameter question indicates that the host's previous injection determination technique uses a formula.

[0021] In Example 13, the subject of any one or more of Examples 9 to 12 optionally includes, wherein the first answer indicates that the host’s previous injection determination technique takes into account the injection-related diet, and wherein the second answer to the second injection configuration parameter question requests the host to provide an indication of the injection insulin dose according to the previous injection determination technique and an indication of the diet associated with the injection insulin dose according to the previous injection determination technique.

[0022] In Example 14, the subject matter of any one or more of Examples 9 to 13 optionally includes, wherein the first answer indicates that the host's previous injection determination technique took into account the host's glucose concentration, and wherein the second answer to the second injection configuration parameter question requests the host to provide an indication of the injection insulin dose and an indication of the deviation between the host's glucose concentration and the host's target glucose concentration.

[0023] In Example 15, the subject of any one or more of Examples 9 to 14 optionally includes, wherein the first answer indicates that the host’s previous injection determination technique uses a constant injection dose, and the method further includes performing a model at least in part based on the first answer and the second answer to generate a first injection configuration parameter from a set of at least one injection configuration parameters.

[0024] In Example 16, the subject matter of any one or more of Examples 9 to 15 optionally includes sending data describing the bolus dose to the insulin delivery system via the bolus application, the data being used to provide the bolus dose to the host via the insulin delivery system.

[0025] Example 17 is a machine-readable medium containing instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations including: displaying a first injection configuration parameter question at a user interface; receiving, via the user interface, a first answer to the first injection configuration parameter question, the first answer describing a previous injection determination technique of the host; selecting a second injection configuration parameter question using the first answer; providing the second injection configuration parameter question at the user interface; determining a set of at least one injection configuration parameter using the first answer and a second answer to the second injection configuration parameter question; receiving a host glucose concentration from a continuous glucose sensor; determining an injection dose for the host using the host glucose concentration and the set of at least one injection configuration parameter; and displaying an indication of the injection dose at the user interface.

[0026] Example 18 is a system for managing host treatment using a continuous glucose sensor, the system comprising: at least one processor programmed to perform operations including: acquiring an indication of an injection dose to be administered to the host; receiving glucose concentration data from the continuous glucose sensor describing the host's glucose concentration; generating effect data describing the effect of the injection dose, the generation using the glucose concentration data; and displaying the effect data to the host at a user interface.

[0027] In Example 19, the subject matter of Example 18 optionally includes the operation further comprising the instruction to receive the bolus dose from the insulin delivery system.

[0028] In Example 20, the subject matter of any one or more of Examples 18 to 19 optionally includes, wherein the glucose concentration data comprises multiple glucose concentrations of the host during a first time period, and the operation further comprises using the multiple glucose concentrations of the host during the first time period to determine the indication of the bolus dose.

[0029] In Example 21, the subject matter of any one or more of Examples 18 to 20 optionally includes, wherein the glucose concentration data indicates the current glucose concentration of the host, the operation further comprising: determining a glucose correction for the bolus dose based at least in part on the current glucose concentration and the target glucose concentration of the host; determining a correction component of the bolus dose based at least in part on the glucose correction and the bolus dose; and determining a dietary component of the bolus dose based at least in part on the correction component, wherein generating the effect data includes determining the carbohydrate coverage of the dietary component.

[0030] In Example 22, the subject matter of any one or more of Examples 18 to 21 optionally includes the operation further comprising: acquiring dietary data describing a diet associated with the bolus dose; determining a dietary component of the bolus dose based at least in part on the dietary data; and determining a correction component of the bolus dose based at least in part on the dietary component, wherein generating the effect data includes determining glucose correction based at least in part on the correction component.

[0031] In Example 23, the subject matter of Example 22 optionally includes, wherein obtaining the dietary data comprises: determining the diet associated with the bolus dose; and obtaining a carbohydrate count associated with the diet.

[0032] In Example 24, the subject matter of any one or more of Examples 22 to 23 optionally includes, wherein determining the diet associated with the bolus dose comprises an image of receiving at least a portion of the diet associated with the bolus dose from an insulin delivery system.

[0033] In Example 25, the subject matter of any one or more of Examples 18 to 24 optionally includes, wherein the effect data contains carbohydrate coverage associated with the bolus dose, and wherein the effect data displayed at the user interface includes an indication of the carbohydrate coverage.

[0034] In Example 26, the subject of any one or more of Examples 18 to 25 optionally includes, wherein the effect data comprises glucose correction, and wherein displaying the effect data at the user interface comprises: generating an estimated future glucose concentration trajectory based at least in part on the glucose correction; and displaying the estimated future glucose trajectory.

[0035] In Example 27, the subject matter of any one or more of Examples 18 to 26 optionally includes the operation further comprising: acquiring model data describing a physiological model associated with the host; acquiring prior dietary data describing a diet previously consumed by the host; acquiring prior bolus dose data describing a prior bolus dose administered to the host; and determining carbohydrate coverage using the prior dietary data, the prior bolus dose data, and the model data, wherein the effect data is based at least in part on the carbohydrate coverage.

[0036] Example 28 is a method for managing a host's treatment using a continuous glucose sensor, the method comprising: obtaining an instruction for an injection dose to be administered to the host via an injection application executed on a computing device; receiving glucose concentration data describing the host's glucose concentration via the injection application and from the continuous glucose sensor; generating effect data describing the effect of the injection dose via the injection application, the generation using the glucose concentration data; and displaying the effect data to the host via the injection application at a user interface.

[0037] In Example 29, the subject matter of Example 28 optionally includes the instruction to receive the bolus dose from the insulin delivery system.

[0038] In Example 30, the subject matter of any one or more of Examples 28 to 29 optionally includes, wherein the glucose concentration data comprises multiple glucose concentrations of the host during a first time period, and the method further comprises using the multiple glucose concentrations of the host during the first time period to determine the indication of the bolus dose.

[0039] In Example 31, the subject matter of any one or more of Examples 28 to 30 optionally includes, wherein the glucose concentration data indicates the current glucose concentration of the host, the method further comprising: determining a glucose correction for the bolus dose based at least in part on the current glucose concentration and a target glucose concentration of the host; determining a correction component of the bolus dose based at least in part on the glucose correction and the bolus dose; and determining a dietary component of the bolus dose based at least in part on the correction component, wherein generating the effect data includes determining the carbohydrate coverage of the dietary component.

[0040] In Example 32, the subject matter of any one or more of Examples 28 to 31 optionally includes: acquiring dietary data describing a diet associated with the bolus dose; determining a dietary component of the bolus dose based at least in part on the dietary data; and determining a correction component of the bolus dose based at least in part on the dietary component, wherein generating the effect data includes determining glucose correction based at least in part on the correction component.

[0041] In Example 33, the subject matter of Example 32 optionally includes, wherein obtaining the dietary data comprises: determining the diet associated with the bolus dose; and obtaining a carbohydrate count associated with the diet.

[0042] In Example 34, the subject matter of any one or more of Examples 32 to 33 optionally includes, wherein determining the diet associated with the bolus dose comprises an image of receiving at least a portion of the diet associated with the bolus dose from an insulin delivery system.

[0043] In Example 35, the subject matter of any one or more of Examples 28 to 34 optionally includes, wherein the effect data contains carbohydrate coverage associated with the bolus dose, and wherein the effect data displayed at the user interface includes an indication of the carbohydrate coverage.

[0044] In Example 36, the subject of any one or more of Examples 28 to 35 optionally includes, wherein the effect data comprises glucose correction, and wherein displaying the effect data at the user interface comprises: generating an estimated future glucose concentration trajectory based at least in part on the glucose correction; and displaying the estimated future glucose trajectory.

[0045] In Example 37, the subject matter of any one or more of Examples 28 to 36 optionally includes, via the injection application, obtaining model data describing a physiological model associated with the host; via the injection application, obtaining prior dietary data describing a diet previously consumed by the host; via the injection application, obtaining prior injection dose data describing a prior injection dose administered to the host; and via the injection application, determining carbohydrate coverage using the prior dietary data, the prior injection dose data, and the model data, wherein the effect data is at least partially based on the carbohydrate coverage.

[0046] Example 38 is a machine-readable medium having instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations including: acquiring an indication of an injection dose to be provided to the host; receiving glucose concentration data from the continuous glucose sensor describing the glucose concentration of the host; generating effect data describing the effect of the injection dose, the generation using the glucose concentration data; and displaying the effect data to the host at a user interface.

[0047] Example 39 is a system for generating a bolus dose for a host, 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 the current time of day and current glucose concentration data describing the current glucose concentration at the host received from a continuous glucose sensor system; comparing the current case parameter data with a plurality of nominal cases to select the closest nominal case associated with nominal case parameter data and nominal case treatment data, the nominal case parameter data including at least the nominal case time of day and nominal case glucose concentration; determining a treatment modification factor using difference data describing the difference between the current case parameter data and the closest nominal case parameter data; applying the treatment modification factor to the nominal case treatment parameter data to generate current case treatment data; and determining the current case bolus dose using the current case treatment data.

[0048] In Example 40, the subject of Example 39 optionally includes the application of the treatment modification factor comprising applying a multiplier to a bolus configuration parameter associated with the closest nominal case.

[0049] In Example 41, the subject matter of any one or more of Examples 39 to 40 optionally includes the operation further comprising: receiving second current case parameter data describing a second current injection case; comparing the second current case parameter data with the plurality of nominal cases to select a second closest nominal case; and determining that the difference between the second current injection case and the second closest nominal case is greater than a threshold.

[0050] In Example 42, the subject matter of Example 41 optionally includes the operation further comprising: in response to the difference between the second current bolus case and the second closest nominal case being greater than the threshold, determining the bolus dose for the second current case using an alternative bolus method.

[0051] In Example 43, the subject matter of any one or more of Examples 41 to 42 optionally includes the operation further comprising: receiving result data describing the outcome of the second current injection case; and generating a new nominal case using the second current case parameter data and the result data.

[0052] In Example 44, the subject matter of any one or more of Examples 41 to 43 optionally includes the operation further comprising: monitoring outcome data describing the outcome of the second current injection case; determining that an intervention event occurred before the monitoring was completed; and generating supplementary outcome data using the second closest nominal case.

[0053] In Example 45, the subject matter of any one or more of Examples 39 to 44 optionally includes, further comprising: monitoring outcome data describing the outcome of the bolus case; and modifying at least one of the nominal case treatment data or treatment modification parameters based at least in part on the outcome data.

[0054] Example 46 is a system for generating a bolus dose for a host, 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 the current time of day and current glucose concentration data describing the current glucose concentration at the host received from a continuous glucose sensor system; comparing the current case parameter data with a plurality of stored cases to select the 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 the stored case time of day and stored case glucose concentration; determining the current case bolus dose using the stored case treatment parameter data to generate current case treatment data; monitoring outcome data describing the outcome of the current bolus case; determining that an intervention event has occurred before the monitoring is completed; generating supplementary 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 supplementary outcome data.

[0055] Example 47 is a method for a bolus calculator, comprising: receiving current case parameter data describing a current bolus case, the current case parameter data including at least the current time of day and current glucose concentration data describing the current glucose concentration at the host received from a continuous glucose sensor system; comparing the current case parameter data with a plurality of nominal cases to select the closest nominal case, the closest nominal case being associated with nominal case parameter data and nominal case treatment data, the nominal case parameter data including at least the nominal case time of day and nominal case glucose concentration; determining a treatment modification factor using difference data describing the difference between the current case parameter data and the closest nominal case parameter data; applying the treatment modification factor to the nominal case treatment parameter data to generate current case treatment data; and determining the current case bolus dose using the current case treatment data.

[0056] In Example 48, the subject of Example 47 optionally includes the application of the treatment modification factor comprising applying a multiplier to a bolus configuration parameter associated with the closest nominal case.

[0057] In Example 49, the subject matter of any one or more of Examples 47 to 48 optionally includes receiving second current case parameter data describing a second current injection case; comparing the second current case parameter data with the plurality of nominal cases to select a second closest nominal case; and determining that the difference between the second current injection case and the second closest nominal case is greater than a threshold.

[0058] In Example 50, the subject matter of Example 49 optionally includes determining the bolus dose for the second current case using an alternative bolus method in response to the difference between the second current bolus case and the second closest nominal case being greater than the threshold.

[0059] In Example 51, the subject matter of any one or more of Examples 49 to 50 optionally includes receiving outcome data describing the outcome of the second current injection case; and generating a new nominal case using the second current case parameter data and the outcome data.

[0060] In Example 52, the subject matter of any one or more of Examples 49 to 51 optionally includes outcome data describing the outcome of the second current injection case; determining an intervention event that occurred before the monitoring was completed; and generating supplementary outcome data using the second closest nominal case.

[0061] In Example 53, the subject matter of any one or more of Examples 47 to 52 optionally includes outcome data that monitors the results describing the outcome of the bolus case; and at least one of the nominal case treatment data or treatment modification parameters that is modified based at least in part on the outcome data.

[0062] Example 54 is a method for generating a bolus dose for a host, comprising: receiving current case parameter data describing a current bolus case, the current case parameter data including at least the current time of a day and current glucose concentration data describing the current glucose concentration at the host received from a continuous glucose sensor system; comparing the current case parameter data with a plurality of stored cases to select the 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 the stored case time of a day and the stored case glucose concentration; determining the current case bolus dose using the stored case treatment parameter data to generate current case treatment data; monitoring outcome data describing the outcome of the current bolus case; determining that an intervention event has occurred before the monitoring is completed; generating supplementary 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 supplementary outcome data.

[0063] Example 55 is a machine-readable medium having instructions thereon 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 the current time of day and current glucose concentration data describing the current glucose concentration at the host received from a continuous glucose sensor system; comparing the current case parameter data with a plurality of nominal cases to select the closest nominal case, the closest nominal case being associated with nominal case parameter data and nominal case treatment data, the nominal case parameter data including at least the nominal case time of day and nominal case glucose concentration; determining a treatment modification factor using difference data describing the difference between the current case parameter data and the closest nominal case parameter data; applying the treatment modification factor to the nominal case treatment parameter data to generate current case treatment data; and determining the current case bolus dose using the current case treatment data.

[0064] Example 56 is a system for determining and providing diabetes treatment, the system comprising: at least one processor programmed to perform operations including: acquiring training data; training a classification model; receiving test bolus data describing a test bolus dose of the host; receiving glucose concentration data describing a glucose concentration of the host from a continuous glucose sensor; applying the classification model to determine that the test bolus dose belongs to a first bolus category, the application of the classification model using the test bolus data and the glucose concentration data; selecting a host action based at least in part on the test bolus data and the first bolus category; and providing a host action prompt at a bolus application user interface, the bolus application prompt prompting the host to take the host action.

[0065] In Example 57, the subject matter of Example 56 optionally includes the operation further comprising: comparing the test injection data with first injection category data describing a plurality of injection doses in the first injection category; determining the difference between the test injection data and the first injection category data; and selecting the host action based on the difference between the test injection data and the first injection category data.

[0066] In Example 58, the subject matter of Example 57 is optionally included, wherein the host action comprises a modification of the host's base dose.

[0067] In Example 59, any one or more topics from Examples 57 to 58 are optionally included, wherein the host action includes a modification of the host's feed configuration parameters.

[0068] In Example 60, the subject matter of any one or more of Examples 56 to 59 optionally includes the operation further comprising: determining changes in insulin pump parameters based at least in part on the test bolus data and the first bolus category; and sending insulin pump change data indicating the changes in insulin pump parameters.

[0069] In Example 61, the subject of any one or more of Examples 56 to 60 optionally includes the operation further comprising: generating a glucose concentration trajectory for the host using the glucose concentration data; generating a user interface screen indicating the glucose concentration trajectory; and displaying a test injection indicator at a location on the user interface screen corresponding to the time of the test injection, wherein the test injection indicator also indicates the first injection category.

[0070] In Example 62, the subject matter of any one or more of Examples 56 to 61 optionally includes the operation further comprising using the glucose concentration data and the first injection category to determine that the host has a hypoglycemic risk greater than a threshold, wherein the host action is to treat hypoglycemia.

[0071] In Example 63, any one or more of the topics in Examples 56 to 62 are optionally included, wherein the classification model comprises a logistic regression model.

[0072] Example 64 is a method for determining and providing diabetes treatment using a computing device, the method comprising: acquiring training data via an injection application executed at the computing device; training a classification model; receiving test injection data describing a test injection dose of the host via the injection application; receiving glucose concentration data describing a glucose concentration of the host via the injection application and from a continuous glucose sensor; applying the classification model via the injection application to determine that the test injection dose belongs to a first injection category, the application of the classification model using the test injection data and the glucose concentration data; selecting a host action via the injection application based at least in part on the test injection data and the first injection category; and providing a host action prompt at a user interface of the injection application, the prompt prompting the host to take the host action.

[0073] In Example 65, the subject matter of Example 64 optionally includes comparing the test injection data with first injection category data describing a plurality of injection doses in the first injection category; determining the difference between the test injection data and the first injection category data; and selecting the host action based on the difference between the test injection data and the first injection category data.

[0074] In Example 66, the subject matter of Example 65 is optionally included, wherein the host action comprises a modification of the host's base dose.

[0075] In Example 67, any one or more of the topics in Examples 65 to 66 are optionally included, wherein the host action includes modification of the host's feed configuration parameters.

[0076] In Example 68, the subject matter of any one or more of Examples 64 to 67 optionally includes determining changes in insulin pump parameters based at least in part on the test injection data and the first injection category via the injection application; and sending insulin pump change data indicating the changes in insulin pump parameters via the injection application.

[0077] In Example 69, the subject of any one or more of Examples 64 to 68 optionally includes generating a glucose concentration trajectory for the host using the glucose concentration data; generating a user interface screen indicating the glucose concentration trajectory; and displaying a test injection indicator at a location on the user interface screen corresponding to the time of the test injection, wherein the test injection indicator also indicates the first injection category.

[0078] In Example 70, the subject of any one or more of Examples 64 to 69 optionally includes using the glucose concentration data and the first injection category to determine that the host has a hypoglycemic risk greater than a threshold, wherein the host action is to treat hypoglycemia.

[0079] In Example 71, any one or more of the topics in Examples 64 to 70 are optionally included, wherein the classification model comprises a logistic regression model.

[0080] Example 72 is a machine-readable medium having instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations including: acquiring training data; training a classification model; receiving test bolus data describing a test bolus dose of the host; receiving glucose concentration data describing a glucose concentration of the host from a continuous glucose sensor; applying the classification model to determine that the test bolus dose belongs to a first bolus category, the application of the classification model using the test bolus data and the glucose concentration data; selecting a host action based at least in part on the test bolus data and the first bolus category; and providing a host action prompt at a bolus application user interface, the bolus application prompting the host to take the host action.

[0081] Example 73 is a system for managing diabetes treatment, the system comprising: at least one processor programmed to perform operations including: acquiring corrected bolus data describing a corrected bolus dose received by a host at a first time; receiving glucose concentration data from a glucose sensor describing the host over a first time interval including the first time interval; determining recommended changes to on-plate insulin parameters for the host using the corrected bolus data and the glucose concentration data; and providing the host with an indication of the recommended changes to the on-plate insulin parameters.

[0082] In Example 74, the subject matter of Example 73 optionally includes the operation further comprising acquiring dietary bolus data describing the dietary bolus dose received by the host at a second time prior to the first time, wherein the recommended variation for determining the insulin parameters on the plate is based at least in part on the dietary bolus data.

[0083] In Example 75, the subject of Example 74 optionally includes the operation further comprising determining that there is a time less than a threshold between the second time and the first time.

[0084] In Example 76, the subject matter of any one or more of Examples 73 to 75 optionally includes the operation further comprising: determining the actual on-plate insulin value at the first time; and comparing the actual on-plate insulin value with a calculated on-plate insulin value determined using the on-plate insulin parameters of the host, wherein the recommended change of the on-plate insulin parameters is based at least in part on the comparison.

[0085] In Example 77, the subject matter of Example 76 optionally includes the operation further comprising determining a calculated on-board insulin parameter that results in a second calculated on-board insulin value substantially the same as the actual on-board insulin value, wherein the recommended variation of the on-board insulin parameter is for the calculated on-board insulin parameter.

[0086] In Example 78, the subject matter of any one or more of Examples 73 to 77 optionally includes the operation further comprising: acquiring past corrected bolus data describing a plurality of corrected bolus doses received by the host prior to the first time; and identifying a post-bolus pattern in the host's glucose concentration after the plurality of corrected bolus doses, wherein the change in the on-plate insulin parameter is at least partially based on the post-bolus pattern.

[0087] In Example 79, the subject matter of Example 78 optionally includes, wherein the post-injection pattern describes a glucose concentration lower than the host's target glucose concentration, and wherein the change in the plate insulin parameter is a reduction in the estimated plate insulin for dietary bolus injection.

[0088] In Example 80, the subject matter of any one or more of Examples 78 to 79 optionally includes, wherein the post-injection pattern describes a glucose concentration higher than the host's target glucose concentration, and wherein the change in the on-plate insulin parameter is an increase in the estimated on-plate insulin for dietary bolus injection.

[0089] Example 81 is a method for managing diabetes treatment using a computing device, the method comprising: acquiring corrected bolus data describing a corrected bolus dose received by a host at a first time; receiving glucose concentration data from a glucose sensor describing the host, including glucose concentration data for a first time period at the first time; determining recommended changes to on-plate insulin parameters for the host using the corrected bolus data and the glucose concentration data; and providing the host with an indication of the recommended changes to the on-plate insulin parameters.

[0090] In Example 82, the subject matter of Example 81 optionally includes obtaining dietary bolus data describing the dietary bolus dose received by the host at a second time prior to the first time, wherein the recommended changes in determining the insulin parameters on the plate are based at least in part on the dietary bolus data.

[0091] In Example 83, the subject of Example 82 optionally includes determining that there is a time less than a threshold between the second time and the first time.

[0092] In Example 84, the subject matter of any one or more of Examples 81 to 83 optionally includes determining the actual on-plate insulin value at the first time; and comparing the actual on-plate insulin value with a calculated on-plate insulin value determined using the on-plate insulin parameters of the host, wherein the recommended variation of the on-plate insulin parameters is based at least in part on the comparison.

[0093] In Example 85, the subject matter of Example 84 optionally includes determining a calculated on-board insulin parameter that results in a second calculated on-board insulin value that is substantially the same as the actual on-board insulin value, wherein the recommended variation of the on-board insulin parameter is for the calculated on-board insulin parameter.

[0094] In Example 86, the subject matter of any one or more of Examples 81 to 85 optionally includes acquiring past corrected bolus data describing a plurality of corrected bolus doses received by the host prior to the first time; and identifying a post-bolus pattern in the host's glucose concentration after the plurality of corrected bolus doses, wherein the change in the insulin parameters on the plate is at least partially based on the post-bolus pattern.

[0095] In Example 87, the subject matter of Example 86 optionally includes, wherein the post-injection pattern describes a glucose concentration lower than the host's target glucose concentration, and wherein the change in the plate insulin parameters is a reduction in the estimated plate insulin for dietary bolus injection.

[0096] In Example 88, the subject matter of any one or more of Examples 86 to 87 optionally includes, wherein the post-injection pattern describes a glucose concentration higher than the host's target glucose concentration, and wherein the change in the on-plate insulin parameter is an increase in the estimated on-plate insulin for dietary bolus injection.

[0097] Example 89 is a machine-readable medium having instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations including: acquiring corrected bolus data describing a corrected bolus dose received by a host at a first time; receiving glucose concentration data from a glucose sensor describing the host for a first time interval including the first time interval; determining a recommended change for on-plate insulin parameters for the host using the corrected bolus data and the glucose concentration data; and providing the host with an indication of the recommended change for the on-plate insulin parameters.

[0098] Example 90 is a system for managing diabetes in a host using a continuous glucose sensor, the system comprising: at least one processor programmed to perform operations including: receiving glucose concentration data from the continuous glucose sensor, the glucose concentration data describing at least a first glucose concentration of the host at a first time and a second glucose concentration of the host at a second time; determining a rate of change of the host's glucose concentration using the glucose concentration data; determining a predicted glucose concentration of the host at a future time using the rate of change of the glucose concentration; and determining a bolus dose for the host using the predicted glucose concentration at the future time and the host's current glucose concentration at the current time.

[0099] In Example 91, the subject matter of Example 90 optionally includes that the operation further comprises using the host’s predicted glucose concentration and insulin sensitivity factor (ISF) to determine a trend component of the bolus dose, wherein the bolus dose is at least partially based on the trend component.

[0100] In Example 92, the subject of any one or more of Examples 90 to 91 may optionally include a few minutes after the current time.

[0101] In Example 93, the subject of any one or more of Examples 90 to 92 optionally includes the operation further comprising selecting the future time by means of the betting application based at least in part on the age of the host.

[0102] In Example 94, the subject matter of any one or more of Examples 90 to 93 optionally includes the operation further comprising: receiving, via the injection application and from the continuous glucose sensor, second glucose concentration data describing at least a third glucose concentration of the host at a third time and a fourth glucose concentration of the host at a fourth time; determining, via the injection application, a second glucose concentration change rate of the host using the glucose concentration data; determining, via the injection application, that the second glucose concentration change rate is negative; determining a trend component of omitting a second injection dose of the host; and determining a second injection dose of the host using the second glucose concentration data.

[0103] In Example 95, the subject matter of any one or more of Examples 90 to 94 optionally includes the operation further comprising: receiving, via the injection application and from the continuous glucose sensor, second glucose concentration data describing at least a third glucose concentration of the host at a third time and a fourth glucose concentration of the host at a fourth time; using the glucose concentration data via the injection application to determine a second glucose concentration change rate of the host; using the second glucose change rate via the injection application to determine a second predicted glucose concentration of the host at a second future time; determining via the injection application that the second predicted glucose concentration of the host is greater than a threshold; determining a trend component that omits a second injection dose of the host; and using the second glucose concentration data to determine a second injection dose of the host.

[0104] In Example 96, the subject of Example 95 optionally includes the operation further comprising selecting the threshold by means of the injection application based at least in part on the host's age.

[0105] In Example 97, the subject matter of any one or more of Examples 90 to 96 optionally includes the operation further comprising: receiving a request to determine a second bolus dose for the host via the bolus application; determining that the request to determine the second bolus was received within a threshold time period for dietary bolus administration to the host; determining a trend component of omitting the second bolus dose for the host; and determining the second bolus dose for the host using second glucose concentration data received from the continuous glucose sensor.

[0106] In Example 98, the subject matter of any one or more of Examples 90 to 97 optionally includes the operation further comprising: receiving, via the injection application, a request to determine a second injection dose for the host, the request including dietary data describing a diet associated with the second injection dose; determining that the request to determine the second injection was received within a threshold time of a previous dietary injection for the host; determining a trend component of omitting the second injection dose for the host; and determining the second injection dose for the host using second glucose concentration data received from the continuous glucose sensor.

[0107] Example 99 is a method for managing diabetes in a host using a continuous glucose sensor and an injection application executed on a computing device, the method comprising: receiving glucose concentration data from the continuous glucose sensor via the injection application, the glucose concentration data describing at least a first glucose concentration of the host at a first time and a second glucose concentration of the host at a second time; determining a rate of change of the host's glucose concentration using the glucose concentration data via the injection application; determining a predicted glucose concentration of the host at a future time using the rate of change of the glucose concentration via the injection application; and determining an injection dose for the host using the predicted glucose concentration at the future time and the host's current glucose concentration at the current time via the injection application.

[0108] In Example 100, the subject matter of Example 99 optionally includes using the host’s predicted glucose concentration and insulin sensitivity factor (ISF) to determine a trend component of the bolus dose, wherein the bolus dose is at least partially based on the trend component.

[0109] In Example 101, the subject of any one or more of Examples 99 to 100 may optionally include a few minutes after the current time.

[0110] In Example 102, the subject of any one or more of Examples 99 to 101 optionally includes selecting the future time by means of the betting application based at least in part on the host's age.

[0111] In Example 103, the subject matter of any one or more of Examples 99 to 102 optionally includes receiving, via the injection application and from the continuous glucose sensor, second glucose concentration data describing at least a third glucose concentration of the host at a third time and a fourth glucose concentration of the host at a fourth time; determining, via the injection application, a second glucose concentration change rate of the host using the glucose concentration data; determining, via the injection application, that the second glucose concentration change rate is negative; determining a trend component of omitting a second injection dose of the host; and determining a second injection dose of the host using the second glucose concentration data.

[0112] In Example 104, the subject matter of any one or more of Examples 99 to 103 optionally includes receiving, via the injection application and from the continuous glucose sensor, second glucose concentration data describing at least a third glucose concentration of the host at a third time and a fourth glucose concentration of the host at a fourth time; using the glucose concentration data via the injection application to determine a second glucose concentration change rate of the host; using the second glucose change rate via the injection application to determine a second predicted glucose concentration of the host at a second future time; determining via the injection application that the second predicted glucose concentration of the host is greater than a threshold; determining a trend component that omits a second injection dose of the host; and using the second glucose concentration data to determine a second injection dose of the host.

[0113] In Example 105, the subject of Example 104 optionally includes selecting the threshold by means of the boosting application based at least in part on the host's age.

[0114] In Example 106, the subject matter of any one or more of Examples 99 to 105 optionally includes receiving a request to determine a second bolus dose for the host via the bolus application; determining that the request to determine the second bolus is received within a threshold time for the host's dietary bolus; determining a trend component of omitting the second bolus dose for the host; and determining the second bolus dose for the host using second glucose concentration data received from the continuous glucose sensor.

[0115] In Example 107, the subject matter of any one or more of Examples 99 to 106 optionally includes receiving, via the injection application, a request to determine a second injection dose for the host, the request containing dietary data describing a diet associated with the second injection dose; determining that the request to determine the second injection was received within a threshold time of a previous dietary injection for the host; determining a trend component of omitting the second injection dose for the host; and determining the second injection dose for the host using second glucose concentration data received from the continuous glucose sensor.

[0116] Example 108 is a machine-readable medium having instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations including: receiving glucose concentration data from the continuous glucose sensor, the glucose concentration data describing at least a first glucose concentration of the host at a first time and a second glucose concentration of the host at a second time; determining a rate of change of the host's glucose concentration using the glucose concentration data; determining a predicted glucose concentration of the host at a future time using the rate of change of the glucose concentration; and determining a bolus dose of the host using the predicted glucose concentration at the future time and the host's current glucose concentration at the current time.

[0117] Example 109 is a system for managing diabetes in a host using a continuous glucose sensor, comprising: at least one processor programmed to perform operations including: acquiring glucose concentration data from the continuous glucose sensor, the glucose concentration data indicating the host's current glucose concentration; acquiring bolus data indicating a bolus dose received by the host; selecting a hyperglycemia alarm threshold based at least in part on the bolus data; determining that the current glucose concentration meets the hyperglycemia alarm threshold; and providing a glucose alarm to the host.

[0118] In Example 110, the subject matter of Example 109 optionally includes the operation further comprising determining the on-plate insulin value of the host, wherein the determination of the hyperglycemia alarm threshold is based at least in part on the on-plate insulin value.

[0119] In Example 111, the subject matter of Example 110 optionally includes the operation further comprising determining that the insulin value on the plate is less than a threshold, wherein selecting the hyperglycemia alarm threshold comprises reducing the hyperglycemia alarm threshold at least in part based on determining that the insulin value on the plate is less than the threshold.

[0120] In Example 112, the subject matter of any one or more of Examples 110 to 111 optionally includes the operation further comprising determining that the insulin value on the plate is greater than a threshold, wherein selecting the hyperglycemia alarm threshold comprises increasing the hyperglycemia alarm threshold at least in part based on determining that the insulin value on the plate is greater than the threshold.

[0121] In Example 113, the subject matter of any one or more of Examples 109 to 112 optionally includes the operation further comprising determining that a threshold time has elapsed since the host received the bolus dose, wherein the determination of the hyperglycemia alarm threshold is based at least in part on the determination that a threshold time has elapsed since the host received the bolus dose.

[0122] In Example 114, the subject matter of Example 113 optionally includes, wherein selecting the hyperglycemia alarm threshold comprises reducing the hyperglycemia alarm threshold at least in part based on the determination that more than the threshold time has elapsed since the host received the bolus dose.

[0123] In Example 115, the subject matter of any one or more of Examples 109 to 114 optionally includes the operation further comprising determining that a time period less than a threshold has elapsed since the host received the bolus dose, wherein selecting the hyperglycemia alarm threshold comprises increasing the hyperglycemia alarm threshold at least in part based on determining that a time period less than the threshold has elapsed since the host received the bolus dose.

[0124] Example 116 is a method for managing diabetes in a host using a continuous glucose sensor and an injection application executed on a computing device, the method comprising: acquiring glucose concentration data from the continuous glucose sensor via the injection application, the glucose concentration data indicating the host's current glucose concentration; acquiring injection data via the injection application indicating an injection dose received by the host; selecting a hyperglycemia alarm threshold via the injection application based at least in part on the injection data; determining via the injection application that the current glucose concentration meets the hyperglycemia alarm threshold; and providing a glucose alarm to the host via the injection application.

[0125] In Example 117, the subject matter of Example 116 optionally includes determining the host's on-plate insulin value via the injection application, wherein the determination of the hyperglycemia alarm threshold is based at least in part on the on-plate insulin value.

[0126] In Example 118, the subject matter of Example 117 optionally includes determining that the insulin value on the plate is less than a threshold, wherein selecting the hyperglycemia alarm threshold includes reducing the hyperglycemia alarm threshold at least in part based on determining that the insulin value on the plate is less than the threshold.

[0127] In Example 119, the subject matter of any one or more of Examples 117 to 118 optionally includes determining that the insulin value on the plate is greater than a threshold, wherein selecting the hyperglycemia alarm threshold includes increasing the hyperglycemia alarm threshold at least in part based on determining that the insulin value on the plate is greater than the threshold.

[0128] In Example 120, the subject matter of any one or more of Examples 116 to 119 optionally includes determining, via the injection application, that a threshold time has elapsed since the host received the injection dose, wherein the determination of the hyperglycemia alarm threshold is based at least in part on the determination that a threshold time has elapsed since the host received the injection dose.

[0129] In Example 121, the subject matter of Example 120 optionally includes, wherein selecting the hyperglycemia alarm threshold comprises reducing the hyperglycemia alarm threshold at least in part based on the determination that more than the threshold time has elapsed since the host received the bolus dose.

[0130] In Example 122, the subject matter of any one or more of Examples 116 to 121 optionally includes determining, via the injection application, that a period of time less than a threshold has elapsed since the host received the injection dose, wherein selecting the hyperglycemia alert threshold includes increasing the hyperglycemia alert threshold at least in part based on determining that a period of time less than a threshold has elapsed since the host received the injection dose.

[0131] Example 123 is a machine-readable medium having instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations including: acquiring glucose concentration data from a continuous glucose sensor, the glucose concentration data indicating the current glucose concentration of the host; acquiring bolus data indicating a bolus dose received by the host; and selecting a hyperglycemia alarm threshold based at least in part on the bolus data; determining that the current glucose concentration meets the hyperglycemia alarm threshold; and providing a glucose alarm to the host.

[0132] This overview is intended to provide an overview of the subject matter of this patent application. It is not intended to provide an exclusive or exhaustive interpretation of this disclosure. Detailed descriptions are included to provide further information about this patent application. Other aspects of this disclosure will be apparent to those skilled in the art after reading and understanding the following detailed descriptions and viewing the accompanying drawings, which form a part thereof, and each of these detailed descriptions and drawings should not be considered limiting. Attached Figure Description

[0133] In accompanying drawings that are not necessarily drawn to scale, similar numbers can describe similar components in different views. The same numbers with different letter suffixes can represent different examples of similar components. The accompanying drawings illustrate, by way of example rather than limitation, the various embodiments described herein.

[0134] Figure 1 This is a diagram illustrating an example of an environment including an analyte sensor system.

[0135] Figure 2 It shows including Figure 1 A diagram illustrating an example of a medical device system using an analytical sensor system.

[0136] Figure 3 This is a diagram illustrating an example of a sensor.

[0137] Figure 4 yes Figure 3 An enlarged view of the analyte sensor section of an example analyte sensor system shown.

[0138] Figure 5 yes Figure 3 and 4 A cross-sectional view of the analyte sensor.

[0139] Figure 6 This is a schematic diagram of a circuit representing the behavior of a sensor in an example analysis object.

[0140] Figure 7 This is a diagram illustrating an instance of an environment that demonstrates the use of a push application to determine and utilize a set of at least one push configuration parameters of the host.

[0141] Figure 8 This is a flowchart illustrating an example of a processing flow, as described herein, that can be executed by a push application to determine a set of one or more push configuration parameters.

[0142] Figure 9 This is a flowchart illustrating an example of a problem workflow that can be executed through a push application to determine push configuration parameters.

[0143] Figure 10This is a flowchart illustrating an example of a process flow that can be executed by a betting application to determine one or more betting configuration parameters using a model.

[0144] Figure 11 This is a diagram illustrating an example of an environment that demonstrates the use of a push application to determine and utilize push effect data.

[0145] Figure 12 This is a flowchart illustrating an example of a processing flow that can be executed by a bolus application to determine and display bolus effect data.

[0146] Figure 13 This is a flowchart illustrating an example of a process that can be executed by an injection application to determine the injection effect data of the injection dose.

[0147] Figure 14 This is a flowchart illustrating an example of a process that can be executed by an injection application to determine the injection effect data of the injection dose.

[0148] Figure 15 This is a diagram showing an example screen of the betting application user interface, displaying betting effect data.

[0149] Figure 16 This is a diagram illustrating an instance of an environment that demonstrates the application of instance-based case-based reasoning techniques using a bolus application.

[0150] Figure 17 This is a flowchart illustrating an example of a process that can be executed by an injection application to determine the injection dose for the host.

[0151] Figure 18 This is a flowchart illustrating an example of a process that can be performed by an injection application when the difference between the current case and the closest nominal case is too large to determine an appropriate and accurate bolus dose.

[0152] Figure 19 This is a flowchart illustrating an example of a process that can be performed via an injection application when an intervention event occurs during monitoring of outcome data for potential new nominates or stored cases.

[0153] Figure 20 This is a diagram showing an example of an environment that demonstrates the use of a bolus application to perform a classification model for classifying bolus doses.

[0154] Figure 21 This is a flowchart illustrating an example of a process that can be executed by a bolus application to determine the bolus dose category using a classification model.

[0155] Figure 22This is a flowchart illustrating an example of a processing flow that can be executed by a push application to determine the recommended host action based on the category of the test push determined using a classification model.

[0156] Figure 23 This is a diagram illustrating an example of an environment that uses a push application to modify on-plate insulin (IOB) parameters.

[0157] Figure 24 This is a flowchart illustrating an example of a processing flow that can be executed by the push application to generate recommended changes to the IOB parameters.

[0158] Figure 25 This is a diagram illustrating an example of the environment described herein, demonstrating the use of a bolus application to determine the bolus dose for the host using trend adjustment.

[0159] Figure 26 This is a flowchart illustrating an example of a process that can be executed by a bolus application to determine the host's bolus dose using a trend component.

[0160] Figure 27 It shows Figure 26 A diagram of another example of the processing flow, in which in some cases there are additional operations for omitting the push trend component.

[0161] Figure 28 The diagram shows an example of environment 2800, which illustrates a bolus application 2834 configured to take bolus data into account to generate glucose concentration alarms.

[0162] Figure 29 This is a flowchart illustrating an example of a process that can be executed by a push application to generate push notification alerts for the host.

[0163] Figure 30 This is a flowchart illustrating an example of a processing flow that can be executed by a push application to perform the various techniques described herein.

[0164] Figure 31 This is a block diagram illustrating a computing device hardware architecture in which an executable instruction set or sequence of instructions is provided to enable the machine to perform any of the methods discussed herein. Detailed Implementation

[0165] The various examples described herein relate to analyte sensors and methods for using analyte sensors to manage host insulin bolus doses. The analyte sensor is placed in contact with the host's bodily fluids to measure the concentration of an analyte, such as glucose, in the fluid. In some instances, the analyte sensor is inserted under the host's skin and placed in contact with the interstitial fluid beneath the skin to measure the concentration of the analyte in the interstitial fluid.

[0166] Patients with diabetes who receive insulin may receive both basal insulin doses and bolus insulin doses. The basal insulin dose, also referred to herein as the basal dose, is used to manage resting glucose concentrations, while the bolus insulin dose is used to correct for or cover events that cause elevated glucose levels, such as meals. The basal dose is provided to produce the desired background or resting glucose concentration. In patients using insulin pumps or similar delivery devices, the basal dose may be provided constantly or semi-constantly according to a curve of changes over time. In some instances, long-acting insulin medications are used for the basal dose. For example, some patients who do not use insulin pumps receive a basal dose of long-acting insulin once or more daily, typically at a constant amount.

[0167] A bolus insulin dose, also referred to herein as a bolus dose, typically utilizes a short-acting insulin drug that has a strong, but usually short-lived, effect on glucose concentration. Therefore, a bolus dose is used to cover the food consumed by the patient (dietary bolus) and / or to correct for deviations from the target glucose concentration (corrective bolus). In some instances, the bolus dose is determined and / or administered in conjunction with the basal dose. For example, any suitable example described herein can be used to generate a combined dose comprising both a bolus portion and a basal portion.

[0168] Many factors are relevant to determining the bolus dose for a patient, including the amount of food the host intends to consume, the host's current glucose concentration, the host's bodily response to food, the host's activity level, and the host's alcohol intake. The various examples in this article pertain to arrangements for hosts receiving bolus doses, for example, using analyte sensors and / or analyte data detected by analyte sensors.

[0169] Figure 1 This is a diagram illustrating an example of an environment 100 including an analyte sensor system 102. The analyte sensor system 102 is coupled to a host 101, which may be a human patient. In some instances, the host 101 is a diabetic patient suffering from temporary or permanent diabetes or other health conditions that make analyte monitoring useful. It should be understood that the environment 100 includes a variety of components that can be used in various different combinations to implement the systems and methods described herein.

[0170] The analyte sensor system 102 includes an analyte sensor 104. In some instances, the analyte sensor 104 is or includes a glucose sensor configured to measure glucose concentration in a host 101. The analyte sensor 104 can be exposed to the analyte at the host 101 in any suitable manner. In some instances, the analyte sensor 104 is fully implantable under the skin of the host 101. In other instances, the analyte sensor 104 is wearable on the body of the host 101 (e.g., on the body but not under the skin). Furthermore, in some instances, the analyte sensor 104 is a percutaneous device (e.g., having a sensor at least partially located under or within the host skin). It should be understood that the apparatus and methods described herein can be applied to any apparatus capable of detecting the concentration of an analyte such as glucose and providing an output signal representing the analyte concentration.

[0171] According to various embodiments, the glucose detected can be D-glucose. However, glucose, as well as any stereoisomers or mixtures of stereoisomers of glucose in open-chain, cyclic, or mixed forms, can be detected. Figure 1 In some instances, the analyte sensor system 102 also includes sensor electronics 106. In some instances, sensor electronics 106 and the analyte sensor 104 are housed in a single integrated package. In other instances, the analyte sensor 104 and sensor electronics 106 are separate components or modules. For example, the analyte sensor system 102 may include a disposable (e.g., single-use) sensor mounting unit. Figure 3 The sensor mounting unit may include an analyte sensor 104, components for attaching the sensor 104 to a host (e.g., an adhesive pad), and / or be configured to receive an analyte sensor 104. Figure 2 The mounting structure of some or all of the sensor electronics units in the sensor electronics 106 shown is illustrated. The sensor electronics units are reusable.

[0172] The analyte sensor 104 may use any known method, including invasive, minimally invasive, or non-invasive sensing techniques (e.g., optically excited fluorescence, microneedles, transdermal glucose monitoring), to provide a raw sensor signal indicating the concentration of the analyte in the host 101. The raw sensor signal may be converted into calibrated and / or filtered analyte concentration data to provide a useful value of the analyte concentration (e.g., an estimated blood glucose level) to a user, such as the host or a caregiver (e.g., a parent, relative, guardian, teacher, doctor, nurse, or any other individual interested in the health of the host 101).

[0173] In some instances, the analyte sensor 104 is or includes a continuous glucose sensor. A continuous glucose sensor may be or includes a subcutaneous, transdermal (e.g., transdermal), and / or intravascular device. In some embodiments, such a sensor or device may cyclically (e.g., periodically or intermittently) analyze sensor data. The glucose sensor can use any glucose measurement method, including enzymatic, chemical, physical, electrochemical, spectrophotometric, optical rotation, calorimetric, iontophoresis, radiation, immunochemistry, etc. In various instances, the analyte sensor system 102 may be or includes components available from DexCom, Inc. (e.g., DexCom G5) in San Diego, California. TM Sensor or Dexcom G6 TM (sensor or any variant thereof), from Abbott TM (For example, Libre) TM (sensor) or from Libre TM (For example, Enlite) TM A continuous glucose sensor (the sensor) obtains this information.

[0174] In some instances, the analyte sensor 104 includes an implantable glucose sensor, as described with reference to U.S. Patent 6,001,067 and U.S. Patent Publication No. US-2005-0027463-A1, which are incorporated herein by reference. In some instances, the analyte sensor 104 includes a transdermal glucose sensor, as described with reference to U.S. Patent Publication No. US-2006-0020187-A1, which are incorporated herein by reference. In some instances, the analyte sensor 104 may be configured to be implanted in or outside the host blood vessel, as described in U.S. Patent Publication No. US-2007-0027385-A1, filed October 4, 2006; U.S. Patent Publication No. US-2008-0119703-A1, co-pending; U.S. Patent Publication No. US-2008-0108942-A1, filed March 26, 2007; and U.S. Patent Application No. US-2007-0197890-A1, filed February 14, 2007, all of which are incorporated herein by reference. In some instances, the continuous glucose sensor may include a percutaneous sensor as described in U.S. Patent 6,565,509 to Say et al., which is incorporated herein by reference. In some instances, the analyte sensor 104 may include a continuous glucose sensor, such as a subcutaneous sensor as described in U.S. Patent 6,579,690 to Bonnecaze et al. or U.S. Patent 6,484,046 to Say et al., which are incorporated herein by reference. In some instances, the continuous glucose sensor may include a refillable subcutaneous sensor, such as described in U.S. Patent 6,512,939 to Colvin et al., which is incorporated herein by reference. The continuous glucose sensor may include an intravascular sensor, such as described in U.S. Patent 6,477,395 to Schulman et al., which is incorporated herein by reference. The continuous glucose sensor may include an intravascular sensor, such as described in U.S. Patent 6,424,847 to Mastrototaro et al., which is incorporated herein by reference.

[0175] Environment 100 may also include a second medical device 108. The second medical device 108 may be or include a drug delivery device, such as an insulin pump or insulin pen. In some instances, 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 3-axis accelerometer), or an acoustic sensor (e.g., to capture ambient sound or sound within the body). The medical device 108 may be wearable, such as on a watch, glasses, contact lenses, patches, wristbands, ankle straps, or other wearable items, or may be integrated into a handheld device (e.g., a smartphone). In some instances, the medical device 108 includes a multi-sensor patch that may, for example, detect one or more of the following: analyte levels (e.g., glucose, lactate, insulin, or other substances), heart rate, respiration (e.g., using impedance), activity (e.g., using an accelerometer), posture (e.g., using an accelerometer), skin conductance response, and tissue fluid levels (e.g., using impedance or pressure).

[0176] In some instances, the analyte sensor system 102 and the second medical device 108 communicate 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 signal 110. For example, the analyte sensor system 102 may be configured to communicate using radio frequency (e.g., Bluetooth, Medical Implantable 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 Communications (GSM)) or via wired connections (e.g., serial, parallel, etc.).

[0177] In some instances, environment 100 also includes a wearable sensor 130. The wearable sensor 130 may include sensor circuitry (e.g., sensor circuitry configured to detect glucose concentration or other analyte concentration) and communication circuitry, which may be, for example, NFC circuitry. In some instances, information from the wearable sensor 130 can 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 its communication circuitry, for example, when the user device 132 is placed near the wearable sensor 130. For example, swiping the user device 132 on the sensor 130 can retrieve sensor data from the wearable sensor 130 using NFC or other suitable wireless communication. The use of NFC communication can reduce the power consumption of the wearable sensor 130, which can reduce the size of the power source (e.g., a battery or capacitor) in the wearable sensor 130 or extend its lifespan. In some instances, the wearable sensor 130 may be worn on the upper arm as shown in the figure. In some instances, wearable sensor 130 may additionally or alternatively be located on the patient's upper torso (e.g., on the heart or lungs), which may, for example, help detect heart rate, breathing, or posture. Wearable sensor 136 may also be located on the lower extremities (e.g., on the legs).

[0178] In some instances, environment 100 also includes a wearable device 120, such as a watch. Wearable device 120 may include activity sensors, heart rate monitors (e.g., light-based or electrode-based sensors), breathing sensors (e.g., sound-based or electrode-based sensors), location sensors (e.g., GPS), or other sensors. Wearable device 120 may communicate with user device 132, smart device 112, tablet computing device 114, or other suitable computing devices. For example, user device 132, smart device 112, or other suitable computing devices may execute applications that communicate with wearable device 120 and provide host 101 with data captured by and / or derived from one or more sensors of wearable device 120.

[0179] In some instances, sensor arrays or networks may be associated with a 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 communication (e.g., Bluetooth, MICS, NFC, or any other option described above). The additional wearable sensor 130 may be any of the examples described above with respect to medical device 108. The analyte sensor system 102, medical device 108, and additional sensor 130 on host 101 are provided for illustration and description purposes and are not necessarily drawn to scale.

[0180] Environment 100 may also include one or more computing devices, such as a handheld smart device (e.g., a smart device) 112, a tablet computing device 114, a smart pen 116 (e.g., an insulin delivery pen with 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. in San Diego, California), any of which may communicate with the analyte sensor system 102 via wireless communication signal 110 and may also communicate with a server system (e.g., a remote data center) or a remote terminal 128 via network 124 to facilitate communication with remote users (not shown), such as technical support staff or clinicians.

[0181] In some instances, environment 100 includes server system 126. Server system 126 may include one or more computing devices, such as one or more server computing devices. In some instances, server system 126 is used to collect analyte data from analyte sensor system 102 and / or analyte or other data from multiple other devices, analyze the collected data, generate or apply a general or individualized model of glucose concentration, and transmit such analysis, model, or information based thereon back to one or more devices in environment 100. In some instances, server system 126 collects inter-host and / or intra-host adaptation data to generate one or more adaptation features, as described herein.

[0182] Environment 100 may also include a wireless access point (WAP) 138 for communicatively coupling one or more of the analyte sensor system 102, network 124, server system 126, medical device 108, or any of the aforementioned peripheral devices. For example, WAP 138 may provide Wi-Fi and / or cellular connectivity within environment 100. Other communication protocols such as NFC or Bluetooth may also be used between devices in environment 100.

[0183] Various devices in environment 100 can execute injection applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H. Injection applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H perform functions related to managing one or more insulin injection doses for host 101, as described herein. In some instances, this includes determining the injection dose for host 101. For example, injection applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H can receive injection input parameters, such as the host's glucose concentration, the amount of carbohydrates to be consumed, etc., and output the injection dose, for example, in units of insulin. In some instances, the bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H can also detect and / or characterize the bolus insulin dose, for example, to determine and / or optimize future treatment options for host 101.

[0184] The insulin bolus dose determined by the bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H can be provided to a drug delivery device, such as an insulin pump or other suitable drug delivery device included in medical device 108 and / or smart pen 116. The drug delivery device can provide the indicated bolus dose to host 101 directly (e.g., via an insulin pump) and / or indirectly (by setting the dose of insulin pen 116, which can then be used by the host or other suitable human user to administer the bolus insulin dose to the host).

[0185] exist Figure 1In environment 100, various injection applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H are executed by different computing devices, including medical device 108 (injection application 134A), user computing device 132 (injection application 134B), tablet computing device 114 (injection application 134C), smart device 112 (injection application 134D), computing device 118 (injection application 134E), medical device 122 (injection application 134F), and server system (injection application 134H). In some instances, injection applications 134A, 134B, 134C, 132D, 132E, 134F, 134G, and 134H are executed on only one of these devices to provide some or all of the functions described herein. For example, host 101 can utilize the injection application 134A executed at medical device 108 to determine the insulin injection dose or provide other functions described herein. In other instances, injection applications 134A, 134B, 134C, 132D, 132E, 134F, 134G, and 134H executed at different devices can operate independently or in combination with each other to perform the functions described herein.

[0186] The bolus dose determined by bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H may include a corrected portion, a dietary portion, or both. A bolus dose that includes only the corrected portion is referred to herein as a corrected bolus. A bolus dose that includes a dietary portion is referred to herein as a dietary bolus. A dietary bolus may or may not include a corrected portion.

[0187] The correction component of the bolus dose is used to correct for deviations from the target glucose concentration of the host 101. It can be used by bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, 134H. An example formula for determining the correction component is given by equation [1]: [1]

[0189]

[0190] In equation [1], CC is the correction component. GC M This is the measured glucose concentration of host 101, indicating the glucose concentration of host 101 at or approximately at the time of receiving the bolus dose. In some instances, the measured glucose concentration is indicated as a value named in milligrams per deciliter (mg / dL). In some instances, the measured glucose concentration is GC... MIt is based on measurements performed by the analyte sensor 104. GC T The target glucose concentration is the desired glucose concentration for host 101. The target glucose concentration is the glucose concentration that is expected to be determined. The target glucose concentration may be selected for host 101, for example, by input from a physician or medical professional. In some instances, the target glucose concentration is selected based on the host's age, sex, weight, or other characteristics. In equation [1], ISF is the insulin sensitivity factor of host 101. The ISF of host 101 indicates the amount of glucose concentration reduction per unit of insulin. For example, ISF can be expressed in mg / dL per unit of insulin. CC in equation [1] refers to the correction component and is expressed in insulin units.

[0191] The bolus dose of the meal portion is used to cover the food consumed by host 101. When host 101 consumes food, the host 101's body converts the food into glucose. This increases the host's glucose concentration. The host 101's body uses insulin to process glucose, either as energy or as fat storage. The bolus dose of the meal portion provides some or all of the insulin that host 101 needs to process the meal. An example formula for determining the bolus dose of the meal portion is given by the following equation [2]: [2]

[0193]

[0194] In equation [2], MC is the dietary portion and is expressed as units of insulin. C is a measure of the carbohydrates consumed from the diet. C can be expressed in different appropriate units, but is usually expressed as the mass of carbohydrates consumed in grams. One gram of carbohydrate is sometimes called a “carb”. In reality, the body can convert other components of the diet into glucose, such as protein, fat, etc. However, in many applications, because the glucose effect of protein and other food types is smaller and more delayed than that of carbohydrates, the appropriate dietary portion can be determined by considering only carbohydrates. However, in some instances, the estimated dietary portion is determined by considering carbohydrates as well as other components of the diet (e.g., protein, fat, etc.).

[0195] ICR is the ratio of insulin to carbohydrates in host 101. ICR indicates the number of insulin units required by host 101's body to process a unit of food. In equation [2], which uses grams of carbohydrates to represent a unit of food, ICR is expressed as grams of carbohydrates per unit of insulin. For the same patient / host 101, ICR varies from patient to patient and even over time. ICR can also be affected by environmental or behavioral factors. For example, if host 101 has been exercising or plans to exercise, host ICR can be effectively reduced (by reducing food intake). Other behavioral factors, such as alcohol consumption, also affect ICR.

[0196] As described herein, the bolus dose may include a dietary portion, a corrected portion, or both. Furthermore, in some instances, bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H may consider factors other than those in Equations 1 and 2. For example, bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H may also consider plate insulin (IOB), trend adjustment, plate carbohydrate (COB), and / or other factors. IOB indicates the amount of insulin present and active in the body of host 101. An increased IOB may tend to reduce the bolus dose of host 101.

[0197] Trend adjustment is based on how the host's measured glucose concentration changes affect the insulin bolus dose. Consider a first instance where the host's glucose concentration is 120 mg / dL and decreasing at a rate of 10 mg / dL per minute, and a second instance where the host's glucose concentration is 120 mg / dL and stable. It should be understood that the same bolus dose may not be indicated for the two instances. All other things being equal, applying trend adjustment may tend to result in a lower bolus dose for the first instance than for the second instance. Various techniques can be used in conjunction with trend adjustment when determining the bolus dose, including, for example, the Scheiner method, the Pettus / Edelman method, the Klonoff / Kerr method, the Endocrine Society method, etc.

[0198] COB is an indicator of carbohydrates previously ingested by the host but not yet processed by the body. All other things being equal, the presence of COB may tend to increase the bolus dose. Further details are described herein of bolus applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H programmed to utilize IOB, COB, and / or trend adjustments.

[0199] Figure 2 It shows including Figure 1A diagram illustrating an example of a medical device system 200 with an analytical sensor system 102. Figure 2 In one example, the analyte sensor system 102 includes sensor electronics 106 and sensor mounting unit 290. While a specific example of the component division between sensor mounting unit 290 and sensor electronics 106 has been shown, it should be understood that some examples may include additional components in sensor mounting unit 290 or sensor electronics 106, and some components shown in sensor electronics 106 (e.g., a battery or supercapacitor) may alternatively or additionally (e.g., redundantly) be provided in sensor mounting unit 290.

[0200] exist Figure 2 In the example shown, sensor mounting unit 290 includes analyte sensor 104 and battery 292. In some examples, sensor mounting unit 290 may be replaceable, and sensor electronics 106 may include debounce circuitry (e.g., gates with hysteresis or delay) to avoid cyclic execution of power-on or power-off processes, such as when the battery is repeatedly connected and disconnected, or to avoid processing of noise signals associated with battery removal or replacement.

[0201] Sensor electronics 106 may include electronic components configured to process sensor information, such as raw sensor signals, and generate corresponding analyte concentration values. Sensor electronics 106 may, for example, include electronic circuitry associated with measuring, processing, storing, or transmitting continuous analyte sensor data, including anticipated algorithms associated with the processing and calibration of the raw sensor signals. Sensor electronics 106 may include hardware, firmware, and / or software capable of measuring analyte levels via a glucose sensor. The electronic components may be mounted to a printed circuit board (PCB) and can take various forms. For example, the electronic components may take the form of integrated circuits (ICs), such as application-specific integrated circuits (ASICs), microcontrollers, and / or processors.

[0202] exist Figure 2In one example, sensor electronics 106 includes measurement circuitry 202 (e.g., a voltage regulator) coupled to analyte sensor 104 and configured to cyclically acquire analyte sensor readings using analyte sensor 104. For example, measurement circuitry 202 can continuously or cyclically measure a raw sensor signal indicating the current at analyte sensor 104 between the working electrode and a reverse or reference (e.g., anti-reference) electrode. Sensor electronics 106 may include gate circuitry 294 for gating the connection between measurement circuitry 202 and analyte sensor 104. For example, analyte sensor 104 can accumulate charge during an accumulation period. After the accumulation period, gate circuitry 294 is deactivated, allowing measurement circuitry 202 to measure the accumulated charge. Gating analyte sensor 104 can improve the performance of sensor system 102 by generating a greater signal-to-noise ratio or interference ratio (e.g., because charge accumulates from the analyte reaction; however, interfering sources such as acetaminophen, present near a glucose sensor, do not accumulate or accumulate less charge from the analyte reaction).

[0203] The sensor electronics 106 may also include a processor 204. The processor 204 is configured to retrieve instructions 206 from memory 208 and execute instructions 206 to control various operations within 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 regulator at the measurement circuit 202, interpret the raw sensor signal from the analyte sensor 104, and / or compensate for environmental factors.

[0204] Processor 204 may also store information in or retrieve information from data storage memory 210. In various instances, data storage memory 210 may be integrated with 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.

[0205] Sensor electronics 106 may also include a sensor 212 that may be coupled to processor 204. Sensor 212 may be a temperature sensor, accelerometer, or other suitable sensor. Sensor electronics 106 may also include a power source such as a capacitor or battery 214, which may be integrated into sensor electronics 106 or may be removable or part of a separate electronic unit. Battery 214 (or other power storage components, such as capacitors) may optionally be recharged via a wired or wireless (e.g., inductive or ultrasonic) recharging system 216. Recharging system 216 may harvest energy or may receive energy from an external or onboard source. In various instances, the recharging circuitry may include triboelectric charging circuitry, piezoelectric charging circuitry, RF charging circuitry, photoelectric charging circuitry, ultrasonic charging circuitry, thermal charging circuitry, heat harvesting circuitry, or circuitry that harvests energy from communication circuitry. In some instances, the recharging circuitry may use power supplied by a replaceable battery (e.g., a battery provided by the basic components) to recharge a rechargeable battery.

[0206] Sensor electronics 106 may also include one or more supercapacitors in the sensor electronics unit (as shown) or sensor mounting unit 290. For example, the supercapacitor may allow energy to be drawn from battery 214 in a highly consistent manner to extend the lifespan of battery 214. After the supercapacitor has delivered energy to the communication circuitry or processor 204, battery 214 may recharge the supercapacitor, making it ready to deliver energy during subsequent high-load cycles. In some instances, the supercapacitor may be configured in parallel with battery 214. The device may be configured to preferentially draw energy from the supercapacitor, in contrast to battery 214. In some instances, the supercapacitor may be configured to receive energy from a rechargeable battery for short-term storage and transfer energy to a rechargeable battery for long-term storage. The supercapacitor may extend the operating life of battery 214 by reducing strain on battery 214 during high-load cycles.

[0207] The sensor electronics 106 may also include wireless communication circuitry 218, which may include, for example, a wireless transceiver operatively coupled to an antenna. Wireless communication circuitry 218 may be operatively coupled to processor 204 and may be configured to communicate wirelessly with one or more peripheral devices or other medical devices such as insulin pumps or smart insulin pens.

[0208] exist Figure 2 In one example, the medical device system 200 also includes an optional peripheral device 250. The peripheral device 250 can be any suitable user computing device, such as a wearable device (e.g., an activity monitor), such as wearable device 120. In other examples, the peripheral device 250 can be… Figure 1The handheld smart device shown (e.g., a smartphone or other device such as a proprietary handheld device available from Dexcom), tablet computing device 114, smart pen 116, or computing device 118.

[0209] Peripheral device 250 may include UI 252, memory circuitry 254, processor 256, wireless communication circuitry 258, sensor 260, or any combination thereof. Peripheral device 250 may not necessarily include... Figure 2 All components are shown. Peripheral device 250 may also include a power source, such as a battery.

[0210] For example, UI 252 can be provided using any suitable one or more input / output devices of peripheral device 250, such as a touchscreen interface, a microphone (e.g., for receiving voice commands) or speaker, vibration circuitry, or any combination thereof. UI 252 can receive information (e.g., instructions, glucose values) from a host or another user. UI 252 can also deliver information to a host or other user, for example, by displaying UI elements at UI 252. For example, UI elements can indicate glucose or other analyte concentration values, glucose or other analyte trends, glucose or other analyte alarms, etc. Trends can be indicated by UI elements such as arrows, graphics, charts, etc.

[0211] Processor 256 may be configured to present information to a user or receive input from a user via UI 252. Processor 256 may also be configured to store and retrieve information in memory circuitry 254, such as communication information (e.g., pairing information or data center access information), user information, sensor data or trends, or other information. Wireless communication circuitry 258 may include a transceiver and an antenna configured to communicate via a wireless protocol, such as any wireless protocol described herein. Sensor 260 may include, for example, an accelerometer, temperature sensor, position sensor, biosensor or glucose sensor, blood pressure sensor, heart rate sensor, respiration sensor, or other physiological sensor.

[0212] Peripheral device 250 may be configured to receive and display sensor information that can be transmitted by sensor electronics 106 (e.g., in a customized data packet transmitted to a display device based on its respective preferences). Sensor information (e.g., blood glucose concentration level) or alarms or notifications (e.g., “high glucose level,” “low glucose level,” or “rate of decline alarm”) may be transmitted via UI 252 (e.g., via visual display, sound, or vibration). In some instances, peripheral device 250 may be configured to display or otherwise transmit sensor information while it is being transmitted from sensor electronics 106 (e.g., in a data packet transmitted to a corresponding display device). For example, peripheral device 250 may transmit processed data (e.g., an estimated analyte concentration level determined by processing raw sensor data) such that the receiving device does not need to further process the data to determine available information (e.g., the estimated analyte concentration level). In other instances, peripheral device 250 may process or interpret the received information (e.g., to issue an alarm based on glucose values ​​or glucose trends). In various instances, the peripheral device 250 may receive information directly from the sensor electronics 106 or via a network (e.g., via a cellular or Wi-Fi network, which receives information from the sensor electronics 106 or from a device communicatively coupled to the sensor electronics 106).

[0213] exist Figure 2 In this example, medical device system 200 includes an optional medical device 270. For example, medical device 270 may be used in addition to or in place of peripheral device 250. Medical device 270 may be or include any suitable type of medical or other computing device, including, for example... Figure 1 The illustrated medical device 108, peripheral medical device 122, wearable device 120, wearable sensor 130, or wearable sensor 136. Medical device 270 may include a UI 272, memory circuitry 274, processor 276, wireless communication circuitry 278, sensor 280, treatment circuitry 282, or any combination thereof.

[0214] Similar to UI 252, UI 272 can be provided using any suitable one or more input / output devices of medical device 270, such as a touchscreen interface, microphone or speaker, vibration circuitry, or any combination thereof. UI 272 can receive information (e.g., glucose values, alarm preferences, calibration codes) from a host or another user. UI 272 can also deliver information to a host or other user, for example, by displaying UI elements at UI 252. For example, UI elements can indicate glucose or other analyte concentration values, glucose or other analyte trends, glucose or other analyte alarms, etc. Trends can be indicated by UI elements such as arrows, graphics, charts, etc.

[0215] Processor 276 may be configured to present information to a user or receive input from a user via UI 272. Processor 276 may also be configured to store and retrieve information in memory circuitry 274, such as communication information (e.g., pairing information or data center access information), user information, sensor data or trends, or other information. Wireless communication circuitry 278 may include a transceiver and an antenna configured to communicate via a wireless protocol, such as any wireless protocol described herein.

[0216] Sensor 280 may include, for example, an accelerometer, temperature sensor, position sensor, biosensor or blood glucose sensor, blood pressure sensor, heart rate sensor, respiration sensor or other physiological sensor. Medical device 270 may include two or more sensors (or memory or other components), even when... Figure 2 Only one sensor 280 is shown in the example. 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 devices, therapeutic devices, or combinations thereof.

[0217] In instances where medical device 270 is or includes an insulin pump, the pump and analyte sensor system 102 may be in bidirectional communication (e.g., the pump may request a change in the analyte delivery protocol, such as requesting data points or requesting more frequently scheduled data), or the pump and analyte sensor system 102 may communicate using unidirectional communication (e.g., the pump may receive analyte concentration level information from the analyte sensor system). In unidirectional communication, glucose values ​​may be incorporated into an advertising message, which may be encrypted using a previously shared key. In bidirectional communication, the pump may request the analyte sensor system 102 to share or obtain and share values ​​in response to a request from the pump, and either or both of these communications may be encrypted using one or more previously shared keys. For one or more reasons, the insulin pump may use unidirectional communication with the pump to receive and track analyte (e.g., glucose) values ​​sent from the analyte sensor system 102. For example, the insulin pump may pause or activate insulin administration based on glucose values ​​below or above a threshold.

[0218] In some instances, 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 offer many different user interfaces, the content of data packets (e.g., the amount, format, and / or type of data to be displayed, alarms, etc.) can be customized (e.g., programmed differently by the manufacturer and / or by the end user) for each specific device. For example, now refer to... Figure 1For example, multiple different peripheral devices may directly communicate wirelessly with sensor electronics 106 (e.g., on-skin sensor electronics 106 physically connected to continuous analyte sensor 104) during a sensor session to enable multiple different types and / or levels of display and / or functions associated with displaying sensor information, or to save battery power in sensor system 102. One or more designated devices may communicate with analyte sensor system 102 and relay (i.e., share) information to other devices directly or via server system 126 (e.g., a network-connected data center).

[0219] Figure 3 This is a side view of an example analytical sensor 334 that can be implanted in a host. The mounting unit 314 can be adhered to the host's skin using an adhesive pad 308. The adhesive pad 308 may be formed of a stretchable material and can be removably attached to the skin using an adhesive. An electronic device unit 318 may be mechanically coupled to the mounting unit 314. In some instances, the electronic device unit 318 and the mounting unit 314 are positioned similarly to... Figure 1 and 2 The sensor electronics 106 and sensor mounting unit 290 are arranged in the manner shown.

[0220] Figure 4 This is an enlarged view of the distal portion of the analyte sensor 334. The analyte sensor 334 is adapted to be inserted under the host skin and can be mechanically coupled to the mounting unit 314 and electrically coupled to the electronics unit 318. Figure 4 The illustrated example analyzer sensor 334 includes an elongated conductor 341. The elongated conductor 341 may include a core on which various layers are positioned. 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 the first layer 338 are made of a single material (e.g., platinum). 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 above the working electrode and may cover the other layers and / or electrodes of the sensor 334, as described herein.

[0221] The first layer 338 may be formed of a conductive material. The working electrode (at window 339) is the exposed portion of the surface of the first layer 338. Therefore, the 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, and alloys thereof.

[0222] The second layer 340 surrounds at least a portion of the first layer 338, thereby defining the boundary of the working electrode. In some instances, the second layer 340 serves as an insulator and is formed of an insulating material, such as polyimide, polyurethane, poly(p-phenylene dimethyl) or any other suitable one or more insulating materials.

[0223] The analyte sensor 334 may include two (or more) electrodes, such as a working electrode exposed at layer 338 and window 339, and at least one additional electrode, such as a reference (e.g., anti-reference) electrode of layer 343. Figures 3 to 5 In some instances, the reference electrode also serves as the counter electrode, although other arrangements may include a separate counter electrode. While in some instances the analyte sensor 334 may be used with the mounting unit, in others it may be used with other types of sensor systems. For example, the analyte sensor 334 may be part of a system comprising a battery and sensor in a single package, and may optionally include, for example, near-field communication (NFC) circuitry.

[0224] Figure 5 yes Figure 4 A cross-sectional view of sensor 334 on plane 2-2 shows membrane system 332. Membrane system 332 may include multiple domains (e.g., layers). In one example, membrane system 332 may include an enzyme domain 342, a diffusion resistance domain 344, and a bioprotection domain 346 located around the working electrode. In some examples, a single diffusion resistance domain and bioprotection domain may be included in membrane system 332 (e.g., where the functions of both the diffusion resistance domain and the bioprotection domain are incorporated into one domain).

[0225] In some instances, the membrane system 332 also includes an electrode layer 347. The electrode layer 347 may be arranged to provide an environment conducive to electrochemical reactions between the working electrode and a reference (e.g., anti-reference) electrode. For example, the electrode layer 347 may include a coating that holds a layer of water at the electrochemically reactive surface of the sensor 334.

[0226] In some instances, sensor 334 can be configured for short-term implantation (e.g., from about 1 to 30 days). However, it should be understood that membrane system 332 can be modified for use in other devices, for example, by including only one or more domains or additional domains. For example, membrane system 332 may include multiple resistance layers or multiple enzyme layers. In some instances, resistance domain 344 may include multiple resistance layers, or enzyme domain 342 may include multiple enzyme layers.

[0227] The diffusion resistance domain 344 may include a semipermeable membrane that controls the flow of oxygen and glucose to the underlying enzyme domain 342. Therefore, the upper linear limit for glucose measurement is extended to a much higher value than that achieved without the diffusion resistance domain 344.

[0228] In some instances, membrane system 332 may include a bioprotective domain 346, also referred to as a domain or biointerface domain, which contains the base polymer. However, in some instances, membrane system 332 may also include multiple domains or layers, including, for example, electrode domains, interference domains, or cell disruption domains, as described in more detail elsewhere herein and in U.S. Patents 7,494,465, 8,682,608, and 9,044,199, which are incorporated herein by reference in their entirety.

[0229] It should be understood that, for example, sensing membranes modified for other sensors may include fewer or additional layers. For instance, in some instances, membrane system 332 may include an electrode layer, an enzyme layer, and two bioprotective layers, while in other instances, membrane system 332 may include an electrode layer, two enzyme layers, and a bioprotective layer. In some instances, the bioprotective layer may be configured to act as a diffusion resistance domain 344 and control the flux of the analyte (e.g., glucose) to the underlying membrane layer.

[0230] although Figures 4 to 5 The examples shown relate to circumferentially extended membrane systems, but the membranes described herein can be applied to any planar or non-planar surface, such as the substrate-based sensor structure of U.S. Patent No. 6,565,509 to Say et al., which is incorporated herein by reference.

[0231] In the example where the analyte sensor 334 is a glucose sensor, glucose analyte can be detected using glucose oxidase or another suitable enzyme, as described in more detail elsewhere herein. For example, glucose oxidase can react with glucose to produce hydrogen peroxide (H₂O₂). The oxidation / redox reaction pair, serving as the working and reference electrodes, generates a sensor current. The magnitude of the sensor current indicates the concentration of hydrogen peroxide, and thus also the concentration of glucose.

[0232] 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 glucose diffusivity through the sensor membrane system, the operating potential at the reference electrode, etc. The glucose diffusivity of the membrane system can vary over time, which can cause the sensor's glucose sensitivity to change or "drift" over time. For example, sensor drift can be compensated for by modeling the sensor drift and appropriately adjusting the calibration curve. For example, using the techniques described herein, variations in the operating potential at the reference (e.g., anti-reference) electrode, which are described in more detail elsewhere herein, can be mitigated and / or compensated for.

[0233] Figure 6 It means as Figures 3 to 5The diagram shows a schematic of the circuitry 600 illustrating the behavior of an example analyte sensor 334. As described herein, the interaction of hydrogen peroxide (generated from the interaction between the glucose analyte and glucose oxidase) with the working electrode (WE) 604 creates a voltage difference between the working electrode (WE) 604 and a reference (e.g., anti-reference) electrode (RE) 606 that drives the current. This current can constitute all or part of the original sensor signal, which is generated by, for example... Figures 1 to 2 The sensor electronics 106 measures and is used to estimate the concentration of the analyte (e.g., glucose concentration).

[0234] Circuit 600 also includes a double-layer capacitor (Cdl) 608, which appears between the working electrode (WE) 604 and the adjacent film ( Figure 6 Not shown in the image, see, for example, the one above. Figures 3 to 5 At the interface between the working electrode 604 and the adjacent membrane, due to the presence of two layers of ions with opposite polarities, a double-layer capacitance (Cdl) may appear at the interface between the working electrode 604 and the adjacent membrane. This may occur during the application of a voltage between the working electrode 604 and the reference (e.g., anti-reference) electrode. The equivalent circuit 600 may also include a polarization resistance (Rpol) 610, which may be relatively large and may be modeled as, for example, a static value (e.g., 100 megohms) or as a variable that varies as a function of glucose concentration level.

[0235] When a bias potential is applied to sensor circuitry 600, an estimated analyte concentration can be determined from the raw sensor signal based on the measured current (or charge flow) passing through analyte sensor membrane 612. For example, sensor electronics or another suitable computing device can use the raw sensor signal and the sensor's sensitivity (which correlates the detected current with glucose concentration levels) to generate the estimated analyte concentration. In some instances, the device also utilizes break-in features as described herein.

[0236] The variation in glucose diffusion rate over time presents a problem because there are two unknown variables in the system (the glucose concentration around membrane 612 and the glucose diffusion rate within membrane 612). For example, drift can be addressed using frequent glucometer calibration, but this need for calibration may be undesirable for various reasons (e.g., inconvenience to patients, cost, the possibility of inaccurate glucometer data, etc.).

[0237] Referring to the equivalent circuit 600, when a voltage is applied across the working electrode 604 and the reference (e.g., anti-reference) electrode 606, current can be considered to flow (forward or backward depending on polarity) through the transmitter's internal electronics (represented by R_Tx_internal) 611; through the reference (e.g., anti-reference) electrode (RE) 606 and the working electrode (WE) 604, which can be designed to have relatively low resistance; and through the sensor membrane 612 (Rmembr, which is relatively small). Depending on the state of the circuit, current may also flow through or into a relatively large polarization resistor 610 (which is represented as a fixed resistance, but may also be a variable resistance that varies with the body's glucose levels, where higher glucose levels provide a smaller polarization resistance), or into a double-layer capacitor 608 (i.e., charging a double-layer thin-film capacitor formed at the working electrode 604), or both.

[0238] The membrane's impedance (or conductivity) (Rmembr) 612 is related to the electrolyte mobility in the membrane, which in turn is related to the glucose diffusivity in the membrane. As impedance decreases (i.e., conductivity increases as electrolyte mobility in membrane 612 increases), glucose sensitivity increases (i.e., higher glucose sensitivity means that a given glucose concentration will produce a larger signal in the form of a larger current or charge flow). Impedance, glucose diffusivity, and glucose sensitivity are further described in U.S. Patent Publication No. US2012 / 0262298, the entire contents of which are incorporated herein by reference.

[0239] The various arrangements described herein relate to arrangements for setting up bolus configuration parameters used to determine the bolus insulin dose for the host. Booster configuration parameters are input parameters used to generate the bolus dose for the host. Example bolus configuration parameters include insulin sensitivity factor (ISF), insulin-to-carbohydrate ratio (ICR), and target glucose concentration (GC). T As described herein with respect to equations [1] and [2]. For example, as described herein, other injection configuration parameters include parameters for utilizing plate insulin, plate carbohydrates, trend adjustment, or other features. As described herein, injection configuration parameters depend on the individual physiological function of the host 101 and can even vary over time.

[0240] Sometimes, when host 101 starts using a new betting calculator, such as one implemented by betting applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H, host 101 will have input fields such as ISF, ICR, and GC that can be entered into betting applications 134A, 134B, 134C, 134D, 134E, 134F, 134G, and 134H. TThe initial values ​​of the injection configuration parameters, etc. For example, host 101 may have pre-calculated the injection dose using different injection calculators, manually calculated the injection dose, and / or the healthcare provider may have recommended specific configuration parameters. This allows host 101 to copy previously used injection configuration parameters to a new injection calculator.

[0241] However, in some instances, host 101 begins using the injection calculator without knowing the previously used injection configuration parameters. Sometimes host 101 is completely unaware of the injection configuration parameters used with prior techniques. Moreover, sometimes host 101 has previously used different methods for determining the injection dose, which do not use the same injection configuration parameters as the expected injection calculator.

[0242] For example, some patients use bolus dosing techniques based on a simple trial-and-error approach that don't translate well to bolus calculators. For instance, some patients receive the same bolus dose (e.g., via meal) regardless of the specific food consumed in the meal. Other patients receive bolus doses that are coarse adjustments to the patient's current glucose concentration, rather than coarse adjustments to the amount of food consumed. Still others receive fixed bolus doses for specific meal sizes (e.g., X units of insulin for a small meal, Y units for a lunch, and Z units for a large meal).

[0243] The various examples described herein address these and other problems by implementing a betting application configured to determine at least one set of betting configuration parameters for host 101. Figure 7 This diagram illustrates an example of environment 700, demonstrating the use of an injection application 734 to determine and utilize a set of at least one injection configuration parameters for host 701. In this example, host 701 utilizes computing device 702 to execute the injection application 734. Computing device 702 can be any suitable computing device, such as medical device 108, user computing device 132, tablet computing device 114, smart pen 116, smart device 112, medical device 122, computing device 118, remote terminal 128, and / or server system 126.

[0244] The computing device 702 may include an analyte sensor system 712 and a delivery system 714 and / or communicate with said analyte sensor system and delivery system. Similar to the analyte sensor system 102, the analyte sensor system 712 can detect an analyte at the host 701, such as the glucose concentration of the host 701. The delivery system 714 is configured to deliver an bolus dose to the host 701. For example, the delivery system 714 may be or include an insulin pen, an insulin pump, or other suitable delivery system. An injection application 734 generates an injection application user interface 703 provided to the host 701. The injection application user interface 703 may include visual and / or auditory elements to provide information to and / or receive information from the host 701. Figure 7 In this configuration, the injection application 734 is configured to generate a set of at least one injection configuration parameters for generating an injection dose for the host 701. The set of at least one injection configuration parameter may include one injection configuration parameter and / or more than one injection configuration parameter.

[0245] exist Figure 7 In one example, the betting application 734 uses a set of questions, which may include adaptive questions, to determine betting configuration parameters. The betting application 734 may determine the betting configuration parameters, for example, during setup. Based on the adaptive question set, questions are selected based on the answers provided by the host 701 to previous questions. For example, the first question may ask the host 701 to provide a description of the betting determination technique currently used by the host 701. Subsequent questions may be selected based on the host's current betting determination technique.

[0246] exist Figure 7 In the examples, multiple instance screens 704, 706, and 708 of the insulin injection application user interface 703 are shown. The first screen 704 of the insulin injection application user interface 703 may present a first question to the host 701. For example, the first question may ask the host 701 about information regarding the host's previous insulin injection determination techniques. The first question may be arranged in a format that is easy for the host 701 to understand and answer. For example, the first question may ask the host 701, "Do you use formulas or equations to calculate insulin injection doses?" The host 701 provides the answer to the first question via the insulin injection application user interface 703, for example, using an input device such as a microphone, keyboard, touchpad, etc., of the computing device 702. In another example, the first question may be about a characteristic of the host 701, such as "What is your weight?"

[0247] Upon receiving a response to the first question, the betting application 734 selects a second betting configuration parameter question and provides the host 701 with a second screen 706 instructing the host to answer the second betting configuration parameter question. The second betting configuration parameter question is based on the answer to the first betting configuration parameter question provided. For example, if the host 701 provides a first answer instructing the host 701 to use a formula to calculate the bet, the second question may specifically require the host 701 to currently use the ISF, ICR, or GC. T If host 701 provides a first answer instructing host 701 not to use a formula to calculate the insulin bolus dose, then the second question may pose a question providing a rough indication of bolus configuration parameters. For example, the second question may request host 701 to provide an example diet and example bolus that will be used to cover the diet under the host's previous bolus determination technique. In some instances, host 701 is prompted to provide an image of the example diet. The bolus application 734 can derive nutritional information (e.g., the amount of carbohydrates) from the image. In some instances, the image is captured by a camera or other image sensor incorporated into the delivery system 714. Although in Figure 7 Two questions are described, but in some instances, additional adaptive questions may be provided, and the host 701 provides the answers to these additional questions. Upon receiving answers to one or more betting configuration parameter questions, the betting application 734 determines parameters such as ISF, ICR, or GC. T A set of one or more push configuration parameters, etc.

[0248] When determining a set of one or more injection configuration parameters, the injection application 734 may provide an injection calculator UI screen 708. The injection calculator UI screen 708 is provided to the host 701 when, for example, an injection dose is requested by the host 701 and / or the injection application 734 (e.g., in response to the detection of an uncovered meal or a desired correction). The host 701 may provide injection input parameters, such as the amount of carbohydrates consumed or to be consumed. In some instances, the injection application 734 receives the glucose concentration of the host 701 from the analyte sensor system 712. Based on the injection input parameters and injection configuration parameters, the injection application 734 uses any suitable technique, including, for example, the techniques described herein, to determine the injection dose for the host 701.

[0249] The determined bolus dose can be indicated to the host 701 via the bolus application user interface 703. The host 701 can then receive the determined insulin bolus dose using a syringe, insulin pen, insulin pump, or other suitable delivery system. In some instances, the bolus application 734 provides an indication of the determined bolus dose to the delivery system 714. In response, the delivery system 714 can deliver the bolus dose and / or configure itself to deliver the bolus dose. In instances where the delivery system 714 is or includes an insulin pen, the insulin pen can be configured to deliver the determined bolus dose. The host 701 can use the pen to deliver the determined bolus dose. In some instances where the delivery system 714 is or includes an insulin pump, the insulin pump can deliver the determined bolus with or without further input from the host 701.

[0250] In some instances, the injection application 734 requests data from the host 701 via UI 703 describing the previous diet (e.g., the amount of carbohydrates in the previous diet) and the associated injection dose received by the host 701 for the previous diet. The injection application 734 may use this data, alone or in combination with answers to other questions, to derive injection configuration parameters.

[0251] Figure 8 This is a flowchart illustrating an example of a processing flow 800, as described herein, that can be executed by the betting application 734 to determine a set of one or more betting configuration parameters. At operation 802, the betting application 734 queries the host 701 to provide data describing the current betting technique used by the host 701. Based on the answers provided by the host 701, the betting application 734 selects a set of questions for further questions. The selected set of questions includes one or more questions based on the answers provided by the host 701 to the questions in operation 802. The selected set of questions may include questions related to the current betting technique, characteristics of the host 701 (e.g., weight, height, etc.), or any other suitable topics for determining the betting calculator parameters. At operation 806, the betting application 734 executes one or more questions from the set of questions selected in operation 804.

[0252] At operation 808, the injection application 734 determines whether the answer it has received from the host 701 is sufficient to determine all the injection configuration parameters required to determine the injection dose of the host 701. For example, as described herein, if the injection application 734 determines that it can determine all the injection configuration parameters, it can do so, and operation 810 uses the determined parameters to calculate the injection dose of the host 701.

[0253] If the referencing application 734 does not have enough answers to determine the referencing configuration parameters, it may skip to operation 816, or optionally, determine at operation 812 whether there is an additional set of questions to be presented to the host 701. If the referencing application 734 does have enough answers to determine the referencing configuration parameters, it may execute the referencing parameter model at operation 816 (as described herein), or, optionally at operation 812, the referencing application 734 may determine whether there is an additional set of questions. If there is an additional set of questions, at operation 814, the referencing application 734 selects the next set of questions, and then at operation 806, executes one or more questions from the selected set. The additional set of questions selected at operation 814 may be based on one or more answers received from the host 701 to the previous set of questions.

[0254] If no additional set of questions is provided at operation 812 (or in an arrangement where operation 812 is omitted), then at operation 816, the injection application 734 may execute an injection configuration parameter model. The injection configuration parameter model can be any suitable type of model that associates the characteristics of host 701 with injection configuration parameters. In some instances, the model also associates the answers to the questions provided to the host at operation 806 with the injection configuration parameters, incorporating or substituting for host characteristics. Instance host characteristics that may be used by the model include weight, body mass index (BMI), diabetes diagnosis (e.g., type I or type II), other medications taken, type of insulin used, etc. The injection application 734 may query host 701 to provide one or more characteristics, for example, if these characteristics have not been provided in response to other queries previously. In some instances, host characteristics may be received in response to questions from the set of questions executed at operation 806. Figure 9 and 10 Describe further details about the instance model.

[0255] Figure 9 This is a flowchart illustrating an example of a question workflow 900 that can be executed through the injection application 734 to determine the injection configuration parameters of the host 701. For example, workflow 900 shows an arrangement in which questions can be presented to the host 701 to determine the injection configuration parameters.

[0256] At 902, the injection application 734 queries the host 701 (e.g., via the injection application user interface 703) to instruct information about a previously used injection determination technique employed by the host 701. In some instances, the injection application 734 queries the host 701 to instruct the host 701 on what to consider when determining the injection dose using a previously used injection determination technique. For example, the host 701 may determine the injection insulin dose based on the diet consumed at or near the time of injection (e.g., injection-related diet) and / or based on glucose concentration. An example problem for performing 902 is represented by Example Problem 1:

[0257] Example Question 1: The amount of insulin I take with each meal is:

[0258] (A) Based on my glucose concentration and dietary intake

[0259] (B) Based solely on my food intake

[0260] (C) I eat the same thing every time I have breakfast, lunch, or dinner.

[0261] (D) Every meal is the same.

[0262] In some instances, the query at position 902 may include more than one question, as in the following example questions 2 and 3:

[0263] Example Question 2: Did you use glucose concentration to determine the bolus?

[0264] Example Question 3: Do you use dietary intake to determine the bolus dose?

[0265] Based on one or more answers provided by host 701 to the inquiry at 902, injection application 734 selects the next set of one or more questions. If host 701 instructs him or her to use both the glucose concentration and dietary amount of the diet related to injection to determine injection using a previously used injection determination technique, then injection application 734 queries host 701 using question set 904. For example, at 912, injection application 734 queries host 701 to indicate whether the previously used injection determination technique includes the use of a formula. The use of a formula may indicate that host 701 already knows or is able to find direct values ​​for one or more injection configuration parameters. If host 701 instructs the previously used injection determination technique to use a formula, then injection application 734 queries host 701 for one or more direct questions at 920. Direct questions may include requiring host 701 to directly provide information such as ISF, ICR, GC, etc. TThe question concerns one or more injection configuration parameters. At 924, the injection application 734 determines whether the answer provided by the host 701 to the direct question at 920 provides all injection configuration parameters for determining the insulin injection dose for the host 701. If all injection configuration parameters are received, the injection application 734 can determine one or more insulin injection doses for the host 701 at operation 934.

[0266] If, at 912, host 701 instructs host 701 not to use a formula to determine the dose using the previously used dose determination technique (or if the direct question at 920 does not provide all the dose configuration parameters), then the dose application 734 selects a set of questions that include indirect questions about the diet and corrected dose portions. At 922, the dose application 734 queries host 701 for the selected indirect questions. The indirect questions may not directly query host 701 to provide dose input parameters, but may instead query host 701 for other information that can be used to derive the dose configuration parameters. Example indirect questions related to dietary dose portions are shown below:

[0267] Example Question 4: What is your typical lunch?

[0268] Example Question 5: If your glucose reaches the target,

[0269] How much insulin would you consume for a typical lunch as you described earlier?

[0270] Based on the answers to these questions, the injection application 734 is able to determine the insulin resistance rate (ICR) of host 701. For example, the injection application 734 can estimate the amount of carbohydrates in a typical lunch (e.g., grams of carbohydrates). Based on the insulin intake of host 701, the injection application 734 determines the ICR. For example, the ICR of host 701 can be or is based on the estimated carbohydrate intake of the diet multiplied by the indicated insulin intake. In some instances, versions of example questions 4 and 5 are asked for each meal of the day to determine the injection configuration parameters for a particular meal.

[0271] Furthermore, in some instances, the injection application 734 requests information about different instance meals in order to check the validity of the answers provided by the host 701. For example, the host 701 may be asked about multiple common lunches. If the ICRs obtained from different lunches are the same or within a threshold, the injection application 734 can determine that the obtained ICRs are valid. (If the ICRs from different instance meals are different but within a threshold, in some instances, the injection application 734 uses the average of the different ICRs or another set.) If the ICRs determined based on different meals are completely different from each other, the injection application 734 may consider all determined ICRs unreliable and discard them.

[0272] The injection application 734 can determine the reliability of different instance diets derived from the ICR in any suitable manner. For example, the injection application 734 can receive and / or be programmed to have a maximum acceptable error threshold in the ICR. This could be a constant, for example. The maximum acceptable error for an instance constant is when the instance diet does not generate an ICR greater than 2 g / unit compared to any other ICR. In some instances, the maximum acceptable error threshold is different for different age ranges. For example, 2 g / unit for hosts under eight years old, 5 g / unit for hosts aged 9 to 18 years old, and 10 g / unit for hosts over 18 years old. In other instances, the maximum acceptable error threshold is a multiple of the ISF (e.g., between 1 / 3 and 2 / 3 of the ISF, approximately 1 / 2 of the ISF).

[0273] An example of an indirect problem for determining the injection configuration parameters associated with the corrected injection component is given by the following example:

[0274] Example Question 6: When your blood sugar is higher than the target

[0275] When your insulin dose is 20 mg / dL, how do you adjust it during meals?

[0276] Example Question 7: When your blood sugar is higher than the target

[0277] When your insulin dose is 50 mg / dL, how do you adjust it during meals?

[0278] The injection application 734 can determine the ISF, for example, using answers to questions similar to those in Example Questions 6 and 7. In some instances, the injection application 734 checks the determined ISF, for example, by comparing the ISF indicated by the answers with multiple questions similar to those in Example Questions 6 and 7. If the determined ISFs are within each other's thresholds, the injection application 734 can use the determined ISF (or the average of similar ISFs or other sets) as an ISF injection configuration parameter. If the ISFs determined based on different questions are completely different from each other, the injection application 734 can consider all determined ISFs unreliable and discard them.

[0279] When the indirect dietary and glucose questions are queried at 922, at operation 926, the injection application 734 determines whether it has successfully determined the injection configuration parameters to determine the insulin injection dose for host 701. If yes, then at operation 934, the injection application 734 can determine the insulin injection dose. If no, then at operation 932, the injection application 734 can execute the model, as described in more detail herein.

[0280] Returning to reference 902, if host 701 instructs him or her to determine the bolus dose solely based on the dietary amount relevant to the bolus, then the bolus application 734 may select only the set of dietary questions 906 and, at 914, ask host 701 one or more indirect dietary amount questions. The indirect dietary amount questions may request host 701 to provide an example dietary description and the corresponding insulin dose, for example, similar to example questions 4 and 5 above. At 928, the bolus application 734 determines whether the answer to the indirect questions at 914 provides sufficient bolus configuration parameters to determine the insulin bolus dose for host 701. If yes, then at operation 934, the bolus application 734 may determine the insulin bolus dose. If no, then at operation 932, the bolus application 734 may execute a model, as described in more detail herein.

[0281] Returning to reference 902, if host 701 instructs him or her to determine the bolus dose solely based on their glucose concentration, then the bolus application 734 may select only the glucose question set 908 and, at operation 916, query host 701 with one or more indirect glucose questions. The indirect glucose questions may request host 701 to provide example insulin boluses provided at different glucose concentrations and / or with different deviations from the target glucose concentration, as in example questions 6 and 7 above. At 930, the bolus application 734 determines whether the answer to the indirect question at 916 provides sufficient bolus configuration parameters to determine the insulin bolus dose for host 701. If yes, then at operation 934, the bolus application 734 may determine the insulin bolus dose. If no, then at operation 932, the bolus application 734 may execute a model, as described in more detail herein.

[0282] If, at 902, host 701 instructs him or her to use a constant bolus dose independent of dietary intake or blood glucose, then in some instances, the bolus application 734 executes a model at 932 to generate bolus configuration parameters for host 701. This model can be a trained model, which can, for example, combine the following... Figure 10 The model is trained as described. In other instances, the model can be a manually designed model, a heuristic, or a set of heuristics. For example, the push application 734 can apply rules or a set of rules to the answers received in workflow 900.

[0283] Figure 10This is a flowchart illustrating an example of a process flow 1000 that can be executed by a betting application 734 to determine one or more betting configuration parameters using a model. At operation 1002, the betting application 734 trains the model using training data. Any suitable type of model can be trained, including, for example, regression models such as linear regression, multinomial regression, logistic regression, quantile regression, support vector regression, regression tree, principal component regression, etc. The training data can correlate various host characteristics with different values ​​of the betting configuration parameters. The training data can describe host 701 and / or can describe multiple different hosts. In some instances, operation 1002 precedes other operations of process flow 1000. For example, the model can be trained and the trained model stored at computing device 702. In some instances, the model is trained at another computing device (e.g., at server system 126) and provided to computing device 702 executing the betting application 734.

[0284] At operation 1004, the injection application 734 queries the host 701 using a set of questions, including one or more questions, to retrieve model input. Any suitable model input can be queried, including, for example, host weight, host BMI, host's diabetes diagnosis type, other medications the host 701 is taking, etc. At operation 1006, the injection application 734 uses the received model input to execute a trained model to generate one or more injection configuration parameters. At operation 1008, the injection application 734 uses the injection configuration parameters determined at operation 1006 to determine the injection dose of insulin for the host 701.

[0285] In some instances, in addition to determining the bolus dose itself, or instead of determining the bolus dose itself, an injection application is used to monitor and / or manage the host's bolus dose. The injection application can be configured to determine the effect of the bolus, such as glucose concentration correction, the amount of food covered by the bolus (e.g., the amount of carbohydrates), etc. This effect data can be displayed to the host or other users. The host or other users can use the bolus effect data for review. For example, if the host intends to cover a specific diet with the bolus dose, he or she will expect the bolus dose effect data to match the diet. Similarly, if the host intends to provide a given glucose concentration correction with the bolus dose, he or she will expect the displayed bolus effect data to match the expected correction.

[0286] Although in the context of determining the host's bolus dose... Figures 7 to 10Techniques for determining bolus configuration parameters are described herein, but some or all of the examples described herein can be used with respect to the basal dose. For example, the bolus and basal doses can be determined together in a single calculation, such that the bolus configuration parameters described herein are used to calculate the combined basal / bolus insulin dose, including the bolus and basal components. Furthermore, in some instances, some or all of the bolus configuration parameters described herein are related to determining the host's basal dose. Therefore, bolus application 1134 (or another suitable application) can determine the bolus configuration parameters as described herein and use them at least in part to determine the basal insulin dose.

[0287] Figure 11 This diagram illustrates an example of environment 1100, demonstrating the use of injection application 1134 to determine and utilize injection effect data. In this example, host 1101 utilizes computing device 1102 to execute injection application 1134. Computing device 1102 can be any suitable computing device, such as medical device 108, user computing device 132, tablet computing device 114, smart pen 116, smart device 112, medical device 122, computing device 118, remote terminal 128, and / or server system 126.

[0288] The computing device 1102 may include an analyte sensor system 1112 and a delivery system 1114 and / or communicate with said analyte sensor system and delivery system. Similar to the analyte sensor system 102, the analyte sensor system 1112 may detect an analyte at the host 1101, such as the glucose concentration of the host 1101. The delivery system 1114 is configured to deliver an injection dose to the host 1101. For example, the delivery system 1114 may be or include an insulin pen, an insulin pump, or other suitable delivery system. An injection application 1134 generates an injection application user interface 1103 provided to the host 1101. The injection application user interface 1103 may include visual and / or auditory elements to provide information to and / or receive information from the host 1101.

[0289] exist Figure 11 In this configuration, the injection application 1134 is configured to generate injection effect data describing the injection dose that has been or will be administered to the host 1101. The injection effect data may include, for example, glucose concentration correction associated with the injection dose, carbohydrate coverage associated with the injection dose, etc. Figure 11 An example screen 1104 of the injection application user interface 1103, which provides example injection effect information, is shown. In this example, the displayed injection effect information indicates that the planned or most recently administered injection dose will cover 124 grams of carbohydrates.

[0290] Figure 12This is a flowchart illustrating an example of a processing flow 1200 that can be executed by the injection application 1134 to determine and display injection effect data. At operation 1202, the injection application 1134 receives an instruction for the injection dose. The instruction for the injection dose can be received in any suitable manner. In some instances, the instruction for the injection dose is received from a delivery system 1114. Consider instances where the delivery system 1114 is or includes an insulin pen, for example… Figure 1 The smart pen 116. The host 1101 can configure the insulin pen to deliver a desired bolus dose. The insulin pen provides an indication of the bolus dose to the bolus application 1134 via a computing device 1102. The insulin pen can provide an indication of the bolus dose before or after administering the bolus dose to the host 1101. Consider delivery system 1114 as another example, which is or includes an insulin pump. The insulin pump can similarly provide an indication to the bolus application 1134 of the bolus dose to be delivered or already delivered. In some instances described more specifically herein, the bolus application 1134 is configured to detect the bolus using data received from the analyte sensor system 1112. For example, this document relates to... Figures 20 to 22 Describe an example used to detect the bolus dose and / or data about the bolus dose.

[0291] At operation 1204, the injection application 1134 determines the injection effect data. Injection effect data can be determined in various different ways. This article is about... Figures 13 to 15 An example is provided for determining injection effect data. At operation 1206, injection application 1134 displays injection effect data at injection application user interface 1103.

[0292] Figure 13 This is a flowchart illustrating an example of a process flow 1300, executed by the injection application 1134, to determine the injection dose and its effect data. Figure 13 In one instance, the injection application 1134 receives an instruction for the injection dose at operation 1302, as described herein.

[0293] At operation 1304, the injection application 1134 determines a glucose correction associated with the injection dose. The glucose correction can be determined in any suitable manner. In some instances, the injection application 1134 receives glucose concentration data from the analyte sensor system 1112, where the glucose concentration data indicates the glucose concentration of the host 1101. The injection application 1134 can determine the glucose correction by comparing the glucose concentration with the target glucose concentration (GC) of the host 1101. TThe glucose correction is determined by comparison. For example, if the host 1101's 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, a negative glucose correction is allowed. For example, if the host's current glucose concentration is lower than the target glucose concentration, the glucose concentration is negative.

[0294] At operation 1306, the bolus application 1134 determines the correction component of the bolus dose. In some instances, this includes using a formula that correlates glucose correction with the corresponding correction component, such as equation [1] above. In this instance, the glucose correction determined at operation 1304 may be equivalent to GC. M -GC T If the glucose correction is negative, the correction component can also be negative. When determining dietary portions, a negative correction component can be considered, as described below. In some instances, the negative correction component is not displayed to the host 1101 via the injection application user interface 1103.

[0295] At operation 1308, the bolus application 1134 uses the correction component determined at operation 1306 to determine the dietary portion of the bolus dose. The dietary portion can be the total bolus dose minus the correction component. In instances where the correction component is negative, the dietary portion is greater than the total bolus dose. At operation 1310, the bolus application 1134 determines the carbohydrate coverage of the dietary bolus. This can be determined using a formula that correlates the dietary portion with carbohydrates (e.g., grams of carbohydrates).

[0296] Figure 14 This is a flowchart illustrating an example of a process flow 1400, which can be executed by injection application 1134 to determine injection effect data for injection dose. At operation 1402, injection application 1134 receives an instruction for injection dose, as described herein.

[0297] At operation 1404, the injection application 1134 acquires dietary data. The dietary data can be received and / or determined in any suitable manner. In some instances, dietary data is received from host 1101. For example, host 1101 may provide a diet, such as a carbohydrate count of the diet. Host 1101 may input dietary data via the injection application user interface 1103. In other instances, the injection application 1134 receives an image of the diet. The image can be captured using a camera or other suitable image sensor of computing device 1102. In some instances, delivery system 1114 includes an insulin pen that includes an image sensor. Host 1101 uses the insulin pen to capture images of the diet sent from delivery system 1114 to computing device 1102. The injection application 1134 analyzes the image to determine data about the diet, such as an estimated carbohydrate count of the diet (e.g., grams of carbohydrates in the diet).

[0298] An estimated carbohydrate count or other data about the diet can be determined from an image of the meal using any suitable technology. For example, the annotation application 1134 (or other suitable application communicating with the annotation application 1134) can perform image recognition and / or classification algorithms to identify one or more food items depicted in the image. The annotation application 1134 or other suitable application can estimate the quantity of one or more food items, for example, based on the size depicted of the food items (e.g., relative to the size depicted of other objects in the image). The annotation application 1134 or other suitable application can access a database indicating the nutritional content of the detected food items, for example, in the detected quantities.

[0299] At operation 1406, the injection application 1134 determines the dietary portion of the injection dose. For example, the injection application 1134 determines the amount of insulin that will cover the diet described by the dietary data in any suitable manner (including as described herein). In some instances, the injection application 1134 utilizes a formula as shown in the above equation [2].

[0300] In some instances, the injection application utilizes a physiological model of host 1101 to determine the dietary portion of the injection dose. For example, injection application 1134 can use prior glucose concentration data describing host 1101 and prior dietary data describing one or more meals consumed by host 1101 at the time the prior glucose concentration data was collected to train the physiological model. Other training data that can be used by injection application 1134 to train the physiological model may include injection dose data indicating historical injection doses received by the host and other data describing host 1101, such as blood parameters, anthropometric (e.g., body size) values, the type of the host's gut microbiota, etc.

[0301] At operation 1408, the injection application 1134 determines a correction component for the injection dose. The correction component can be the injection dose minus the dietary portion. Consider an instance where the injection dose is 8 units and the dietary portion is 6 units. In this case, the correction component would be 2 units. In instances where the dietary portion equals the injection dose, the correction component is zero. Furthermore, in instances where the dietary portion is greater than the injection dose, the correction component is negative.

[0302] At operation 1410, the injection application 1134 determines the glucose correction for the injection dose. The glucose correction is the decrease in the glucose concentration of the host 1101 caused by the injection dose. The glucose correction can be determined using a formula as shown in equation [1] above or in any other suitable manner. In instances where the correction component is negative, the glucose correction may indicate that the host's glucose concentration will increase rather than decrease after the injection dose.

[0303] In some instances, processing steps 1300 and / or 1400 can be performed while also taking into account the host's basal insulin levels. For example, the injection application 1134 can receive basal dose data describing one or more basal doses received by the host. For example, the injection application 1134 can take into account the basal dose data to modify the dietary portion and / or correction portion of the determined injection effect data.

[0304] Figure 15 This is a diagram showing an example screen 1500 of the betting application user interface 1103, displaying betting effect data. Figure 15 In one instance, the injection application 1134 is configured to determine injection effect data including an estimated future glucose value and an estimated glucose trajectory. The estimated future glucose value is determined in any suitable manner. In some instances, the injection application 1134 determines the estimated future glucose value by considering dietary portions and correction portions provided by the analyte sensor system 1112 for the injection dose and the host's current glucose concentration. For example, the injection application 1134 may extrapolate the estimated future glucose value as the current glucose concentration minus the correction portion. Screen 1500 includes an indication 1502 of the estimated future glucose value, wherein instance indication 1502 is a text statement of the estimated future glucose value. In this instance, indication 1502 also indicates the time (e.g., 1 hour from now) of the estimated future glucose value. This time can be determined, for example, based on an estimate of the insulin action time of the injection dose and / or how long it will take for the host 1101 to eat.

[0305] In some instances, the bolus application 1134 determines an estimated future glucose trajectory. The estimated future glucose trajectory can be determined, for example, based on an estimate of the duration of insulin action of the bolus dose and / or how long the host 1101 will take to finish eating. Figure 15 In the example, the actual glucose concentration trajectory 1504 indicates the host 1101’s historical (e.g., previously measured) glucose concentration and the estimated future glucose concentration trajectory 1506, as shown by the dashed line.

[0306] In some instances, bolus applications use case-based reasoning techniques to determine one or more bolus doses for the host. Case-based reasoning techniques, such as the Advanced Diabetes Booster Calculator at Imperial College London or the ABC4D approach, determine bolus configuration parameters for the bolus dose by comparing the host's current condition, known as case parameters, with a stored set of cases describing previously administered bolus doses. The stored cases include parameter data describing the condition of the previously administered bolus dose, treatment data describing the previously administered bolus dose, and outcome data describing the host's condition after the previously administered bolus dose.

[0307] According to a case-based reasoning approach, the host provides current case parameter data indicating the parameters required for the bolus dose. Current case parameters may include data on the host's glucose concentration, other data about the host, and (if the bolus includes dietary portions) data about the diet associated with the bolus dose. Data on the host's glucose concentration can be determined using an analyte sensor system as described herein and may include both current and previous glucose concentrations (e.g., glucose concentrations 30 minutes, one hour, etc.). Other data about the host may include any other physiological descriptors of the host that may affect the host's physiological response to insulin, including, for example, data on recent exercise, recent alcohol consumption, and the host's menstrual cycle. Data about the relevant diet may include, for example, the carbohydrate content of the diet (e.g., in grams of carbohydrates) and other nutritional information about the diet, including the content of non-carbohydrate nutrients such as protein, fat, and salt.

[0308] The current case parameter data is compared with the parameter data of stored cases to select the closest previous case. For example, variations in Manhattan distance, weighted arithmetic mean, Euclidean distance, Mahalanobis distance, dynamic time-warped distance, or other suitable methods are used to determine the difference between the current case parameter data and the stored case parameter data. In some instances, a calculated bolus is selected to match treatment data from the closest previous case. When the bolus dose is administered, the host can be monitored to generate outcome data for the current case. The current case, including case parameters, treatment data, and outcomes, can then be stored as a new stored case.

[0309] While case-based reasoning can provide positive results, challenges remain. For example, because it relies on stored cases, its accuracy and, sometimes even its operability, depend on a large and diverse set of stored cases. Furthermore, the physiology of different hosts causes them to respond differently to various physiological or environmental factors, such as stress, alcohol, and exercise. Therefore, it may be desirable to generate stored cases from a single host. Consequently, case-based reasoning methods may produce poor results, or even fail entirely, until a large and diverse set of stored cases is generated. Moreover, even with a large set of stored cases, case-based reasoning techniques may suffer performance degradation, or even fail if the host encounters a new or unusual case that does not perfectly match a stored case.

[0310] Another challenge related to case-based reasoning is that it is often desirable for stored cases to include outcome data indicating the host's glucose concentration and / or other factors over an extended time period (typically several hours). However, in reality, the host typically eats and / or receives subsequent boluses within hours of the previous bolus dose. When such an intervention occurs, it can corrupt the outcome data of the previous bolus dose, thus preventing the previous bolus dose from forming the basis for new stored cases. This can make the process of generating a large number of distinct stored cases longer and more difficult.

[0311] Figure 16 This is a diagram illustrating an instance of environment 1600, demonstrating the application of case-based reasoning techniques using the inference application 1634. Figure 16 In one instance, the bolus application 1634 was programmed to modify the bolus configuration parameters of the closest nominal case, thereby generating a bolus dose for host 1601.

[0312] In this example, host 1601 utilizes computing device 1602 to execute the injection application 1634. Computing device 1602 can be any suitable computing device, such as medical device 108, user computing device 132, tablet computing device 114, smart pen 116, smart device 112, medical device 122, computing device 118, remote terminal 128, and / or server system 126.

[0313] The computing device 1602 may include an analyte sensor system 1612 and a delivery system 1614 and / or communicate with said analyte sensor system and delivery system. Similar to the analyte sensor system 102, the analyte sensor system 1612 may detect an analyte at the host 1601, such as the glucose concentration of the host 1601. The delivery system 1614 is configured to deliver a bolus dose to the host 1601. For example, the delivery system 1614 may be or include an insulin pen, an insulin pump, or other suitable delivery system.

[0314] exist Figure 16 In this example, the injection application 1634 acquires current case parameter data 1622. Current case parameter data 1622 may include data describing the host 1601, and optionally include data about the diet associated with the requested injection. Data about the host 1601 may include current and / or historical glucose data received from the analyte sensor system 1612. Data about the host 1601 may also include, for example, physiological descriptors such as data about recent exercise, data about recent alcohol consumption, data about the host's menstrual cycle, etc. Other data about the host 1601 may include data about the host's weight, age, height, body mass index (BMI), etc. Data about the relevant diet may include, for example, the carbohydrate content of the diet (e.g., in grams of carbohydrates), and may also include other nutritional information about the diet.

[0315] The injection application 1634 compares the current case parameter data 1622 with a set of nominal cases 1620. This may include, for example, finding the closest nominal case 1622, where the closest nominal case 1622 is the nominal case 1622 that has the shortest distance or smallest difference between the nominal case parameter data and the current case parameter data 1622. The distance or difference between the current case parameter data 1622 and the closest nominal case 1622 parameter data can be found using any suitable method, including, for example, Manhattan distance, weighted arithmetic mean, Euclidean distance, Mahalanobis distance, changes in dynamic time-warped distance, etc.

[0316] The injection application 1634 can also generate a treatment modification factor 1624 based on the distance or difference between the current case parameter data and the parameter data of the nearest nominal case. The treatment modification factor 1624 includes one or more modifications to the treatment data of the nearest nominal case 1622. For example, the treatment data of the nearest nominal case may include various injection configuration parameters, such as ISF, ICR, etc. The treatment modification factor 1624 includes data describing how to modify one or more injection configuration parameters. For example, the treatment modification factor 1624 may include one or more multipliers of the corresponding injection configuration parameters to be applied to the nearest nominal case 1622. The injection application 1634 applies the treatment modification factor to the injection configuration parameters of the nearest nominal case to determine the treatment data of the current case 1626. The treatment data of the current case 1626 can be used to generate the injection dose for the host 1601. The generated injection dose can be provided to the host via the user interface of the computing device 1602. In some instances, the generated bolus dose is provided directly to delivery system 1614, which then provides the bolus dose to host 1601.

[0317] Figure 17 This is a flowchart illustrating an example of a process flow 1700, executed via injection application 1634, to determine the injection dose for host 1601. At operation 1702, injection application 1634 receives current case parameter data. As described herein, this may include current and / or previous glucose concentration data received from analyte sensor system 1612, as well as information about host 1601, including data indicating recent exercise, recent alcohol consumption, etc. In some instances, the injection application acquires data describing host 1601, which may have been previously received and stored, such as weight, BMI, menstrual cycle status, etc. Furthermore, in some instances, injection application 1634 is configured to receive an image of a meal associated with the injection and derive nutritional information about the meal from that image. The image may be captured, for example, using a camera or other image sensor at delivery system 1614.

[0318] At operation 1704, the injection application 1634 selects the closest nominal case. This may include comparing the current case parameter data with case parameter data of one or more nominal cases describing a previously administered injection dose to host 1601. The closest nominal case may be the nominal case with case parameter data that has the smallest difference from the current case parameter data. The difference may be measured in any suitable manner, including, for example, Manhattan distance, weighted arithmetic mean, Euclidean distance, Mahalanobis distance, change in dynamic time-warped distance, etc.

[0319] At operation 1706, the injection application 1634 determines a treatment modification factor. This treatment modification factor is applied to the treatment data of the closest nominal case to generate the treatment data for the current case. In some instances, Bayesian inference techniques are used to generate the treatment modification factor. In other instances, the injection application 1634 trains a model, such as a regression model, to correlate the treatment data, including injection configuration parameters, from the corresponding treatment data of the closest nominal case with the current case.

[0320] At operation 1708, the injection application 1634 applies the treatment modification factor determined at operation 1706 to the treatment data of the nearest nominal case to determine the treatment data for the current case. In some instances, the treatment modification factor includes a multiplier or a set of multipliers that will be applied to the injection configuration data included together with the treatment data of the nearest nominal case. Thus, generating treatment data for the current case may include injection configuration data, such as ISF, ICR, etc., that applies multipliers to the nominal case treatment data. The injection application 1634 may apply the current case treatment data to determine the current case injection dose, for example, as described herein, including with respect to equations [1] and [2]. The current case injection dose may, for example, be displayed to the host 1601 on the screen of the computing device 1602. In other instances, the injection application 1634 may provide the current case treatment data to the delivery system 1614 to configure the delivery system 1614 to deliver the injection dose to the host 1601.

[0321] At optional operation 1710, the bolus application 1634 monitors the results 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. In some instances, the monitored results data may be used to generate a new nominal case, which can be added to the set of nominal cases for future bolus determination. Furthermore, in some instances, the monitored results data may be used to modify treatment modification factors and / or change the way treatment modification factors are generated. For example, when using a machine learning model to determine treatment modification factors, the monitored results data may be used as or supplemental training data for retraining the model.

[0322] It should be understood that generating current case treatment data in this manner reduces the technology's reliance on a large collection of diverse stored cases. For example, even if there are significant differences between the current case and the most recently stored or nominal cases, processing flow 1700 can still provide appropriately accurate results.

[0323] Figure 18This is a flowchart illustrating an example of a process flow 1800 that can be performed by the injection application 1634 when the difference between the current case and the nearest nominal case is too large to determine an appropriate and accurate bolus dose. For example, process flow 1800 illustrates an example of how the injection application 1634 can perform operation 1704 of process flow 1700.

[0324] At operation 1802, the injection application 1634 determines the nominal case with the smallest difference relative to the current case. This can be determined, for example, as described herein. At operation 1804, the injection application 1634 determines whether the difference between the current case and the nearest nominal case is greater than a threshold. If not, the injection application 1634 returns the determined nearest nominal case and can continue as described in operations 1706, 1708, etc., of process flow 1700.

[0325] If the difference between the current case and the nearest nominal case is greater than a threshold, it may indicate that a suitable treatment modification factor may not be developed. At operation 1808, the injection application 1634 determines a safe injection dose for the host 1601 by applying an alternative injection method. The alternative injection method may include, for example, applying treatment data from the nearest nominal case and then reducing the determined injection dose by a safety factor (e.g., 10%, 20%, etc.). In this way, the injection application 1634 determines an injection dose that, if incorrect, will tend to cause an increase rather than a decrease in the host's glucose concentration. This is because while high glucose concentrations can cause long-term health problems, the adverse effects of low glucose concentrations are more severe. In some instances, the alternative injection method may include the use of any other injection techniques described herein, including, for example, those described herein with respect to equations [1] and [2]. In some instances, the safe injection dose is provided to the host 1601 via computing device 1602 and / or to delivery system 1614 so that the injection dose is delivered to the host 1601.

[0326] At operation 1810, the injection application 1634 monitors the result data of the injection dose determined at operation 1808, for example, as described herein. At operation 1812, the injection application 1634 uses the current case parameter data and the result data. Treatment data for the new nominal case can be based on the injection configuration parameters used to determine a safe injection at operation 1808. For example, if the monitored data indicates an acceptable result, the injection configuration parameters that will generate the same safe injection can be acquired or determined and stored as treatment data for the new nominal case. If the monitored data indicates an unacceptable result, the injection application 1634 modifies the injection configuration parameters used to generate the safe injection.

[0327] As mentioned above, one challenge in implementing case-based reasoning in inference computation is that intervention events can prevent the development of new stored cases. For example, reference Figure 18 If an intervention event (e.g., a new diet or bolus dose) occurs during monitoring at operation 1810, the bolus application 1634 may not obtain a complete set of outcome data.

[0328] Figure 19 This is a flowchart illustrating an example of a process flow 1900 that can be executed via the injection application 1634 when an intervention event occurs during monitoring of outcome data for potential new nominated cases or stored cases. Process flow 1900 can be performed as per [reference to...]. Figure 16 and 17 The described case-based technique is executed in which a treatment modification factor is used to modify the treatment data of the nominal case to more closely match the current case. In some instances, process 1900 can also be used in other case-based inference techniques in which the treatment data of the closest stored case is not modified.

[0329] At operation 1902, application 1634 monitors the outcome data of potential new stored cases. Potential new stored cases can be used for similar purposes as described in this paper. Figures 16 to 18 The nominal cases and / or new stored cases for other implementations of case-based bolus techniques described herein. At operation 1904, the bolus application 1634 determines whether an intervention event has occurred before sufficient outcome data is collected. For example, an intervention event may have occurred if the host 1601 receives a subsequent bolus dose (e.g., a corrective bolus dose and / or a subsequent dietary bolus dose). If no intervention event has occurred, at operation 1910, the bolus application 1634 generates a new stored case, for example, as described herein.

[0330] If an intervention event occurs at operation 1904, the push application 1634 identifies the closest stored case. The closest stored case is the stored case that is closest to the potential new stored case. For example, as described herein, the closest stored case can be found by comparing the potential new stored case with previously stored cases. In some instances, the closest stored case is determined using case parameter data, case treatment data, and incomplete case outcome data (e.g., incomplete due to the intervention event). For example, case definition data such as glucose levels and trends at mealtimes, mealtime food intake, and mealtime IOBs can be considered to determine the closest case. Furthermore, in some instances, glucose level data can be used to determine the closest stored case, where the glucose level data considered is limited to data available for 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 intervention event, data gap, or data artifact, the stored case can be considered close. In some instances, distance techniques that can be used to identify the closest stored case considering an intervention event include Manhattan distance, weighted arithmetic mean, Euclidean distance, Mahalanobis distance, and variations in dynamic time-warped distance.

[0331] At operation 1908, the bolus application 1634 uses the nearest stored case to supplement incomplete outcome data for potential new stored cases. In some instances, this involves copying outcome data from the nearest stored case to the potential new stored case. For example, if the intervention event occurs one hour after the bolus dose of a potential new stored case, and the total monitoring period for the new stored case is two hours, outcome data from the nearest stored case, starting one hour after the bolus dose and extending to two hours after the bolus dose, can be added to the outcome data of the potential new stored case captured prior to the intervention event. This can produce a complete set of outcome data for the potential new stored case, which can then be used as a stored case.

[0332] In some instances, outcome data from the nearest stored case is modified before being added to the outcome data of a 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 injection application 1634 may utilize interpolation to fill gaps in the data between the nearest stored case and the potential new stored case. Furthermore, in some instances, the injection application 1634 may remove continuous glucose sensor artifacts (e.g., caused by erroneous glucose readings).

[0333] In some instances, this article is about Figures 16 to 19The described techniques and equipment may take into account one or more baseline doses of the host. For example, information about one or more recent baseline doses may be part of parametric data describing one or more cases. Furthermore, in some instances, treatment data associated with a case may specify variations in the host's baseline dose.

[0334] In some instances, the bolus application can be programmed to analyze glucose concentration data based on the bolus dose to determine recommended actions for the host, also referred to herein as host actions. For example, the bolus application can be programmed to use glucose concentration data and bolus dose data to predict hypoglycemic or hyperglycemic episodes in the host. When this occurs, the bolus application can be programmed to recommend host actions for treating the episode (e.g., a corrective bolus for treating a hyperglycemic episode or a snack for treating a hypoglycemic episode). In some instances, the bolus application is programmed to use glucose concentration data and bolus dose data to determine optimization of bolus configuration parameters for the host and / or optimization of the host's basal dose. Furthermore, in some instances, the bolus application is programmed to provide the host with a graphical user interface that includes a trajectory of the host's glucose concentration and indications of when a dietary bolus dose and / or corrective bolus dose has been received.

[0335] However, in many of these instances, it is expected that the bolus application will determine when to administer the bolus dose and differentiate between dietary boluses, corrective boluses, and mixtures of dietary and corrective boluses. For example, if the bolus application is to recommend changes in bolus configuration parameters used by the host at lunchtime, it is expected that the application will identify the dietary or mixed bolus dose received by the host at lunchtime and correlate the bolus dose with glucose concentration data. Whether a change in glucose concentration indicates an impending hyperglycemic or hypoglycemic episode depends on whether the glucose concentration change occurs close to the time of the bolus dose.

[0336] When an injection application calculates the bolus dose for the host, for example, as described herein, the application may have prior information about the bolus dose administered to the host, including the approximate timing of the bolus dose, the type of bolus dose, etc. However, when the host does not use the injection application to calculate the bolus dose, the application may lack this prior knowledge of the bolus dose. As described herein, this may limit the application's ability and / or effectiveness in determining host actions or providing a graphical user interface.

[0337] Various examples address these and other issues by implementing classification models, for example, to derive bolus dose data from glucose concentration data. Figure 20This diagram illustrates an example of environment 2000, demonstrating the use of injection application 2034 to execute classification model 2020 for classifying injection dosage. In this example, host 2001 utilizes computing device 2002 to execute injection application 2034. Computing device 2002 can be any suitable computing device, such as medical device 108, user computing device 132, tablet computing device 114, smart pen 116, smart device 112, medical device 122, computing device 118, remote terminal 128, and / or server system 126.

[0338] The computing device 2002 may include an analyte sensor system 2012 and a delivery system 2014 and / or communicate with said analyte sensor system and delivery system. Similar to the analyte sensor system 102, the analyte sensor system 2012 may detect an analyte at the host 2001, such as the glucose concentration of the host 2001. The delivery system 2014 is configured to deliver an injection dose to the host 2001. For example, the delivery system 2014 may be or include an insulin pen, an insulin pump, or other suitable delivery system. An injection application 2034 generates an injection application user interface 2003 provided to the host 2001. The injection application user interface 2003 may include visual and / or auditory elements to provide information to and / or receive information from the host 2001.

[0339] exist Figure 20 In this configuration, the injection 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 the injection dose as, for example, a dietary injection, a corrected injection, or a mixture of dietary and corrected injections. In some instances, the injection application 2034 receives an indication that an injection dose has been administered to the host 2001. For example, the delivery system 2014 can provide an indication that an injection dose has been administered, and in some instances, the size of the injection dose can be indicated. Furthermore, in some instances, the host 2001 can indicate to the injection application 2034 that an injection dose has been administered, and optionally, the size of the injection dose. In other instances, the injection application 2034 detects the injection dose without receiving any indication of the injection dose from the host 2001 or the delivery system 2014.

[0340] Classification Model 2020 can be any suitable type of machine learning model configured to provide classifications of things or events. For example, a classification model can be or includes linear classifier models such as logistic regression or Naive Bayes classifiers, nearest neighbor models, support vector machines (SVM) models, decision tree models, boosting tree models, random forest models, neural network models, etc. In some instances, Classification Model 2020 is a logistic regression model with L2 penalty.

[0341] Glucose concentration data describing the glucose concentration at host 2001 can be input into classification model 2020. Glucose concentration data can be received directly from and / or derived from analyte sensor system 2012. Instance glucose concentration data can include the rate of change of host glucose concentration at different intervals before and / or after the bolus dose, including, for example, 120 minutes before the bolus dose, 60 minutes before the bolus dose, 30 minutes before the bolus dose, at the bolus dose, 30 minutes after the bolus dose, 60 minutes after the bolus dose, 90 minutes after the bolus dose, etc.

[0342] Other inputs to the classification model 2020 may include data on current and / or historical bolus doses of host 2001, including, for example, the bolus dose size divided by the glucose concentration at that time, the bolus dose size divided by the minimum bolus dose in the most recent time period (e.g., the previous 14 days), the bolus dose size divided by the maximum insulin intake in the most recent time period (e.g., the previous 7 days), the bolus dose size minus the average or median bolus dose in the most recent time period (e.g., the previous 7 days), and / or the difference between the glucose concentration at the bolus dose and the average or median glucose concentration in the most recent time period (e.g., the previous 24 hours, the previous 72 hours, the previous 3 days, etc.). In some instances, the difference is a signed distance, which may have a positive or negative sign indicating the direction relative to the median glucose concentration. For example, if the sign of the distance is positive, the glucose concentration at the bolus dose is higher than the average or median glucose concentration, and the bolus dose is more likely to be a corrected dose. In some instances, the greater the positive difference between the glucose concentration and the average or median glucose concentration, the more likely the bolus dose is to be a corrected bolus dose. Furthermore, in some cases, the time period for ingesting average or median glucose concentrations can be adjusted.

[0343] Another example of the input to the classification model 2020 is a quadratic polynomial with two coefficients, which is suitable for the period (e.g., 30 minutes) of glucose concentration data around the time of the bolus dose.

[0344] The output of Classification Model 2020 is an indication of the bolus category, which can be either a corrective bolus or a dietary bolus. In some instances, Classification Model 2020 is trained to similarly indicate a mixed bolus category that includes both dietary and corrective bolus doses. In other instances, Model 2020 is trained to generally classify mixed bolus doses as dietary boluses.

[0345] The bolus application 2034 is programmed to determine host actions based on one or more bolus dose categories, as indicated by the classification model 2020. In some instances, the bolus application 2034 is programmed to determine recommended changes to the insulin dose (e.g., basal dose and / or bolus dose) for host 2001. For example, if the host's dietary bolus dose consistently causes the host's glucose concentration to drop below the target glucose concentration, the bolus application 2034 may recommend that host 2001 modify bolus configuration parameters, such as reducing the ICR used to generate the bolus dose. In another instance, if the host's glucose concentration is consistently above or below the target glucose concentration before administering a dietary bolus or mixed bolus dose, the bolus application 2034 may be programmed to recommend that host 2001 modify the basal dose. If host 2001 receives insulin via multiple daily injections, this may include increasing or decreasing the cyclical basal dose. If host 2001 receives insulin from an insulin pump, this may include modifying the basal delivery profile of the insulin pump. Figure 20 An example screen 2024 of the insulin injection application user interface 2003 is shown, which includes prompting the host 2001 to take a host action involving changing insulin dose configuration parameters. In this example, the recommended host action is to increase the host's basal dose by one unit.

[0346] In some instances, the injection application 2034 is programmed to predict hyperglycemic or hypoglycemic episodes using one or more injection dose categories determined by the classification model 2020. For example, if host 2001 has received a corrective injection, but the host's glucose concentration continues to rise after the corrective injection (e.g., one hour after the corrective injection), the injection application 2034 can detect the current or predicted hyperglycemic episode and instruct host 2001 to take host actions to treat the hyperglycemic episode. Similarly, if host 2001 has received a dietary injection, but the host's glucose concentration decreases after the dietary injection (e.g., one hour after the dietary injection), then the injection application 2034 can detect a hypoglycemic episode. The injection application 2034 can instruct host 2001 to treat the hypoglycemic episode. Figure 20 An example screen 2026 is shown of an injection application user interface 2003 that can be displayed to the host 2001 to instruct the host 2001 to treat a predicted hypoglycemic episode.

[0347] In some instances, the bolus application 2034 is also programmed to provide a graphical user interface to the host 2001, which, in conjunction with glucose concentration data, indicates different categories of bolus doses. For example, Figure 20 It also includes an instance screen 2028 of the injection application user interface 2003, which includes a trajectory of the glucose concentration of the host 2001. In screen 2028, glucose concentration is represented on the vertical axis and time is represented on the horizontal axis. As shown, instance dietary injections (“dietary”) and instance corrective injections (“corrective”) are indicated on the trajectory when the corresponding injection dose is administered.

[0348] Figure 21 This is a flowchart illustrating an example of a process flow 2100 that can be executed by injection application 2034 to determine the injection dose category using classification model 2020. At operation 2102, injection application 2034 acquires training data. The training data is data that includes at least glucose concentration data, which is labeled to indicate whether the data corresponds to an injection dose, when the injection dose is administered, and, in some instances, which type of injection dose is administered. In some instances, the training data also includes baseline dose information describing one or more baseline doses received by the host or other object of the training data. The training data may describe only the host 2001, or, in some instances, may be collected from other objects (e.g., different hosts). At operation 2104, the training data is used to train the classification model. The classification model 2020 can be trained in any suitable manner.

[0349] In some instances, operations 2102 and 2104 (shown in box 2101) can be performed at the same computing device 2002 executing the classification model 2020, for example, by executing the remainder of processing flow 2100. However, in some instances, operations 2102 and 2104 in box 2101 can be performed by different computing devices. For example, training of the classification model 2020 (e.g., operation 2101) can be performed at server system 126. The trained model can be provided to computing device 2002 (e.g., medical device 108, user computing device 132, tablet computing device 114, smart pen 116, smart device 112, medical device 122, and / or computing device 118) which can utilize the trained classification model 2020 as described herein.

[0350] At operation 2106, the injection application 2034 receives test injection data. The test injection data includes at least glucose concentration data describing the glucose concentration of host 2001 at and / or near the time host 2001 receives the injection dose. In some instances, the test injection data also includes data indicating when host 2001 receives the injection dose and / or, in some instances, the magnitude of the injection dose (e.g., the number of units of insulin delivered). The test injection data may also include information about one or more basal doses received by host 2001. In some instances, the injection application 2034 is configured to determine when to administer the injection dose based on the glucose concentration data. For example, the injection application 2034 may administer the injection dose based on the rate of change (first time derivative) and / or the change in the rate of change (second time derivative) of the glucose concentration data.

[0351] At operation 2108, the injection application 2034 applies a classification model to the test injection data to determine the category of the test injection. This may include, for example, providing the test injection data as input to classification model 2020 and receiving an output from classification model 2020 indicating the category of the test injection. In some instances where classification model 2020 is or includes a logistic regression model with L2 penalty, classification model 2020 is arranged such that a model output greater than 0.5 corresponds to a corrected injection and any other model output corresponds to a dietary injection. At operation 2110, the injection application 2034 selects a host action based on the category of the injection dose determined at operation 2108. At operation 2112, the injection application 2034 provides the host 2001 with a prompt regarding the host action determined at 2110. This document references, for example, […]. Figure 20 An example is described for determining the host action and providing corresponding prompts.

[0352] Figure 22 This is a flowchart illustrating an example of a process flow 2200 executed by injection application 2034 to determine a recommended host action based on the category of a test injection determined using classification model 2020. At operation 2202, injection application 2034 compares test injection data with category data. The test injection data includes data describing the test injection and, in some instances, includes some or all of the data provided as input to classification model 2020. The category data includes data describing the host 2001's response to other injection doses within the same category as the test injection.

[0353] At operation 2204, the injection application 2034 identifies differences between the test injection data and the category data. For example, the injection application 2034 may determine that the host's glucose concentration has increased or increased at a rate higher than the typical rate after a bolus of the same category. In another instance, when the host's glucose concentration typically increases (at least temporarily) after a dietary bolus, the injection application 2034 may determine that the host's glucose concentration has decreased after the dietary bolus. At operation 2206, the injection application 2034 selects a host action based on the differences identified at operation 2204. For example, if the host's glucose concentration increases at a rate higher than the typical rate for a bolus of the same category, the injection application 2034 may recommend changing the injection or baseline configuration parameters that tend to decrease glucose concentration and / or recommend actions to treat hyperglycemic episodes. In another instance, if the host's glucose concentration is lower or decreases at a rate higher than the typical rate for a bolus of the same category, the injection application 2034 may recommend changing the injection or baseline configuration parameters that tend to increase glucose concentration and / or recommend actions to treat hypoglycemic episodes.

[0354] One instance injection configuration parameter that can be modified by the injection application based on one or more injection dose categories is the Insulin On-Board (IOB) parameter. IOB is the amount of active insulin in the host's body at the time of receiving the injection dose. When the host receives an injection dose with an IOB, it is desirable to reduce the amount of injection dose to address the IOB. For example, the injection dose is typically determined based on the host's current glucose concentration. However, when an IOB is present, it may tend to lower the host's current glucose concentration. Therefore, it is desirable to reduce the injection dose based on the host's current glucose concentration to address the decrease in current glucose concentration caused by the IOB.

[0355] When determining the bolus dose, the IOB (Insulin Oxygen Absorption Scale) can be addressed by considering the IOB component. The IOB component can be based on an insulin action model (e.g., pharmacodynamic or pharmacokinetic), where the insulin action model describes one or more previously administered insulin doses (e.g., bolus dose, basal dose, and / or combination of basal / bolus doses). The time of insulin action (IAT) can be a parameter of the model. The IAT is the amount of time that insulin from a previous dose remains active in the body. In practice, insulin action may not be constant over the IAT. For example, after a host receives an insulin dose, the host's body may initially rapidly metabolize the received insulin and glucose in the host's blood, with the metabolic rate slowing down over time. The IOB component can be based on an insulin action model within the IAT. Such a model uses appropriate curves to represent the decrease in IOB over time, such as linear curves, cumulative log-normal curves, linearly corrected log-normal curves, etc. In some instances, the IOB component is considered for (e.g., subtracted from) both the dietary portion (if any) and the corrected portion (if any). In some instances, the IOB portion is considered for (e.g., subtracted from) the corrective portion, but not for the dietary portion.

[0356] However, correctly modeling the IOB to generate IOB components can be challenging. Different hosts process insulin and glucose in different ways. Furthermore, even the same host processes insulin and glucose differently over time and / or under different conditions. Various instance configurations address this and other issues by determining IOB parameter corrections using glucose concentration data and bolus data indicating one or more bolus doses received by the host.

[0357] Figure 23 This diagram illustrates an example of an environment 2300 demonstrating the use of an injection application 2334 to modify on-plate insulin (IOB) parameters. In this example, the host 2301 utilizes a computing device 2302 to execute the injection application 2334. The computing device 2302 can be any suitable computing device, such as 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.

[0358] The computing device 2302 may include an analyte sensor system 2312 and a delivery system 2314 and / or communicate with said analyte sensor system and delivery system. Similar to the analyte sensor system 102, the analyte sensor system 2312 may detect an analyte at the host 2301, such as the glucose concentration of the host 2301. The delivery system 2314 is configured to deliver a bolus dose to the host 2301. For example, the delivery system 2314 may be or include an insulin pen, an insulin pump, or other suitable delivery system.

[0359] exist Figure 23 In this example, the bolus application 2334 uses insulin dose data and glucose concentration data to determine recommended variations in IOB parameters for the host 2301. IOB parameters are parameters used to determine the IOB component of the bolus dose. For example, IOB parameters may include the type of insulin action model, parameters of the insulin action model such as the shape or offset characteristics of the curve modeling insulin action. Glucose concentration data describes the host's glucose concentration and may be received from the analyte sensor system 2312, as described herein. Insulin dose data may include bolus data and / or baseline data. Bolus data describes one or more bolus doses received by the host 2301, while baseline data describes one or more baseline doses received by the host 2301. For example, bolus data may indicate the time when the host 2301 received the bolus dose, the type of bolus dose (e.g., corrective, dietary, mixed), and / or the size of the bolus dose (e.g., in units of insulin).

[0360] The injection application 2334 can receive and / or acquire insulin dose data in any suitable manner. In some instances, the injection application 2334 receives and / or derives insulin dose data from prior knowledge. For example, if the injection application 2334 determines the bolus and / or basal dose for host 2301, the injection application 2334 can store insulin dose data describing the determined bolus dose. In some instances, the injection application 2334 receives insulin dose data from delivery system 2314. For example, delivery system 2314 can provide the injection application 2334 with data describing the bolus dose delivered by delivery system 2314 to host 2301. In other instances, the injection application 2334 derives some or all of the insulin dose data from other data such as glucose concentration data. For example, as described herein, the injection application 2334 can detect boluses from glucose concentration data and can classify boluses as described herein.

[0361] In some instances, the injection application 2334 considers injection data describing injection doses affected by IOB. An IOB-affected injection dose is an injection dose influenced by, for example, an IOB from a previously received injection dose and / or the basal dose. The injection application 2334 can identify an IOB-affected injection dose by detecting an injection dose received within a threshold time of another injection dose. The threshold time can depend on the insulin action time (IAT). For example, an injection dose received more than a threshold time after a previous injection (e.g., one hour or more, three hours or more, etc.) may not be considered or require any consideration of IOB, because IOB may not exist, and therefore the injection application 2334 may not consider IOB when determining recommended changes to the IOB parameter. Therefore, when the injection application 2334 considers injection data, it can identify and utilize injection data describing injection doses within a threshold time of a previous injection dose, such that the considered corrected injection dose includes the IOB component.

[0362] In some instances, the injection application 2334 considers the corrective bolus dose to determine recommended changes to the IOB parameter. As described herein, a corrective bolus is a bolus dose that provides correction for deviations between the host's current glucose concentration and a target glucose concentration. For example, a corrective bolus is typically administered after a meal if the host 2301 fails to receive a dietary bolus dose and / or if the host's blood glucose unexpectedly rises after a dietary bolus. Therefore, the corrective dose is typically influenced by the IOB. Thus, in some instances, the injection application 2334 considers the corrective bolus dose selected from bolus data to determine recommended changes to the IOB parameter. In some instances, the injection application 2334 determines recommended changes to the IOB parameter, taking into account the influence of the IOB, for example, by identifying corrective boluses received by the host 2301 within a threshold of previous bolus doses.

[0363] Figure 23 A graphical representation 2320, including insulin dosage data and glucose concentration data, illustrates how the injection application 2334 can determine recommended variations in IOB parameters. The graphical representation 2320 is provided as an illustration. In some instances, the graphical representation 2320 is displayed to the host 2301 via the injection application's user interface. In other instances, the injection application 2334 utilizes injection data and glucose concentration data similar to those numerically depicted in the representation 2320 (e.g., without presenting such a graphical representation).

[0364] In graphical representation 2320, the horizontal axis represents time, and the vertical axis represents glucose concentration. The dashed line represents the trajectory of glucose concentration over time. Graphical representation 2320 indicates dietary injection (“dietary”) and corrective injection (“corrective”). In this example, the IOB from the dietary injection appears at the time of the corrective injection. Injection application 2334 determines the behavior of the host's glucose concentration to determine the accuracy of the IOB component of the corrective injection. Figure 23 In the example shown, the host glucose concentration consistently decreases after the bolus correction. If the decrease is below the host's target glucose concentration, it may indicate that the IOB component underestimates the IOB of the correction bolus, resulting in a correction bolus that is higher than the required correction bolus. To correct this, the bolus application 2334 may recommend changing the IOB parameter to reduce the IOB component.

[0365] Figure 24 This is a flowchart illustrating an example of a processing flow 2400 that can be executed by injection application 2334 to generate recommended changes to the IOB parameters. At operation 2402, injection application 2334 acquires corrected bolus data describing at least one corrected bolus. At operation 2404, injection application 2334 acquires dietary bolus data describing at least one dietary bolus dose received by host 2301 prior to the corrected bolus dose. In some instances, operation 2404 is omitted, and injection application 2334 considers only the corrected bolus data to determine recommended changes to the IOB parameters. At operation 2406, injection application 2334 acquires glucose concentration data describing the glucose concentration of host 2301 at or near the time of one or more boluses described by the data acquired at operations 2402 and 2404.

[0366] At operation 2408, the bolus application 2334 determines the variation of the IOB parameter based on the corrected bolus data and glucose concentration data, as well as dietary bolus data acquired at operation 2404 in some instances. Recommended variations of the IOB parameter can be generated using any suitable method. In some instances, the bolus application 2334 substitutes the actual glucose concentration into the corrected bolus dose formula, as in the equation above [1]. Keeping the corrected bolus dose equal to the actual corrected bolus administered, the bolus application 2334 resolves the actual IOB component. The actual IOB parameter can be found by identifying one or more variations of the IOB parameter that result in an IOB component that matches or is similar to the actual IOB component. In some instances, a single IOB parameter or a finite set of IOB parameters may not generate a matching IOB component for each historical bolus dose. If no match is found, the bolus application 2334 may be coded to allocate costs to the difference between the actual IOB component (observed by the host) and the IOB component determined using a specific IOB parameter from the set of IOB parameters. The distance can be determined using the squared difference between IOB components or any other suitable method. The IOB parameters used by the push application 2334 can be determined to minimize the total cost over the set of corrected pushes under consideration.

[0367] In some instances, the injection application 2334 determines variations in the IOB parameter, at least in part, by identifying post-injection patterns in the glucose concentration of host 2301 across a set of considered injection doses described by injection data. The set of considered injection doses may include, for example, injection doses affected by IOB, corrected injection doses, and so on. A post-injection pattern occurs when the host's glucose concentration is similar across some or all of the considered injection doses. The post-injection pattern can be determined in any suitable manner. In some instances, the post-injection pattern is determined by finding the mean, median, or other aggregate of the glucose concentration of host 2301 after the considered injection dose. The post-injection pattern can be observed at any suitable time after the considered injection dose, including, for example, 30 minutes, 60 minutes, 90 minutes, etc.

[0368] Consider an instance where the post-injection pattern indicates that the host 2301's glucose concentration is lower than the host's target glucose concentration (e.g., 20 minutes after the considered bolus dose), which could indicate that the IOB component of the bolus dose underestimates the host's IOB. In this instance, the bolus application 2334 could recommend a change in the IOB parameter that tends to increase the determined IOB component of the bolus. Consider another instance where the post-injection pattern indicates that the host 2301's glucose concentration is higher than the host's target glucose concentration 35 minutes after the considered bolus dose. In this instance, the bolus application 2334 could recommend a change in the IOB parameter that tends to decrease the determined IOB component of the bolus.

[0369] Example IOB parameters include insulin duration of action (IAT), and various coefficients or other parameters describing the shape of the IOB curve. For example, the bolus application 2334 can generate the IOB using a function representing a curve such as a cumulative log-normal distribution curve. The IOB parameters of such a function can include the mean and standard deviation of the normal distribution associated with the log-normal distribution.

[0370] Furthermore, in some instances, changes in IOB parameters can depend on when the post-bolus pattern occurs (e.g., how long after the bolus dose) or the size of the bolus. These and other factors can influence the magnitude of changes in one or more IOB parameters, the choice of which IOB parameters to change, and so on.

[0371] Determining the accurate bolus dose for the host is a consistent challenge. For example, as described herein, the appropriate level of insulin used for the bolus dose to achieve the target glucose concentration depends on many factors, including the host's current blood glucose level, the diet to be consumed (if any), the host's activity level, alcohol consumption, etc. Furthermore, the appropriate level of insulin used for the bolus dose can also depend on physiological factors that are difficult to measure directly. Various examples utilize bolus applications programmed to take trend adjustments into account when determining the host's bolus dose to address these and other issues. Based on trend adjustments, the bolus application uses glucose concentration data received from an analyte sensor system to determine the host's rate of change in glucose concentration (ROC). The bolus application uses the glucose concentration ROC to determine the predicted glucose concentration for future times after the predicted time period. As described herein, the bolus application then determines the host's bolus dose, including adjusting for the trend component of the predicted glucose concentration.

[0372] Figure 25This diagram illustrates an example of environment 2500 described herein, demonstrating the use of a bolus application 2534 to determine a bolus dose for host 2501 using trend adjustment. In this example, host 2501 utilizes computing device 2502 to execute the bolus application 2534. Computing device 2502 can be any suitable computing device, such as medical device 108, user computing device 132, tablet computing device 114, smart pen 116, smart device 112, medical device 122, computing device 118, remote terminal 128, and / or server system 126.

[0373] The computing device 2502 may include an analyte sensor system 2512 and a delivery system 2514 and / or communicate with said analyte sensor system and delivery system. Similar to the analyte sensor system 102, the analyte sensor system 2512 may detect an analyte at the host 2501, such as the glucose concentration of the host 2501. The delivery system 2514 is configured to deliver a bolus dose to the host 2501. For example, the delivery system 2514 may be or include an insulin pen, an insulin pump, or other suitable delivery system.

[0374] exist Figure 25 In one instance, the bolus application 2534 receives bolus request data describing the requested bolus dose. (In some instances, the bolus application 2534 determines the combined basal / bolus dose and / or the basal dose in addition to the requested bolus dose). As described herein, the bolus application 2534 adjusts for a glucose concentration trend by taking into account a trend component of the bolus dose. As described elsewhere herein, the bolus dose may be determined by taking into account a correction component and (if the bolus dose is associated with a diet) a dietary component. An example for determining the correction component is given herein by equation [1], while an example for determining the dietary component is given herein by equation [2]. Also as described herein, the total bolus dose can be found by summing the correction component and the dietary component (if any).

[0375] Figure 25 This includes a graphical representation 2520 illustrating how the injection application 2534 uses trend components to determine the injection dose. In some instances, the injection application 2534 generates or presents a graphical representation similar to graphical representation 2520, for example, to be displayed on a display of computing device 2502. However, in other instances, the injection application 2534 utilizes some or all of the concepts described herein without presenting a graphical representation similar to graphical representation 2520.

[0376] Graphical representation 2520 shows a glucose concentration trajectory plotted on a graph, where the horizontal axis corresponds to time and the vertical axis corresponds to glucose concentration. The graph represents the target glucose concentration range (“target range”) and the target glucose concentration value (“target”). In this example, the glucose concentration trajectory begins below the target glucose concentration range and then begins to rise.

[0377] At the indicated time (“BD request”), the bolus application 2534 receives a request to determine the bolus dose for the host 2501. In some instances, this request is accompanied by dietary data describing the diet associated with the bolus dose (if the bolus dose is to include meal portions). As described herein, the dietary data may include the amount of carbohydrates in the diet.

[0378] The injection application 2534 receives glucose concentration data from the analyte sensor system 2512. The glucose concentration data may include the glucose concentration of the host 2501 at multiple different times. The injection application 2534 uses the glucose concentration data to generate a rate of change (ROC) of glucose concentration in the host 2501. The glucose concentration ROC indicates the change in glucose concentration per unit time (e.g., mg / dL per second). A positive glucose concentration ROC can indicate that the glucose concentration of the host 2501 is increasing, while a negative glucose concentration ROC can indicate that the glucose concentration of the host 2501 is decreasing.

[0379] Using the glucose concentration ROC, the injection application 2534 extrapolates from the host 2501's current glucose concentration ("current GC") to generate a predicted glucose concentration ("predicted GC") for the host 2501 at a future time. The future time is after the current time, where the current time is the time when the injection dose is requested or will be administered. The future time is separated from the current time into a prediction time period ("predicted time period"). The prediction time period can be any suitable value. In some instances, the prediction time period is between approximately five and sixty minutes. In some instances, the prediction time period is between approximately ten and approximately forty minutes. In some instances, the prediction time period varies depending on the characteristics of the host 2501. For example, for hosts above a threshold age, the injection application 2534 may use a first prediction time period, while for hosts below a threshold age, the injection application may use a shorter second prediction time period. In some instances, a twenty-minute prediction time period is used for hosts 2501 under the age of eighteen, while a thirty-minute prediction time period is used for hosts 2501 eighteen years and older.

[0380] Graphical representation 2520 shows the correction (“correction”), which is the current glucose concentration of host 2501 (GC in Equation [1]). M) and the target glucose concentration of host 2501 (GC in Equation [1] T The difference between ) can be used, for example, to generate a corrected component for the bolus using the correction of host 2501 and insulin sensitivity factor (ISF), as shown in Equation [1].

[0381] The glucose application 2534 can find trend components, for example, as given by the following equation [3]: [3]

[0383]

[0384] In equation [3], TC is the trend component. M This is the measured glucose concentration of host 2501 (e.g., current GC), and indicates the glucose concentration of host 101 at or approximately at the time of receiving the bolus dose. GC P The predicted glucose concentration is the result after the predicted time period. Similar to Equation [1], in Equation [3], ISF is the insulin-sensitizing factor of host 2501. The total bolus dose determined by the bolus application 2534 may be the sum of the corrected portion, the dietary portion (if any), and the trend portion, or other suitable combinations.

[0385] Figure 26 This is a flowchart illustrating an example of a process flow 2600 that can be executed by injection application 2534 to determine the injection dose of host 2501 using a trend component. At operation 2602, injection application 2534 receives injection dose request data describing the requested injection dose. The injection dose request data describes the injection dose to be determined. For example, the injection dose request data may include dietary data describing a diet associated with the injection dose. The injection dose data may also indicate that no diet is associated with the injection dose (e.g., it is a corrective injection).

[0386] At operation 2604, the injection 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 multiple (e.g., at least two) glucose concentration values ​​of the host 2501. At operation 2606, the injection application 2534 uses the glucose concentration data to determine the glucose concentration ROC of the host 2501. The glucose concentration ROC can be determined in any suitable manner. In some instances, the injection application 2534 finds the best-fit line between the glucose concentration values ​​of the host 2501 over two or more measurements. In other instances, the glucose concentration ROC is found by measuring two glucose concentration values ​​and taking the difference between the two glucose concentration values ​​over time. Furthermore, any other suitable technique can be used to find the glucose concentration ROC.

[0387] At operation 2608, the injection application 2534 determines a predicted glucose concentration at a future time, where the future time is a predicted period of time after the current time, as described herein. At operation 2610, the injection application 2534 uses the predicted glucose concentration to determine the injection dose. For example, the injection application 2534 may generate a trend component, for example, as shown in Equation [3]. The trend component may be added to a correction component (e.g., determined according to Equation [2]) and, if an associated diet exists, to a dietary component (e.g., determined according to Equation [1]).

[0388] In some instances, the bolus application 2534 is also configured to take into account on-board carbohydrate (COB) portions. To utilize on-board carbohydrate portions, the bolus application 2534 is configured to view bolus data describing the previous bolus dose provided to the host 2501 and / or the meals previously consumed by the host. The bolus data describing the previous bolus dose can be received in any suitable manner, including those described herein. In addition, in some instances, the host 2501 can provide dietary data describing the previously consumed meals. Based on the bolus data and / or dietary data, the bolus application 2534 can determine COB values ​​describing carbohydrates previously consumed but not covered by the previous bolus dose. COB values ​​can be converted to COB portions, for example, as shown in the following equation [4]: [4]

[0390]

[0391] In equation [4], COBC is the plate carbohydrate component of the bolus dose. COB is the plate carbohydrate value mentioned above, which indicates the carbohydrates previously consumed by host 2501 but not yet covered by the previous bolus dose. ICR is the ratio of insulin to carbohydrates in host 2501. The COB component can be added to other components (e.g., dietary component, corrective component, trend adjustment, plate insulin, etc.) to generate the bolus dose.

[0392] In some instances, it is not desirable to use trend adjustment to determine the bolus dose of host 2501 in all cases. Figure 27 It shows Figure 26 A diagram of another example of the processing flow 2600 is shown, in which in some cases there are additional operations for omitting the bolus trend component. For example, after determining the glucose concentration ROC at operation 2606, the bolus application 2534 may optionally determine at operation 2702 whether the glucose concentration ROC is rising. 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, at operation 2710, the bolus application 2534 may determine the bolus dose for the host 2501 while omitting the trend component (e.g., using only the correction component and dietary component, if any)).

[0393] Similarly, at optional operation 2704, after determining the predicted glucose concentration at operation 2608, the injection application 2534 can determine whether the difference between the predicted glucose concentration and the current glucose concentration is less than a threshold. For example, if the difference between the predicted glucose concentration and the current glucose concentration is greater than the threshold amount, it can indicate that the predicted glucose concentration is unreliable. Therefore, the injection application 2534 can determine the injection dose for the host 2501, while omitting the trend component at operation 2710. In some instances, instead of omitting the trend component, the injection application 2534 modifies the predicted glucose concentration to the maximum permissible 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, then the glucose application 2534 can set the predicted glucose concentration value to 200 mg / dL and use the trend component to determine the injection.

[0394] Another situation where trend adjustment might be undesirable is when there is an immediate preceding meal bolus, or if the host has recently ingested food, for example, if the host began eating before receiving the bolus dose covering the meal. In this case, all or part of the glucose concentration ROC may be due to mealtime variations in glucose concentration, making the glucose concentration ROC less predictive of the host's future glucose concentration. For example, the host's previous meal may have caused an increase in the host's glucose concentration (and associated ROC).

[0395] Therefore, at optional operation 2706, the injection application 2534 can determine whether a previous dietary bolus was accepted by the host 2501 within a threshold time period (e.g., 30 minutes, 1 hour, 2 hours, etc.). For example, the injection application 2534 can determine whether it provided a dietary bolus confirmation during that time. In addition to or instead of determining whether it provided a dietary bolus confirmation within the threshold time period, the injection application 2534 can analyze glucose concentration data to detect the previous bolus dose and / or characterize the previous bolus dose as a dietary bolus, for example, as described herein. If no previous dietary bolus is detected within the threshold time period, the injection application 2534 proceeds to operation 2610.

[0396] In some instances, after determining at operation 2706 that a previous dietary bolus existed within a threshold time period, the bolus application can determine at operation 2710 to omit the trend component based on the current bolus. In other instances, at operation 2708, the bolus application 2534 first determines whether the currently requested bolus dose includes a dietary component. If the currently requested bolus dose does include a dietary component, then at operation 2710, the bolus application 2534 can omit the trend component. If the currently requested bolus dose does not include a dietary component, then the bolus application 2534 can proceed to operation 2610.

[0397] Figure 28 This diagram illustrates an example of environment 2800, showing a bolus application 2834 configured to consider bolus data to generate glucose concentration alarms. For example, an alarm needs to be issued to the host 2801 when its glucose concentration is outside a target range. For instance, if the host's glucose concentration is above the target range, it could indicate a current or impending hyperglycemic episode. The host 2801 may need to treat the hyperglycemic episode, for example, by receiving a corrective bolus. Similarly, if the host's glucose concentration is below the target range, it could indicate a current or impending hypoglycemic episode. The host 2801 may need to treat the hypoglycemic episode, for example, by receiving a food containing carbohydrates to increase glucose concentration.

[0398] However, in various instances, the relationship between glucose concentration and the likelihood of hyperglycemic or hypoglycemic episodes depends on bolus data describing one or more recent bolus doses received by the host 2801. For example, the host's glucose concentration typically rises during meals and then decreases again after the dietary bolus dose received with the meal begins to take effect. This rise, combined with the dietary bolus, may not indicate a current or impending hyperglycemic event. Moreover, the host 2801 may sometimes forget to take a bolus dose before a meal. When this occurs, it may be necessary to capture the missed bolus dose early to allow the host to receive a bolus dose before the host's glucose concentration becomes dangerously high.

[0399] In various instances, these and other issues are addressed by configuring the injection application 2834 to select a glucose concentration alarm threshold for alerting the host 2801, at least in part, based on injection data. The glucose concentration alarm threshold is a glucose concentration level above which the injection application 2834 generates an alarm 2820 to the host 2801 indicating a potential hypoglycemic or hyperglycemic episode. In some instances, the injection application 2834 utilizes both hyperglycemic and hypoglycemic alarm thresholds. When the host 2801's glucose concentration is above the hyperglycemic alarm threshold, the injection application 2834 generates an alarm 2820 to the server indicating a current or impending hyperglycemic event. When the host 2801's glucose concentration is below the hypoglycemic alarm threshold, the injection application 2834 provides an alarm 2820 indicating a current or impending hypoglycemic event.

[0400] exist Figure 28 In this example, host 2801 utilizes computing device 2802 to execute the injection application 2834. Computing device 2802 can be any suitable computing device, such as medical device 108, user computing device 132, tablet computing device 114, smart pen 116, smart device 112, medical device 122, computing device 118, remote terminal 128, and / or server system 126.

[0401] The computing device 2802 may include an analyte sensor system 2812 and a delivery system 2814 and / or communicate with said analyte sensor system and delivery system. Similar to the analyte sensor system 102, the analyte sensor system 2812 may detect an analyte at the host 2801, such as the glucose concentration of the host 2801. The delivery system 2814 is configured to deliver a bolus dose to the host 2801. For example, the delivery system 2814 may be or include an insulin pen, an insulin pump, or other suitable delivery system.

[0402] exist Figure 28In one instance, the injection 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 host 2801. The injection application 2834 may also receive injection data. The injection data indicates at least one previous injection dose provided to the host 2801. The injection data can be received or obtained from any suitable source. In some instances, the injection data is stored in a data storage location associated with the injection application 2834, for example, at the computing device 2802. For example, the injection data may include data regarding one or more previous injection doses determined by the injection application 2834 for the host 2801. In other instances, the injection data is received from the host 2801, for example, via the injection application user interface. Furthermore, in some instances, the injection data is received from the delivery system 2814, for example, based on a record of injection doses provided to the host 2801 by the delivery system 2814.

[0403] Using the bolus data, the bolus application 2834 modifies the glucose concentration alarm threshold. In some instances, the selected glucose concentration alarm threshold is a hyperglycemia alarm threshold. For example, if host 2801 receives a dietary bolus within a threshold time period (e.g., one hour, two hours, four hours, etc.), the bolus application 2834 may tend to increase the hyperglycemia alarm threshold such that alarm 2820 is not sent to indicate a current or impending hyperglycemic episode until or unless host 2801's glucose concentration is higher than a level that would otherwise trigger alarm 2820.

[0404] On the other hand, if host 2801 does not receive a dietary bolus within a threshold time period (e.g., one hour, two hours, four hours, etc.), it can indicate that host 2801 has missed the dietary bolus due to eating, or may miss it (e.g., eating without receiving the corresponding bolus dose). Therefore, the bolus application 2834 can lower the hyperglycemia alarm threshold, causing alarm 2820 to be sent to indicate a current or impending hyperglycemic episode in host 2801's glucose concentration earlier than in other cases.

[0405] In some instances, the injection application 2834 utilizes on-plate insulin (IOB) values ​​derived from injection data to determine one or more glucose concentration alarm thresholds. The injection application 2834 can determine the IOB value of host 2801 based on the injection data. For example, the injection application 2834 can consider the time since host 2801 received its most recent injection and the insulin duration of action (IAT) model described herein. The injection application 2834 can set a hyperglycemia alarm threshold based on the IOB. A higher IOB (e.g., above the IOB threshold) can cause the injection application 2834 to raise the hyperglycemia alarm threshold. For example, a higher IOB can indicate that host 2801's IOB will tend to lower host 2801's glucose concentration without further treatment, meaning that treatment for a current or impending hyperglycemic episode may not be necessary before a high blood glucose level is received. Similarly, a lack of IOB in host 2801 can indicate a long period of time since a previous injection, which can indicate that host 2801 is about to eat or may have missed a meal injection. Therefore, a low or absent IOB may cause the bolus application 2834 to lower the hyperglycemia alarm threshold. In some instances, IOB can be used to modify the hypoglycemia alarm threshold, indicating when the host 2801 is at risk of a hypoglycemic event. For example, if there is a recent bolus or a high current IOB (e.g., above the threshold), the hypoglycemia alarm threshold can be raised because under these conditions, the remaining insulin action can further lower glucose and put the host at greater risk of a hypoglycemic episode.

[0406] Other factors that may be considered in determining the glucose concentration alarm threshold may include historical glucose patterns, contextual information, the host's food intake history or calculated on-board carbohydrates, and / or glucose variability. For example, historical glucose patterns may be considered to make the glucose concentration alarm threshold more or less aggressive at different times of the day, as individual hosts tend to have high or low glucose. Contextual information, such as data describing the host's exercise or stress levels, can influence the probability of hyperglycemic episodes and can be taken into account accordingly. For example, if contextual information indicates that the host is at higher risk of hyperglycemic episodes, the injection application 2834 may utilize a lower hypoglycemic alarm threshold. For example, if the host has recently eaten or has on-board carbohydrates, the host's food intake history or calculated on-board carbohydrates may be used to raise the hypoglycemic alarm threshold. For example, when the current glucose variability is high, the glucose variability rate may be used to lower the hypoglycemic alarm threshold. In some instances, predicted glucose to address the current variability rate may be assessed against the hypoglycemic alarm threshold rather than the current glucose level.

[0407] Figure 29This is a flowchart illustrating an example of a process flow 2900 that can be executed by the injection application 2834 to generate an injection notification alarm for the host 2801. At operation 2902, the injection application 2834 acquires, for example, glucose concentration data from the analyte sensor system 2812. At operation 2904, the injection application acquires injection data, for example, as described herein. For example, the injection data may describe the basal / injection dose of previous injections and / or combinations received by the host 2801.

[0408] At operation 2906, the injection application 2834 modifies the hyperglycemia alarm threshold based on the injection data. For example, if a period exceeding the threshold has elapsed since the host 2801 received a previously higher injection dose and / or IOB value, the injection application 2834 may lower the hyperglycemia alarm threshold. Conversely, if a period less than the threshold has elapsed since the host 2801 received a previously higher injection dose and / or IOB value, the injection application 2834 may raise the hyperglycemia alarm threshold. Any suitable threshold can be used. In some instances, if a period less than the threshold has elapsed since the previously higher injection dose and / or IOB value, the hyperglycemia alarm threshold may be between approximately 220 mg / dL and 280 mg / dL. In some instances, the threshold is approximately 250 mg / dL. Furthermore, in some instances, if a period exceeding the threshold has elapsed since the previously lower injection dose and / or IOB value, the hyperglycemia alarm threshold may be between approximately 160 mg / dL and approximately 200 mg / dL. In some instances, the threshold was approximately 180 mg / dL.

[0409] At operation 2908, the injection application 2834 determines whether the glucose concentration of the host 2801 is greater than the hyperglycemia alarm threshold determined at operation 2906. If the glucose concentration is greater than the hyperglycemia alarm threshold, the injection application 2834 can provide alarm 2820 at operation 2910. If the glucose concentration is not greater than the hyperglycemia alarm threshold, the injection application may not provide alarm 2820 at operation 2912.

[0410] The various examples of managing bolus doses described herein can be practiced individually, or in some instances, together in any suitable combination. For example, Figure 30This is a flowchart illustrating an example of a processing flow 3000 that can be executed 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 should be understood that, depending on the configuration, any operation of processing flow 3000 can be omitted and / or replaced. In other instances, the order of operations in processing flow 300 can be modified. For example, determining the bolus dose (operation 3004) and determining the bolus dose effect data (3006) can be performed together or in reverse order. Other modifications may also be considered.

[0411] At operation 3002, the bolus application determines the bolus configuration parameters used to determine the host's bolus dose. This can be performed in any suitable manner, including, for example, as described herein. Figures 7 to 10 As described above. In some instances, the injection application can directly query the host to provide injection configuration parameters. In some instances, the injection application can start with a default set of injection configuration parameters, which is the same for each host and / or based on host characteristics (e.g., size, weight, age, type of diabetes, etc.).

[0412] At operation 3004, the injection application determines the host's injection dose, for example, based on a request from the host. The determined injection dose can be a corrected injection dose, a dietary injection dose, and / or a mixed injection dose. Various different techniques can be used. In some instances, the injection application implements the methods described herein. Figures 16 to 19 The case-based reasoning technique described herein. In some instances, the inference application implements the methods described in this article. Figures 25 to 27 The trend adjustment techniques described herein. In some instances, the injection application implements a combination of these techniques, for example, using case-based inference techniques that treat glucose concentration trends as case parameters. In other instances, the injection application may determine the injection dose using the application of formulas or sets of formulas, such as equations [1] and [2] described herein. The determined injection dose may be displayed to the host and / or provided to the delivery device at the user interface, as described herein.

[0413] At operation 3006, the injection application determines the injection dose effect data, for example, as shown here regarding... Figures 11 to 15 As described herein, bolus dose efficacy data can be provided to the host to allow the host to verify the accuracy of the determined bolus dose before receiving it.

[0414] At operation 3008, the bolus application modifies the bolus configuration parameters based on glucose concentration data received after receiving the determined bolus dose. In some instances, this includes, as described herein... Figures 20 to 22 The aforementioned bolus dosage. In some instances, the bolus application is also based on... Figures 20 to 22 The aforementioned classification is used to determine host actions. This document references... Figure 23 and 24 This describes an example of modifying the IOB parameter push configuration parameters.

[0415] At operation 3010, the injection application, for example, alerts the host to an event based on glucose concentration data. This event could be an episode of hyperglycemia or hypoglycemia, and / or an indication of other host action, such as as referenced herein. Figure 28 and 29 As stated above.

[0416] Figure 31 This is a block diagram illustrating a computing device hardware architecture 3100, in which an executable instruction set or sequence of instructions is provided to enable a machine to perform any of the methods discussed herein. Hardware architecture 3100 can describe various computing devices, including, for example, sensor electronics 106, peripheral medical devices 122, intelligent devices 112, tablet computing devices 114, etc.

[0417] Architecture 3100 can operate as a standalone device or be connected (e.g., networked) to other machines. In a networked deployment, Architecture 3100 can operate as a server or client machine in a server-client network environment, or it can act as a peer machine in a peer-to-peer (or distributed) network environment. Architecture 3100 can be implemented in a personal computer (PC), tablet PC, hybrid tablet, set-top box (STB), personal digital assistant (PDA), mobile phone, web device, network router, network switch, bridge, or any machine capable of executing instructions (sequentially or otherwise) specifying the actions to be taken by that machine.

[0418] Instance architecture 3100 includes a processor unit 3102, which includes at least one processor (e.g., a central processing unit (CPU), a graphics processing unit (GPU), or both, a processor core, or a computing node). Architecture 3100 may also include main memory 3104 and static memory 3106, which communicate with each other via link 3108 (e.g., a bus). 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 instances, the video display unit 3110, the input device 3112, and the UI navigation device 3114 are integrated into a touchscreen display. Architecture 3100 may additionally 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.

[0419] In some instances, processor unit 3102 or another suitable hardware component may support hardware interrupts. In response to a hardware interrupt, processor unit 3102 may suspend its processing and perform an ISR, for example, as described herein.

[0420] Storage device 3116 includes machine-readable medium 3122 on which one or more sets of data structures and instructions 3124 (e.g., software) embodying or used by any one or more methods or functions described herein are stored. During execution of instructions 3124 by architecture 3100, the instructions may also reside wholly or at least partially in main memory 3104, static memory 3106, and / or in processor unit 3102, wherein main memory 3104, static memory 3106, and processor unit 3102 also constitute machine-readable medium.

[0421] Executable instructions and machine storage media

[0422] Various memories (i.e., the memories of 3104, 3106, and / or the processor unit 3102) and / or storage devices 3116 may store one or more sets of instructions and data structures (e.g., instructions) 3124 embodying or used by any one or more methods or functions described herein. These instructions, when executed by the processor unit 3102, cause various operations to implement the disclosed instances.

[0423] As used herein, the terms “machine storage medium,” “device storage medium,” and “computer storage medium” (collectively, “machine storage medium 3122”) refer to the same thing and are used interchangeably in this disclosure. The term refers to single or multiple storage devices and / or media (e.g., centralized or distributed databases, and / or associated caches and servers) storing executable instructions and / or data, as well as cloud-based storage systems or networks comprising multiple storage devices or apparatuses. Therefore, these terms should include, but are not limited to, solid-state memory and optical and magnetic media, including memory internal or external to the processor. Specific examples of machine storage medium, computer storage medium, and / or device storage medium 3122 include non-volatile memory, such as semiconductor memory devices, such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), FPGAs, and flash memory devices; disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROMs and DVD-ROMs. The terms machine storage medium, computer storage medium, and device storage medium 3122 specifically exclude carrier waves, modulated data signals, and other such media, at least some of which are covered under the term "signal medium" discussed below.

[0424] signal medium

[0425] The terms "signal medium" or "transmission medium" should be considered to include any form of modulated data signal, carrier wave, etc. The term "modulated data signal" refers to a signal whose one or more characteristics are set or altered in a manner that encodes information in the signal.

[0426] Computer-readable media

[0427] The terms "machine-readable medium," "computer-readable medium," and "device-readable medium" refer to the same thing and are used interchangeably in this disclosure. The terms are defined to include both machine storage media and signal media. Therefore, the terms include storage devices / media and carrier / modulated data signals.

[0428] Instruction 3124 may further be transmitted or received via a network interface device 3120 using a transmission medium over a communication network 3126 using any of a variety of well-known transport protocols (e.g., HTTP). Examples of communication networks include LANs, WANs, the Internet, mobile phone networks, ordinary old-style telephone service (POTS) networks, and wireless data networks (e.g., Wi-Fi, 3G, 4G LTE / LTE-A, 5G, or WiMAX networks). The term "transmission medium" should be considered to include any intangible medium capable of storing, encoding, or carrying instructions for machine execution and comprising digital or analog communication signals, or other intangible media facilitating the communication of such software.

[0429] Throughout this specification, multiple instances may implement components, operations, or structures described as single instances. While individual operations of one or more methods are shown and described as separate operations, one or more of these operations may be performed concurrently, and the order in which they are performed is not required. Structures and functionalities presented as separate components in an instance configuration may be implemented as composite structures or components. Similarly, structures and functionalities presented as single components may be implemented as separate components. These and other variations, modifications, additions, and improvements fall within the scope of this document.

[0430] Various components are described in this disclosure as being configured in a particular manner. Components can be configured in any suitable manner. For example, a component that is or includes a computing device can be configured with suitable software instructions for programming the computing device. Components can also be configured by means of their hardware arrangement or in any other suitable manner.

[0431] The above description is intended to be illustrative and not restrictive. For example, the examples above (or one or more aspects thereof) may be used in combination with other examples. For example, other examples may be used by one of ordinary skill in the art upon review of the above description. The abstract is intended to allow the reader to quickly determine the nature of the technical disclosure, such as conformity with U.S. 37C.FR §1.72(b). It should be understood that this abstract is not intended to interpret or limit the scope or meaning of the claims.

[0432] Furthermore, in the above specific embodiments, various features may be combined to simplify this disclosure. However, the claims cannot elaborate on every feature disclosed herein, as an example may feature a subset of said features. Moreover, an example may include fewer features than those disclosed in a particular example. Therefore, the appended claims are hereby incorporated into the detailed description, with each claim serving as an independent, separate example. The scope of the examples disclosed herein will be determined with reference to the appended claims and the full scope of their authorized equivalents.

[0433] Each of these non-limiting instances in any part of the above description can be used independently or in various permutations or combinations with one or more other instances.

[0434] The above detailed description includes reference to the accompanying drawings, which form part of the detailed description. The drawings illustrate, by way of illustration, specific embodiments in which the subject matter can be practiced. These embodiments are also referred to herein as “examples.” Such examples may include elements other than those shown or described. However, the inventors also contemplate examples in which only those elements shown or described are provided. Furthermore, the inventors contemplate examples of any combination or arrangement of those elements (or one or more aspects thereof) shown or described herein, relative to a particular example (or one or more aspects thereof) or relative to other examples (or one or more aspects thereof) shown or described herein.

[0435] In the event of any inconsistency between the usage in this document and any other document incorporated herein by reference, the usage in this document shall prevail.

[0436] In this document, as is common in patent documents, the terms “a” or “an” are used to include one or more, independent of any other instances or uses of “at least one” or “one or more”. In this document, unless otherwise stated, the term “or” is used to indicate non-exclusivity, or “A or B” includes “A but not B,” “B but not A,” and “A and B.” In this document, the terms “comprising” and “in which” are used as simple English equivalents to the corresponding terms “including” and “wherein.” Furthermore, in the following claims, the terms “comprising” and “including” are open-ended, meaning that a system, apparatus, article, composition, formulation, or process that includes elements other than those listed after such terms in the claims is still considered to fall within the scope of the claims. Additionally, in the following claims, the terms “first,” “second,” “third,” etc., are used only as designations and are not intended to impose numerical requirements on their objects.

[0437] Unless the context otherwise indicates, geometric terms such as “parallel,” “perpendicular,” “circular,” or “square” are not intended to require absolute mathematical precision. Rather, such geometric terms allow for variation due to manufacturing or equivalent function. For example, if an element is described as “circular” or “generally circular,” components that are not precisely circular (e.g., slightly elliptical or polygonal) are still included in this specification.

[0438] The methods described herein can be implemented, at least in part, by a machine or computer. Some examples may include computer-readable or machine-readable media encoded with instructions operable to configure electronic devices to perform the methods described in the examples above. Implementation of such methods may include code, such as microcode, assembly language code, high-level language code, etc. Such code may include computer-readable instructions for performing various methods. The code may form part of a computer program product. Furthermore, in one example, the code may be tangibly stored, for example during execution or at other times, on one or more volatile, non-transitory, or non-volatile tangible computer-readable media. Examples of such tangible computer-readable media may include, but are not limited to, hard disks, removable disks, removable optical disks (e.g., compact discs and digital video discs), magnetic tapes, memory cards or sticks, random access memory (RAM), read-only memory (ROM), etc.

[0439] The above description is intended to be illustrative and not restrictive. For example, the above examples (or one or more aspects thereof) may be used in combination with each other. Other embodiments may be used by those skilled in the art upon review of the above description. An abstract is provided to allow the reader to quickly determine the nature of the technical disclosure. It should be understood that this abstract is not intended to interpret or limit the scope or meaning of the claims. Furthermore, in the above detailed description, various features may be combined together to simplify the disclosure. This should not be construed as meaning that any unclaimed disclosed feature is essential for any claim. Rather, the inventive subject matter may exist with fewer than all the features of the particular disclosed embodiment. Therefore, the following claims are thus incorporated into the detailed description as examples or embodiments, wherein each claim is an independent, separate embodiment, and such embodiments are considered to be combined with each other in various combinations or arrangements. The scope of this subject matter should be determined with reference to the claims and the full scope of their authorized equivalents.

Claims

1. A system for generating a bolus dose for a host, the system comprising: At least one processor, said processor being programmed to perform operations including the following: The first method for determining the injection configuration parameters includes: The issue involves displaying at least one first injection configuration parameter in the user interface. The user interface receives at least one first answer to the at least one first betting configuration parameter question, the at least one first answer describing the host's previous betting determination technique; Use at least one first answer to select at least one second recommendation configuration parameter question; The issue of providing the at least one second injection configuration parameter at the user interface; Receive at least one second answer to the question regarding the at least one second push configuration parameter through the user interface; The first suggestion configuration parameter is derived using the at least one first answer and the at least one second answer, wherein neither the at least one first answer nor the at least one second answer contains the first suggestion configuration parameter; Based on the at least one first answer and the at least one second answer, it is determined that the second recommendation configuration parameter cannot be obtained through the first method; In response to determining that the second push configuration parameter cannot be obtained by the first method, the second push configuration parameter is determined by a second method different from the first method, the second method including using a trained model that associates the second push configuration parameter with one or more of the at least one first answer and the at least one second answer; Receive host glucose concentration from a continuous glucose sensor; The host's injection dose is determined using the host glucose concentration, the first injection configuration parameter, and the second injection configuration parameter; an indication of the injection dose is displayed at the user interface. Receive at least one additional host glucose concentration after the bolus dose is delivered to the host from the continuous glucose sensor; as well as The trained model is retrained based on the provided injection dose and the at least one additional host glucose concentration.

2. The system of claim 1, wherein the operation further comprises using the at least one first answer to select a second set of questions, wherein the second push configuration parameter question is part of the second set of questions.

3. The system according to claim 1, wherein the operation further comprises: After receiving the at least one second answer, it is determined that the at least one first answer and the at least one second answer are insufficient to determine at least the first push configuration parameter; and A third injection configuration parameter question is provided at the user interface, wherein the derivation of the first injection configuration parameter is also based at least in part on the third answer to the third injection configuration parameter question.

4. The system of claim 1, wherein the at least one first answer indicates that the host's previous injection determination technique takes into account indications of glucose concentration and dietary intake, and wherein the at least one second answer to the at least one second injection configuration parameter question indicates that the host's previous injection determination technique uses a formula.

5. The system according to claim 1, The first answer indicates that the host's previous injection determination technique took into account the injection-related diet. The at least one of the second injection configuration parameter issues requires the host to provide an instruction for the injection insulin dose according to the previously determined injection technique and an instruction for a diet associated with the injection insulin dose according to the previously determined injection technique; The at least one second answer contains information about at least one bolus insulin dose regarding at least one exemplary diet; and The derivation of the first injection configuration parameter includes deriving the insulin-carbohydrate ratio based on information about at least one injection dose of insulin for at least one exemplary diet, and the first injection configuration parameter includes the insulin-carbohydrate ratio.

6. The system according to claim 1, wherein: The at least one first answer indicates that the host's previous injection determination technique took into account the host's glucose concentration. When there is a specific deviation between the host's glucose concentration during a diet and the host's target glucose concentration, the at least one second injection configuration parameter issue requires the host to provide an indication of changes in the injection insulin dosage; The at least one second answer contains information related to changes in insulin administration during the diet when the specific deviation is present; as well as The derivation of the first injection configuration parameter includes deriving an insulin sensitivity factor based on information related to changes in the administration of the injected insulin, and the first injection configuration parameter includes the insulin sensitivity factor.

7. The system of claim 1, wherein the at least one first answer instructs the host’s previous injection determination technique to use an injection dose independent of dietary intake or blood glucose, and wherein the determination of the second injection configuration parameter comprises performing the trained model at least in part based on the at least one first answer and the at least one second answer to generate the second injection configuration parameter.

8. The system of claim 1, wherein the operation further comprises sending data describing the bolus dose to an insulin delivery system, the data being used to provide the bolus dose to the host via the insulin delivery system.

9. A method for generating a bolus insulin dose for a host using a bolus application, the method comprising: The first method for determining the injection configuration parameters includes: The problem involves the injection application and the display of at least one first injection configuration parameter at the injection application user interface; Receive at least one first answer to the at least one first betting configuration parameter question through the betting application and through the betting application user interface, the at least one first answer describing the host's previous betting determination technique; Use at least one first answer to select at least one second recommendation configuration parameter question; The issue is addressed by providing the at least one second injection configuration parameter through the injection application and at the injection application user interface. Receive at least one second answer to the at least one second injection configuration parameter question through the injection application and through the injection application user interface; The first prediction configuration parameter is derived by the prediction application using at least one first answer and at least one second answer, wherein neither the at least one first answer nor the at least one second answer contains the first prediction configuration parameter; Based on the at least one first answer and the at least one second answer, it is determined that the second recommendation configuration parameter cannot be obtained through the first method; In response to determining that the second push configuration parameter cannot be obtained by the first method, the second push configuration parameter is determined by a second method different from the first method, the second method comprising using a trained model that associates the second push configuration parameter with one or more of the at least one first answer and the at least one second answer; The host glucose concentration is received via the injection application and from a continuous glucose sensor; The insulin injection dose for the host is determined by the injection application using the host glucose concentration, the first injection configuration parameter, and the second injection configuration parameter. The insulin injection dose is indicated by displaying the injection dose at the injection application user interface. Receive at least one additional host glucose concentration from the continuous glucose sensor after the insulin bolus is administered to the host; as well as The trained model is retrained based on the provided injection dose and the at least one additional host glucose concentration.

10. The method of claim 9, further comprising using the at least one first answer to select a second set of questions, wherein the second push configuration parameter question is part of the second set of questions.

11. The method of claim 9, further comprising: After receiving the at least one second answer, the betting application determines that it is capable of calculating all of less than one set of betting configuration parameters; and The third injection configuration parameter question is provided through the injection application and at the injection application user interface, wherein the derivation of the first injection configuration parameter is at least partially based on the third answer to the third injection configuration parameter question.

12. The method of claim 9, wherein the at least one first answer indicates that the host's previous injection determination technique takes into account indications of glucose concentration and dietary intake, and wherein the at least one second answer to the at least one second injection configuration parameter question indicates that the host's previous injection determination technique uses a formula.

13. The method of claim 9, wherein the at least one first answer indicates that the host's prior injection determination technique takes into account an injection-related diet, and wherein the second answer to the at least one second injection configuration parameter question requires the host to provide an indication of the injection insulin dose according to the prior injection determination technique and an indication of a diet associated with the injection insulin dose according to the prior injection determination technique.

14. The method of claim 9, wherein the at least one first answer indicates that the host's previous injection determination technique took into account the host's glucose concentration, and wherein the second answer to the at least one second injection configuration parameter question requests the host to provide an indication of the injection insulin dose and an indication of the deviation between the host's glucose concentration and the host's target glucose concentration.

15. The method of claim 9, wherein the at least one first answer instructs the host's previous injection determination technique to use an injection dose independent of dietary intake or blood glucose, and wherein the determination of the second injection configuration parameter comprises performing the trained model at least in part based on the at least one first answer and the at least one second answer to generate the second injection configuration parameter.

16. The method of claim 9, further comprising sending data describing the bolus insulin dose to the insulin delivery system via the bolus application, the data being used to provide the bolus insulin dose to the host via the insulin delivery system.

17. A machine-readable medium having instructions thereon, said instructions, when executed by at least one processor, causing said at least one processor to perform operations including: The first method for determining the injection configuration parameters includes: The issue involves displaying at least one first injection configuration parameter in the user interface. The user interface receives at least one first answer to the at least one first betting configuration parameter question, the at least one first answer describing the host's previous betting determination technique; Use at least one first answer to select at least one second recommendation configuration parameter question; The issue of providing the at least one second injection configuration parameter at the user interface; Receive at least one second answer to the question regarding the at least one second push configuration parameter through the user interface; The first suggestion configuration parameter is derived using the at least one first answer and the at least one second answer, wherein neither the at least one first answer nor the at least one second answer contains the first suggestion configuration parameter; Based on the at least one first answer and the at least one second answer, it is determined that the second recommendation configuration parameter cannot be obtained through the first method; In response to determining that the second push configuration parameter cannot be obtained by the first method, the second push configuration parameter is determined by a second method different from the first method, the second method comprising using a trained model that associates the second push configuration parameter with one or more of the at least one first answer and the at least one second answer; Receive host glucose concentration from a continuous glucose sensor; The host's injection dose is determined using the host glucose concentration, the first injection configuration parameter, and the second injection configuration parameter; An indication of the injection dose is displayed at the user interface; Receive at least one additional host glucose concentration after the bolus dose is delivered to the host from the continuous glucose sensor; as well as The trained model is retrained based on the provided injection dose and the at least one additional host glucose concentration.

Images