INSULIN DOSAGE ASSESSMENT AND RECOMMENDATION SYSTEM

• US 20140019396A1
• Filed: 07/11/2012
• Published: 01/16/2014
• Est. Priority Date: 07/11/2012
• Status: Active Grant

• Current Assignee: Roche Diabetes Care Inc. (Roche Holding AG)
• Original Assignee: Roche Diagnostics Operations Incorporated (Roche Holding AG)
• Inventors: Rees, Christen, Wagner, Robin S., Carlsgaard, Peter B.
• Granted Patent: US 9,990,581 B2
• Time in Patent Office: Days
• US Class Current: 706/46
• CPC Class Codes: A61M 5/1723 using feedback of body parameters, e.g. blood-sugar, pressure measurement of body parameters A61B5/00
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G16H 20/17 delivered via infusion or injection
• CPC Class Codes: G16H 40/60 for the operation of medical equipment or devices
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/70 for mining of medical data, e.g. analysing previous cases of other patients

Abstract

A computer-implemented method is presented for recommending insulin dosage adjustments for a patient having diabetes. The method includes: identifying a plurality of bolus events from patient data; grouping bolus events having a recommended bolus dosage substantially equivalent to the amount of administered insulin into a first subset of bolus events; determining a bolus outcome for each of the bolus events in the first subset of bolus events, where the bolus outcome is expressed in relation to a target range of blood glucose values and is selected from a group including above the target range, in the target range and below the target range; determining whether one of the bolus outcomes is predominant amongst the bolus events in the first subset of bolus events; and generating a recommendation pertaining to insulin dosage for the patient in response to a determination that one of the bolus outcomes is predominant.

Claims

1. A computer-implemented method for recommending insulin dosage adjustments for a patient having diabetes, comprising:

receiving patient data pertaining to diabetes care of the patient;

identifying a plurality of bolus events from the patient data, each of the identified bolus events having associated therewith a bolus dosage of insulin recommended to the patient, an amount of insulin administered to the patient in response to the recommended bolus dosage, and a blood glucose measure taken during an acting time of the administered insulin;

grouping, from the plurality of bolus events, bolus events having a recommended bolus dosage substantially equivalent to the amount of administered insulin into a first subset of bolus events;

determining a bolus outcome for each of the bolus events in the first subset of bolus events, where the bolus outcome is expressed in relation to a target range of blood glucose values and is selected from a group including above the target range, in the target range and below the target range;

determining whether one of the bolus outcomes is predominant amongst the bolus events in the first subset of bolus events; and

generating a recommendation pertaining to insulin dosage for the patient in response to a determination that one of the bolus outcomes is predominant, wherein the steps of identifying, grouping and determining are executed by a processor of a computing device.

2. The method of claim 1 wherein the step of identifying a plurality of bolus events further comprises partitioning a day into a plurality of time periods, identifying a given time period from amongst the plurality of time periods, and selecting bolus events from the plurality of bolus events which occurred in the given time period.

3. The method of claim 1 wherein the step of determining whether one of the bolus outcomes is predominant further comprises calculating a percentage of bolus outcomes in each grouping of bolus outcomes in relation to a number of bolus events in the first subset of bolus events.

4. The method of claim 3 further comprises deeming a given group of bolus outcomes are predominant when the percentage of the given group of bolus outcomes exceeds a predefined threshold.

5. The method of claim 1 further comprises recommending to maintain current insulin dosage in response to a determination that bolus outcomes in the first subset of bolus events is predominantly in the target range of blood glucose values.

6. The method of claim 1 further comprises recommending an increase in insulin dosage in response to a determination that bolus outcomes in the first subset of bolus events is predominantly above the target range of blood glucose values.

7. The method of claim 1 further comprises recommending a decrease in insulin dosage in response to a determination that bolus outcomes in the first subset of bolus events is predominantly below the target range of blood glucose values.

8. The method of claim 1 further comprises recommending, in response to a determination that bolus outcomes in the first subset of bolus events are predominantly outside the target range of blood glucose values, to acquire blood glucose measures from the patient in accordance with a structured collection procedure, where the structured collection procedure specifies timing for one or more collection events for obtaining blood glucose measures from the patient.

9. The method of claim 1 further comprises

grouping, from the plurality of bolus events, bolus events having a recommended bolus dosage that differs from the amount of administered insulin, into a second subset of bolus events;

determining a bolus outcome for each of the bolus events in the second subset of bolus events, where the bolus outcome is expressed in relation to a target range of blood glucose values and is selected from a group including above the target range, in the target range and below the target range;

determining whether the bolus outcomes in the second subset of bolus events is predominantly in the target range of blood glucose values; and

generating a recommendation pertaining to insulin dosage for the patient in response to a determination that the bolus outcomes in the second subset of bolus events is predominantly in the target range.

10. The method of claim 1 wherein generating a recommendation pertaining to insulin dosage further comprises assigning a weight to blood glucose measures of the patient depending on how severely a given blood glucose measure lies outside the target range and according to a mathematical transformation;

and computing a first sum of the assigned weights.

11. The method of claim 10 further comprises adjusting a value of each blood glucose measure by an adjustment amount;

assigning a weight to the adjusted blood glucose measures depending on how severely a given blood glucose measure lies outside the target range and according to a mathematical transformation; and

computing a second sum of the assigned weights.

12. The method of claim 11 further comprises comparing the first sum to the second sum and recommending an adjustment to the insulin dosage when the second sum is less than the first sum.

13. A non-transitory processor-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations, comprising:

receiving patient data pertaining to diabetes care of a patient;

identifying a plurality of bolus events from the patient data, each of the identified bolus events having associated therewith a bolus dosage of insulin recommended to the patient, an amount of insulin administered to the patient in response to the recommended bolus dosage, and a blood glucose measure taken during an acting time of the administered insulin;

grouping, from the plurality of bolus events, bolus events having a recommended bolus dosage substantially equivalent to the amount of administered insulin into a first subset of bolus events;

determining a bolus outcome for each of the bolus events in the first subset of bolus events, where the bolus outcome is expressed in relation to a target range of blood glucose values and is selected from a group including above the target range, in the target range and below the target range;

determining whether one of the bolus outcomes is predominant amongst the bolus events in the first subset of bolus events; and

generating a recommendation pertaining to insulin dosage for the patient in response to a determination that one of the bolus outcomes is predominant.

14. A computer-implemented method for recommending insulin dosage adjustments for a patient having diabetes, comprising:

receiving patient data pertaining to diabetes care of the patient;

identifying a plurality of bolus events from the patient data, each of the identified bolus events having associated therewith a bolus dosage of insulin recommended to the patient, an amount of insulin administered to the patient in response to the recommended bolus dosage, and a blood glucose measure taken during an acting time of the administered insulin;

grouping, from the plurality of bolus events, bolus events having a recommended bolus dosage substantially equivalent to the amount of administered insulin into a first subset of bolus events;

grouping, from the plurality of bolus events, bolus events having a recommended bolus dosage that differs from the amount of administered insulin, into a second subset of bolus events;

determining a bolus outcome for each of the bolus events in the second subset of bolus events, where the bolus outcome is expressed in relation to a target range of blood glucose values and is selected from a group including above the target range, in the target range and below the target range;

determining whether the bolus outcomes in the second subset of bolus events is predominantly in the target range of blood glucose values; and

generating a recommendation pertaining to insulin dosage for the patient in response to a determination that the bolus outcomes in the second subset of bolus events is predominantly in the target range, wherein the steps of identifying, grouping and determining are executed by a processor of a computing device.

15. The method of claim 14 wherein the step of determining whether the bolus outcomes is predominant further comprises calculating a percentage of bolus outcomes in the target range in relation to a number of bolus events in the second subset of bolus events and deeming the bolus outcomes are predominant when the percentage of bolus outcomes exceeds a predefined threshold.

16. The method of claim 14 wherein generating a recommendation further comprises calculating coefficients of a linear equation using the bolus events in the second subset of bolus events, where the linear equation computes the bolus dosage of insulin recommended to the patient.

17. A computer-implemented method for recommending insulin dosage adjustments for a patient having diabetes, comprising:

receiving patient data pertaining to diabetes care of the patient;

identifying a plurality of fasting periods from the patient data, each of the identified fasting periods having associated therewith at least one blood glucose measure;

determining a basal outcome for each of the fasting periods in the plurality of fasting periods, where the basal outcome is expressed in relation to a target range of blood glucose values and selected from a group including above the target range, in the target range and below the target range;

determining whether one of the basal outcomes is predominant amongst the fasting periods in the plurality of fasting periods; and

evaluating a bolus dosage of insulin prescribed for the patient in response to a determination that basal outcomes for the patient are predominantly in the target range of blood glucose values, wherein evaluating a bolus dosage includes

identifying a plurality of bolus events from the patient data, each of the identified bolus events having associated therewith a bolus dosage of insulin recommended to the patient, an amount of insulin administered to the patient in response to the recommended bolus dosage, and a blood glucose measure taken during an acting time of the administered insulin;

grouping, from the plurality of bolus events, bolus events having a recommended bolus dosage substantially equivalent to the amount of administered insulin into a first subset of bolus events;

determining a bolus outcome for each of the bolus events in the first subset of bolus events, where the bolus outcome is expressed in relation to a target range of blood glucose values and is selected from a group including above the target range, in the target range and below the target range;

determining whether one of the bolus outcomes is predominant amongst the bolus events in the first subset of bolus events; and

generating a recommendation pertaining to insulin dosage for the patient in response to a determination that one of the bolus outcomes is predominant, wherein the steps of identifying, determining and evaluating are executed by a processor of a computing device.

18. The method of claim 17 wherein the step of determining whether one of the basal outcomes is predominant further comprises calculating a percentage of basal outcomes in each grouping of basal outcomes in relation to a number of basal outcomes in the plurality of fasting periods.

19. The method of claim 18 further comprises deeming a given group of basal outcomes is predominant when the percentage of the given group of basal outcomes exceeds a predefined threshold.

20. The method of claim 17 further comprises recommending to maintain current insulin dosage in response to a determination that basal outcomes for the patient are predominantly in the target range of blood glucose values.

21. The method of claim 17 further comprises recommending an increase in insulin dosage in response to a determination that basal outcomes for the patient are predominantly above the target range of blood glucose values.

22. The method of claim 17 further comprises recommending a decrease in insulin dosage in response to a determination that basal outcomes for the patient are predominantly below the target range of blood glucose values.

23. The method of claim 17 further comprises recommending, in response to a determination that basal outcomes are predominantly outside the target range of blood glucose values, to acquire blood glucose measures from the patient in accordance with a structured collection procedure, where the structured collection procedure specifies timing for one or more collection events for obtaining blood glucose measures from the patient.

24. The method of claim 17 wherein each of the identified fasting periods having associated therewith a starting blood glucose measure taken proximate to a start of the fasting period, an ending blood glucose measure taken proximate to an end of the fasting period and at least one intermediate blood glucose measure taken between the starting blood glucose measure and the ending blood glucose measure.