System, device and method of dynamic glucose profile response to physiological parameters

Patent metadata

Field	Value
Publication number	US-12310757-B2
Application number	US-202318150996-A
Country	US
Kind code	B2
Filing date	Jan 6, 2023
Priority date	Jul 10, 2015
Publication date	May 27, 2025
Grant date	May 27, 2025

Abstract

Method, device and system for providing consistent and reliable glucose response information to physiological changes and/or activities is provided to improve glycemic control and health management.

First claim

The invention claimed is:

1. A method of identifying a glucose response pattern, comprising:
executing, by a data analysis module, a data analysis training routine, the data analysis training routine comprising:
receiving, by the data analysis module, training data including activity metric information and overnight glucose level information over a first time period including a plurality of days;
performing, by the data analysis module, a data analysis training process, the data analysis training process comprising:
categorizing, by the data analysis module, the training data into a first set and a second set, the first set including overnight glucose level information for days with a significant activity metric, and the second set including overnight glucose level information for days without the significant activity metric; and
determining, by the data analysis module, (a) a median glucose of all overnight glucose level information for the days within the second set, (b) a delta median glucose for each day in the first set, and (c) a correlation between the determined delta median glucose for each day and an activity metric corresponding to activity metric information for that day in the first set; and

determining, by the data analysis module, whether the amount of training data received and analyzed is sufficient based on the determined correlation;

receiving, by the data analysis module, a measured level of activity metric for a second time period, the second time period including a single day subsequent to the first time period; and

when the amount of training data is determined to be sufficient:
determining, by the data analysis module, based on the determined correlation and the measured level of activity metric for the second time period, the impact on overnight glucose level for the second period; and
outputting, by the data analysis module, a therapy recommendation based on the determined impact on overnight glucose level for the second time period on a user interface.

2. The method of claim 1 , wherein the days within the first time period with the significant activity metric includes a day with the activity metric exceeding a predetermined threshold, and further, wherein the days within the first time period without the significant activity metric includes a day with the activity metric below the predetermined threshold.

3. The method of claim 2 , wherein the activity metric includes an amount of calories burned during a 24 hour time period.

4. The method of claim 2 , wherein the activity metric includes a number of steps recorded during a 24 hour time period.

5. The method of claim 2 , wherein the activity metric includes one or more of a time duration of an activity, an intensity level of an activity, heart rate data associated with an activity, or a type of an activity.

6. The method of claim 1 , wherein the amount of training data is determined to be sufficient is based on a degree of certainty of an estimated glycemic pattern.

7. The method of claim 1 , wherein determining delta median glucose for each day in the first set includes subtracting the determined median glucose of all overnight glucose level for the second set from an overnight glucose median for each day in the first set.

8. The method of claim 1 , wherein determining the correlation includes identifying an association between each of the determined delta median glucose with the corresponding activity metric.

9. The method of claim 1 , further including outputting information associated with the determined impact on the user interface.

10. The method of claim 9 , wherein the outputted information includes glycemic pattern.

11. The method of claim 1 , further comprising:
determining, by the data analysis module, a quality of the correlation and determining whether the quality of the correlation exceeds a specific value, wherein the amount of training data is determined to be sufficient when the quality of the correlation exceeds the specific value.

12. The method of claim 1 , further comprising:
executing the data analysis training routine at a predetermined time interval, the data analysis training routine further comprising:
adding a new data set to the training data set to provide updated training data, wherein the new data set includes activity metric information and overnight glucose level information over another time period including a plurality of days;
performing the data analysis training process on the updated training data;
determining whether the amount of data in the updated training data is sufficient; and
generating and outputting a notification corresponding to whether the amount of data in the updated training data is sufficient.

13. The method of claim 12 , further comprising removing activity metric information and overnight glucose level information older than a third time period from the training data.

14. The method of claim 13 , wherein the third time period is 90 days or more.

15. The method of claim 12 , further comprising initiating reset of the data analysis training routine and clearing the training data set.

16. The method of claim 12 , wherein the predetermined time interval is once daily.

17. The method of claim 1 , further comprising fitting, by the data analysis module, the determined correlation to a predetermined function, and wherein determining the impact on overnight glucose level is based on the fitted function.

18. The method of claim 17 , wherein the predetermined function includes one of a linear function, constant offset relationship, exponential relationship, logarithmic relationship, or a polynomial relationship.

19. An apparatus for identifying a glucose response pattern, comprising:
a data input module for receiving training data including activity metric information and overnight glucose level information over a first time period including a plurality of days;
a data analysis module operatively coupled to the data input module, and configured to:
perform a data analysis training process on the received data, the data analysis training process comprising:
categorizing the overnight glucose level information for days within the first time period into a first set and a second set, the first set including overnight glucose level information for days with a significant activity metric, and the second set including overnight glucose level information for days without the significant activity metric, wherein the first set comprises at least a plurality of days with a significant activity metric;
determining (a) a median glucose of all overnight glucose level for the days in the second set, (b) a delta median glucose for each day in the first set, and (c) a correlation between the determined delta median glucose for each day and an activity metric corresponding to activity metric information for that day in the first set; and
determining whether the amount of data received and analyzed is sufficient based on the determined correlation;

receive a measured level of activity metric for a second time period, the second time period including at least a single day;
determine, based on the determined correlation and the measured level of activity metric, the impact on overnight glucose level; and

when the amount of training data is determined to be sufficient:
determine a therapy recommendation based on the determined impact on overnight glucose level for the second time period; and

a data output interface operatively coupled to the data analysis module to output information associated

Assignees

• Abbott Diabetes Care Inc

Inventors

• Hayter Gary Alan
• Crouther Nathan Christopher
• Love Michael
• Budiman Erwin Satrya
• Bernstein Daniel Milfred

Classifications

• G16H40/67

  for remote operation · CPC title

• G16H20/17

  delivered via infusion or injection · CPC title

• G16H50/70

  for mining of medical data, e.g. analysing previous cases of other patients · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G16H20/30

  relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising · CPC title