Method, System and Computer Readable Medium for Predictive Hypoglycemia Detection for Mild to Moderate Exercise

• US 20180055452A1
• Filed: 08/31/2016
• Published: 03/01/2018
• Est. Priority Date: 08/31/2016
• Status: Active Grant

• Current Assignee: University of Virginia Patent Foundation (University of Virginia)
• Original Assignee: University of Virginia Patent Foundation (University of Virginia)
• Inventors: Breton, Marc D.
• Granted Patent: US 10,456,086 B2
• Time in Patent Office: Days
• CPC Class Codes: A61B 2562/0219 Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/14532 for measuring glucose, e.g. by tissue impedance measurement
• CPC Class Codes: A61B 5/4839 combined with drug delivery
• CPC Class Codes: A61B 5/7225 Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation A61B5/30, A61B5/316 take precedence; transformers for specific applications H01F38/00; amplifiers H03F
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61M 2005/14208 with a programmable infusion control system, characterised by the infusion program
• CPC Class Codes: A61M 2205/3303 Using a biosensor
• CPC Class Codes: A61M 2205/3327 Measuring
• CPC Class Codes: A61M 2205/35 Communication
• CPC Class Codes: A61M 2205/3561 local, e.g. within room or hospital
• CPC Class Codes: A61M 2205/505 Touch-screens; Virtual keyboard or keypads; Virtual buttons; Soft keys; Mouse touches
• CPC Class Codes: A61M 2205/52 with memories providing a history of measured variating parameters of apparatus or patient
• 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: G16H 40/67 for remote operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A system, method and non-transient computer readable medium for predicting hypoglycemic risk in patients with diabetes following moderate exercise. A system may include a digital processor; and an exercise module configured to generate a hypoglycemia risk signal with a hypoglycemia prediction algorithm and to determine a hypoglycemia risk state with a classifier algorithm that classifies the hypoglycemia risk signal to identify an actionable hypoglycemia risk state based on a predefined threshold.

Claims

1. A method for predicting hypoglycemia for a user comprising:

obtaining a blood glucose signal (BGstart), a ratio of absolute insulin on board over total daily insulin signal (IOB_abs/TDI), and an initial glycemic slope signal (SO);

determining a hypoglycemia risk signal with a hypoglycemia prediction algorithm that determines the probability of the user being hypoglycemic during or after exercise based on the blood glucose signal, the ratio of absolute insulin on board over total daily insulin signal, and the initial glycemic slope signal; and

determining a hypoglycemia risk state with a classifier algorithm that classifies the hypoglycemia risk signal to identify an actionable hypoglycemia risk state based on a predefined threshold.

2. The method of claim 1, wherein the hypoglycemia prediction algorithm is:

3. The method of claim 2, wherein the classifier algorithm is:

4. The method of claim 3, wherein DET_thresh is 0.4.

5. The method of claim 1, wherein the initial glycemic slope signal is obtained based on the blood glucose signal.

6. The method of claim 1 further comprising:

generating an alert if the hypoglycemia risk state indicates a risk of hypoglycemia during or after exercise.

8. The method of claim 1 further comprising:

communicating an instruction to an insulin pump if the hypoglycemic risk state indicates a risk of hypoglycemia during or after exercise.

9. The method of claim 1 further comprising:

communicating an instruction to the user to consume a determined amount of carbohydrate prior to or during the exercise if the hypoglycemia risk state indicates a risk of hypoglycemia during or after exercise.

10. The method of claim 1 further comprising:

communicating an instruction to a pump containing glucose raising drugs (e.g. glucagon) if the hypoglycemic risk state indicates a risk of hypoglycemia during or after exercise.

11. The method of claim 1 further comprising:

obtaining an activity signal from at least one sensor configured to detect when the user begins to exercise.

12. The method of claim 10, wherein the at least one sensor includes one or more of a heartrate sensor and an accelerometer.

13. The method of claim 10 further comprising:

in response to detecting that the user has begun to exercise, generating an alert if the hypoglycemia risk state indicates a risk of hypoglycemia during or after exercise.

15. The method of claim 1 wherein obtaining the blood glucose signal comprises receiving the blood glucose signal from a continuous blood glucose monitor.

17. The system of claim 15, wherein the hypoglycemia prediction algorithm is:

19. The system of claim 15 further comprising:

a display; and

wherein the digital processor is configured to generate an alert on the display if the hypoglycemia risk state indicates a risk of hypoglycemia during or after exercise.

20. The system of claim 15 further comprising:

a continuous blood glucose monitoring sensor in communication with the digital processor, the continuous blood glucose monitoring sensor configured to generate the blood glucose signal.

21. The system of claim 19 further comprising:

an insulin pump in communication with the digital processor and configured to dispense or not dispense insulin in response the determined hypoglycemia risk state.

7. The method of claim 7 further comprising:

displaying the generated alert on a display of a portable computing device.

14. The method of claim lfurther comprising:

obtaining from the user one or more additional signals corresponding to a type of exercise, an intensity of exercise, or a duration of exercise, and

wherein the hypoglycemic prediction algorithm determines the probability of the user being hypoglycemic during or after exercise based at least in part on the one or more additional signals.

16. A system for predicting exercise-induced hypoglycemia for a user comprising:

a digital processor; and

an exercise module in communication with the digital processor, configured to receive a blood glucose signal (BGstart), a ratio of absolute insulin on board over total daily insulin signal (IOB_abs/TDI), and an initial glycemic slope signal (S0),

wherein the exercise module is further configured to generate a hypoglycemia risk signal with a hypoglycemia prediction algorithm that determines the probability of the user being hypoglycemic during or after exercise based on the blood glucose signal, the ratio of absolute insulin on board over total daily insulin signal, and the initial glycemic slope signal, and is further configured to determine a hypoglycemia risk state with a classifier algorithm that classifies the hypoglycemia risk signal to identify an actionable hypoglycemia risk state based on a predefined threshold.

18. The system of claim 16, wherein the classifier algorithm is: