Method, System and Computer Readable Medium for Predictive Hypoglycemia Detection for Mild to Moderate Exercise
First Claim
Patent Images
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 (IOBabs/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 Assignments
0 Petitions
Accused Products
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.
7 Citations
21 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 (IOBabs/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. - View Dependent Claims (2, 3, 4, 5, 6, 8, 9, 10, 11, 12, 13, 15, 17, 19, 20, 21)
-
-
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 (IOBabs/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. - View Dependent Claims (18)
-
Specification