Investigation of glycemic events in blood glucose data
Inventors
Biesinger, William Jacob Benhardt • Burkart, Joshua • BEACH, Nathan Dickerson • Cheng, Shih-Yo
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12396664-B1
Publication Date
2025-08-26
Expiration Date
Abstract
To better understand the impact of glycemic events, some entities have begun examining the relationship between the blood glucose level and another physiological parameter. However, this relationship can be difficult to understand. Introduced here are computer programs and associated computer-implemented techniques for discovering glycemic events in a series of data values representative of blood glucose measurements and then altering the measurement schedule of a sensor capable of generating measurements in a dimension other than blood glucose based on the glycemic events. By altering the measurement schedule of the sensor, a diabetes management platform can better understand how, if at all, dimensions other than blood glucose are related to the glycemic health state of a subject whose blood glucose level is being monitored.
Core Innovation
The document describes a diabetes management platform that identifies a potential instance of a glycemic event by applying a model to a series of explicit values representative of discrete measurements of blood glucose of an individual, and by producing a series of imputed values for the blood glucose of the individual. The platform parses the series of explicit values and/or the series of imputed values to discover one or more values that are determined to be representative of the potential instance of the glycemic event.
After identifying the potential instance of a glycemic event, the platform alters a measurement schedule of a sensor by increasing a frequency at which the sensor measures a physiological parameter other than blood glucose. The increased frequency is applied over an interval of time that corresponds to the potential instance of the glycemic event, so as to increase insight into the physiological parameter over that interval while conserving power during intervals of time that are less relevant to glycemic health of the individual.
The document further describes modulating sensor measurement frequency and resolution/polling frequency to align sensor activity with glycemic-event-relevant intervals, while conserving power at other times. It also characterizes glucose excursions and provides statistical glucose imputation approaches using an imputation model, including Gaussian process model and Kalman filtering model. It includes real-time investigation and predictive investigation workflows and corresponding schedule modulation behavior, and it provides post-glycemic event reporting based on discovered representative values and measurements in other physiological dimensions.
Claims Coverage
The independent claims are directed to a non-transitory medium (instructions stored on a processor) and to methods (processor-executed operations) that identify a potential instance or variation/event by examining explicit blood glucose values and imputed/predicted values and modulate sensor measurement frequency in a non-blood glucose measurement dimension over a corresponding time interval to increase insight while conserving power. Across the independent claims, the inventive content centers on imputed/predicted glucose-based event identification and schedule/sensor frequency modulation, with the third independent claim emphasizing health variation identification from a first physiological parameter and frequency modulation of a second sensor.
Event identification using imputed glucose values
Applying, to a series of explicit values representative of discrete measurements of blood glucose of an individual, a model that produces a series of imputed values for the blood glucose, and parsing the series of explicit values and/or the series of imputed values to discover one or more values determined to be representative of a potential instance of the glycemic event.
Schedule alteration for non-blood glucose sensor insight
Altering, in response to said identifying, a measurement schedule of a sensor by increasing a frequency at which the sensor measures a physiological parameter other than blood glucose, over an interval of time that corresponds to the potential instance of the glycemic event, to increase insight into the physiological parameter while conserving power during intervals of time that are less relevant to glycemic health.
Frequency modulation based on representative event values from explicit and imputed series
Obtaining a series of explicit values and a series of imputed values represented of predicted measurements of the blood glucose level; detecting an instance of a glycemic event by examining the series of explicit values and the series of imputed values to discover one or more values determined to be representative of the instance; and modulating a frequency with which a sensor generates one or more physical measurements for the individual in a measurement dimension other than blood glucose over an interval of time that corresponds to the instance, to increase insight while conserving power during intervals less relevant to glycemic health.
Health variation identification from temporally ordered physiological measurements
Examining a signal representative of discrete, digitally-represented measurements generated by a first sensor for a first physiological parameter and arranged in temporal order, to identify a variation in the first physiological parameter that corresponds to a change in health of an individual.
Conserving power through second-sensor frequency modulation during identified variation
Modulating a frequency with which a second sensor generates one or more measurements of a second physiological parameter over an interval of time corresponding to the variation, so as to increase insight into the second physiological parameter as the individual experiences the change in health while conserving power when the individual is not experiencing variations in the first physiological parameter.
Across the independent claims, the core coverage combines discovering representative glycemic-event values using explicit blood glucose values together with imputed or predicted values and modulating sensor measurement schedules or frequency for non-blood glucose measurements during the event-related interval, while conserving power outside less relevant times. A related independent claim expands the concept to identifying a health-related variation from temporally ordered measurements of a first physiological parameter and modulating a second sensor’s measurement frequency during the interval corresponding to that variation to increase insight while conserving power.
Stated Advantages
Increase insight into the physiological parameter over an interval of time that corresponds to the potential instance of the glycemic event.
Conserve power during intervals of time that are less relevant to glycemic health of the individual.
Increase insight into the measurement dimension while conserving power during intervals of time that are less relevant to glycemic health.
Increase insight into a second physiological parameter as the individual experiences the change in health.
Conserve power when the individual is not experiencing variations in the first physiological parameter.
Documented Applications
A diabetes management platform that discovers glycemic events or excursions in blood glucose data using explicit values and imputed values and adapts a non-blood glucose sensor measurement schedule based on detected events or predicted onsets.
Real-time investigation and predictive investigation workflows that modulate sensor measurement behavior around detected or expected event timing.
Post-glycemic event reporting or notification to the individual or health coach based on discovered glycemic-event representative values and physiological measurements in other dimensions.
Interested in licensing this patent?