Systems and methods for analyzing, interpreting, and acting on continuous glucose monitoring data
Inventors
Liu, Shiping • SHOMALI, Mansur • KUMBARA, Abhimanyu • Iyer, Anand • Peeples, Malinda • DUGAS, Michelle • CROWLEY, Kenyon • GAO, Guodong
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-11344232-B2
Publication Date
2022-05-31
Expiration Date
Abstract
Methods and devices include automated coaching for management of glucose states by receiving a user's glucose levels using a continuous glucose monitoring (CGM) device, determining a time in range (TIR) value, determining a TIR state, receiving a glucose variability (GV) value, determining a GV state, determining a starting state based on the TIR state and the GV state, determining that the starting state corresponds to a non-ideal state, generating an optimized pathway to reach an ideal state based on one or more account vectors such as addressing self-management behavior including food, activity, and medication use. The optimized pathway may further be based on computer detection and classification of significant events of interest over time.
Core Innovation
The invention provides a system for providing glucose trend based behavior outputs for treatment of a glucose based condition. A continuous glucose monitoring (CGM) device outputs a plurality of glucose readings based on analyzing a bodily fluid over a period of time, and a memory stores the plurality of glucose readings. A processor determines a CGM trend based on a change in the glucose readings and/or stored readings using a CGM trace over time, wherein the CGM trend is further based on at least one of a CGM event or a severity score.
Based on the CGM trend and at least one additional factor, the processor determines at least one behavior output comprising insulin intake information and other behavior outputs such as dietary adjustment and exercise adjustment. The system provides the behavior output to the user via a graphical user interface (GUI). The processor then receives an updated CGM trace after providing the behavior output, and generates an updated optimized pathway to reach an ideal state based on the updated CGM trace.
The invention further generates an optimized pathway to reach an ideal state based on one or more user vectors and the CGM trend, where the optimized pathway comprises one or more adjustments to the one or more user vectors, including a medication adjustment, a food consumption adjustment, and an exercise value. The optimized pathway is provided to the user via the GUI and is provided as a machine learning model output including a user vector change based on machine learning inputs comprising the severity score of the CGM trace. Machine learning inputs further include user attributes and are further based on a habit index score of the user determined based on a cohort of users with one or more user attributes in common with the user.
Claims Coverage
The partial content includes three independent claims. Across the independent claims, the coverage centers on determining a CGM trend from a CGM trace and severity score or CGM event, using that trend with additional factors and a machine learning model to produce insulin intake information and related behavior outputs, and generating an optimized pathway to reach an ideal state via a GUI using user vectors, user attributes, and a habit index score, with model updates based on an updated CGM trace.
Glucose trend and severity/event-based behavior outputs with insulin intake information
A processor determines a CGM trend based on a change in CGM readings using a CGM trace mapping glucose readings over time, wherein the CGM trend is further based on at least one of a CGM event or a severity score; determines at least one behavior output based on the CGM trend and at least one additional factor, the at least one behavior output comprising insulin intake information; and provides the at least one behavior output to the user.
Optimized pathway to reach an ideal state using user vectors and CGM trend
The processor generates an optimized pathway to reach an ideal state based on one or more user vectors and the CGM trend, where the optimized pathway comprises one or more adjustments to the one or more user vectors, the one or more adjustments comprise a medication adjustment, a food consumption adjustment, and an exercise value; and provides the optimized pathway to the user via a GUI for treatment using the adjustments to the one or more user vectors.
Machine learning model output with user vector change, user attributes, and habit index score
The optimized pathway is provided as a machine learning model output, the machine learning model output comprising a user vector change based on machine learning inputs comprising the severity score of the CGM trace; the machine learning model inputs further comprise user attributes including a medical attribute, a user preference, a metabolic attribute, and a user demographic; and the optimized pathway is further based on a habit index score of the user determined based on a cohort of users with one or more user attributes in common with the user.
Iterative update loop using updated CGM trace and updated optimized pathway
The system receives an updated CGM trace over a second period of time using the CGM device by sensing an updated concentration of glucose within bodily fluid obtained during the second period of time; generates an updated optimized pathway to reach the ideal state based on the updated CGM trace, the updated optimized pathway comprising insulin intake information; and provides the updated optimized pathway to the user via the GUI.
Behavior categories and machine-learning-driven behavior category outputs
The processor identifies at least one behavior category selected from whether insulin is needed, how much insulin is needed, whether glucose is needed, how much glucose is needed, whether food consumption is needed, how much food consumption is needed, whether exercise is needed, or how much exercise is needed based on the CGM trend and the at least one additional factor; determines at least one behavior output from the identified behavior category using a machine learning model configured to output the at least one behavior output based on inputs comprising one or more past behavior outputs and a corresponding change in a past CGM trend; where the at least one behavior output comprises insulin intake information and at least one of a dietary adjustment and an exercise adjustment.
CGM reading acquisition and sampling increment requirement
The CGM device obtains glucose readings by accessing bodily fluid via a user's skin and is configured to obtain a glucose reading in increments of five minutes or less.
Overall, the independent claims cover deriving a CGM trend from a CGM trace with CGM events and/or a severity score, using that trend with additional factors to produce insulin intake information and other behavior outputs, generating and displaying an optimized pathway to an ideal state via a GUI using user vectors and machine learning outputs that incorporate user attributes and a habit index score, and iteratively updating the pathway based on an updated CGM trace. Some embodiments further specify behavior categories and require CGM glucose readings in increments of five minutes or less.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?