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

WellDoc Inc

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 computer-implemented method for treating a glucose condition of a user by receiving the user’s glucose levels over a first period of time using a continuous glucose monitoring (CGM) device configured to obtain bodily fluid via a skin penetrating component, where the user’s glucose levels are determined by sensing a concentration of analytes within the obtained bodily fluid. The method determines a time in range (TIR) value based on an amount of time the user’s glucose level is within a threshold band over a base time period and determines a TIR state based on the TIR value, and receives a glucose variability (GV) value based at least on the user’s glucose level, where the GV value is one of a standard deviation or a coefficient of variance (CV), and determines a GV state based on the GV value.

The method determines a starting state based on the TIR state and the GV state and determines that the starting state corresponds to a non-ideal state. From this non-ideal starting state, the method generates an optimized pathway to reach an ideal state based on one or more user vectors and the starting state, where the optimized pathway includes one or more adjustments to the one or more user vectors comprising a medication adjustment, a food consumption adjustment, and an exercise value, and is provided to the user via a graphical user interface (GUI) for treatment of the glucose condition.

The optimized pathway is provided as a machine learning model output that includes a user vector change based on machine learning inputs comprising the TIR state and the GV state. 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 determined based on a cohort of users with one or more user attributes in common with the user.

The method receives updated glucose levels over a second period of time using the CGM device, generates an updated optimized pathway to reach the ideal state based on the updated glucose levels, and provides the updated optimized pathway via the GUI, where the updated optimized pathway comprises insulin intake information.

Claims Coverage

Two independent claims are present. Both claim the same core workflow: CGM-based receipt of glucose levels, computation of TIR and GV values and states, determination of a non-ideal starting state, generation of an ML-based optimized pathway using user vectors, and GUI-based provision of the pathway with updates after a second period including insulin intake information.

Across both independent claims, the inventive focus is on CGM-based determination of TIR and GV values and corresponding TIR/GV states, deriving a non-ideal starting state from those states, and generating an ML-based optimized pathway that uses user vectors and user attributes, further constrained by a habit index score from a cohort with shared user attributes, with subsequent updates via a second period of CGM data including insulin intake information.

Stated Advantages

Documented Applications