Exercise Glucose Model for Intensity-Independent Insulin Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing models for predicting blood glucose levels in diabetics fail to accurately account for the effects of physical activity, particularly aerobic exercise, leading to increased risks of hypoglycemia due to neglecting exercise intensity, and are complex with numerous parameters difficult to identify.
Innovation Solution
A simplified exercise model that uses two parameters, exercise glucose effectiveness and exercise input, independent of exercise intensity, to predict blood glucose levels, allowing for real-time adjustments in insulin delivery and reducing model complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex models with multiple parameters are used to describe exercise effects, then modeling accuracy may improve, but parameter identification becomes difficult and model complexity increases
Solution Approach 1:
The patent extracts only the essential parameter (exercise glucose effectiveness) from complex exercise models, eliminating unnecessary parameters while maintaining predictive accuracy for blood glucose changes during exercise
Solution Approach 2:
The patent changes the approach from using multiple intensity-dependent parameters to a single parameter (exercise glucose effectiveness) that captures exercise effects across different intensities, simplifying the model while maintaining accuracy
2Reliability
If exercise intensity is included as a parameter, then the model may better predict blood glucose changes, but the number of parameters increases making identification difficult
Solution Approach 1:
The patent creates a universal parameter (exercise glucose effectiveness) that works across different exercise intensities and types, making the model applicable to various exercise scenarios without requiring separate parameters for each condition
Solution Approach 2:
The patent transforms intensity-dependent exercise effects into a single intensity-independent parameter, allowing the model to predict blood glucose changes during exercise of varying intensities using the same parameter
3Device complexity
If the model neglects exercise effects, then the model remains simple, but the risk of hypoglycemia during exercise increases dramatically
Solution Approach 1:
The patent extracts the critical exercise effect from complex physiological models, isolating the essential parameter (exercise glucose effectiveness) that predicts hypoglycemia risk while maintaining model simplicity
Solution Approach 2:
The model provides feedback about exercise-induced blood glucose changes, enabling timely insulin adjustments to prevent hypoglycemia while keeping the model structure simple
Data Source
AI summary
A system and method for considering the effects of aerobic exercise on blood glucose levels for individuals is described. In at least one embodiment of the system of the present disclosure, the system comprises a computing device for generating a prediction of future blood glucose levels for the individual at least partly based on an exercise model, wherein the exercise model is based on parameters that are independent of intensity of the aerobic exercise, and a means for taking an action at least based on the prediction from the exercise model.