Personal Metabolic Model for Predictive Blood Glucose Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing blood glucose monitoring methods only allow for reactive management of blood sugar levels, primarily benefiting individuals with diabetes, and do not facilitate proactive control or monitoring for general health management.
Innovation Solution
A computer-implemented method and system that simulates a user's metabolic system using a personalized digital model, predicting blood glucose responses to food intake and generating recommendations for improved glucose management, utilizing machine learning models trained with user data and real-time feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional blood glucose monitoring methods are used, then blood glucose levels can be measured, but only reactive management is possible requiring regular testing
Solution Approach 1:
The system performs preliminary action by predicting future blood glucose levels before they actually occur. The metabolic response model forecasts glucose excursions in advance of food intake events, enabling users to take preventive action rather than reacting after glucose levels have already changed. This eliminates the need for frequent reactive testing.
Solution Approach 2:
The system implements feedback by continuously monitoring actual glucose measurements and using them to refine and retrain the metabolic response model. This closed-loop feedback mechanism improves prediction accuracy over time while reducing the frequency of required measurements, thereby decreasing testing burden while maintaining or improving management quality.
2Loss of information
If reactive blood glucose testing is performed, then current glucose levels can be identified, but proactive control is not enabled
Solution Approach 1:
The system generates predictions of glucose responses to various food intake scenarios before the user actually consumes the food. This preliminary information provision enables proactive decision-making about dietary choices, allowing users to prevent unwanted glucose excursions rather than merely responding to them after occurrence.
Solution Approach 2:
The metabolic response model acts as an intermediary between food intake and glucose measurement. Instead of directly measuring glucose and reacting, the model simulates the metabolic process and provides predictive information about future glucose levels, enabling intermediate preventive actions.
3Reliability
If regular blood glucose testing is required, then glucose management can be performed, but user burden increases
Solution Approach 1:
The system creates a digital copy or virtual model of the user's metabolic system. This metabolic response model replicates the complex physiological glucose regulation process, allowing predictions to be made without physically measuring glucose repeatedly. The virtual model captures individual metabolic characteristics while eliminating the need for frequent physical testing.
Solution Approach 2:
The system transitions from measuring multiple glucose parameters over time to estimating a single predictive parameter (future glucose level) based on food intake characteristics. This parameter transformation reduces the frequency and complexity of measurements while maintaining reliable glucose management through the predictive capability.
Data Source
AI summary
Simulating a user's metabolic system and predicting a blood glucose response based on a specified food intake event includes receiving characteristic data representative of specified user characteristics, converting said characteristic data into object data and utilising said object data and a master model to generate a personal digital model representative of said user's metabolic system, receiving food intake data representative of a said specified food intake event, obtaining or generating current glucose data for said user, inputting said food intake data to said personal digital model, and generating, using said personal digital model, a simulation of said user's metabolic system in response to said food intake data and generating a predicted blood glucose response to said specified food intake event, outputting data representative of said predicted blood glucose response, and utilising said data representative of said predicted blood glucose response to retrain said master model and said personal digital model.