Insulin Delivery Modeling for Fasting and Postprandial Periods
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing insulin infusion devices struggle to accurately calculate and administer insulin boluses to maintain blood glucose levels within the desired range, particularly during fasting and postprandial periods, due to variations in user behavior and glucose responses.
Innovation Solution
A method and system for identifying fasting and postprandial periods based on detected events, using a mathematical model trained with therapy-related data and event detection to adapt insulin delivery strategies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single mathematical model is used for insulin delivery, then the device complexity is reduced, but the accuracy of insulin dosing during different periods (fasting vs. postprandial) deteriorates
Solution Approach 1:
The patent divides the insulin delivery control into separate mathematical models for different periods: a first mathematical model for fasting periods and a second mathematical model for postprandial periods. This segmentation allows each model to be optimized for its specific period, improving dosing accuracy without requiring a single overly complex model to handle all scenarios.
Solution Approach 2:
The system dynamically switches between different mathematical models based on the detected period (fasting or postprandial). The insulin delivery strategy adapts in real-time by selecting the appropriate model, allowing the system to maintain high accuracy across varying conditions without permanently increasing structural complexity.
2Adaptability or versatility
If period identification based on detected events is implemented, then the adaptability to user behavior is improved, but the device complexity increases
Solution Approach 1:
The system automatically detects events (such as meal intake, exercise, sleep) and uses these detected events to identify fasting and postprandial periods without requiring manual user input. This self-service approach improves adaptability to user behavior while minimizing the complexity burden on the user, as the system performs the detection and classification autonomously.
Solution Approach 2:
The system uses detected events as feedback to continuously refine period identification and adjust insulin delivery strategies. By incorporating event detection feedback loops, the system adapts to user behavior patterns while maintaining a manageable complexity level through iterative learning rather than requiring complex pre-programming.
Data Source
AI summary
Technologies are provided for identifying fasting and postprandial periods based on detected events and using the same to train a mathematical model. Events during a period can be detected via an event detection system. Each detected event can include a specific activity that is indicative of a physical behavior of the user. Training data and the detected events can be processed to determine timing of fasting periods, timing of postprandial periods, and timing of other periods. Training data from the fasting periods and other training data from the postprandial periods can be identified. The mathematical model of the user can be trained to identify fasting parameters of a physiological blood glucose response of the user during the fasting periods, and fasting parameters of a physiological blood glucose response of the user (differently) during postprandial periods.