Unannounced Meal Estimation via Glucose Variation Difference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current blood glucose management systems for type 1 diabetes, both closed-loop and open-loop, rely on feed-forward actions and struggle to accurately and quickly estimate the size of unannounced meals, leading to delays in insulin compensation and increased risks of glycemic imbalances.
Innovation Solution
A method and system that estimate the size of unannounced meals by calculating the variation difference between measured and expected glucose variations using a storage module, expectation module, and estimation module, incorporating user-specific parameters, with safety thresholds to prevent excessive insulin dosing and including correction and aggressiveness modules for personalized adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If current blood glucose management systems use feed-forward actions with meal announcements, then they can achieve effective control, but they fail to detect and respond to unannounced meals timely
Solution Approach 1:
The system performs preliminary detection of unannounced meals by monitoring blood glucose trends before the meal impact fully manifests. The expectation module predicts expected glucose values based on insulin on board and user parameters, allowing the system to detect deviations early and initiate compensation before hyperglycemia develops.
Solution Approach 2:
The system implements feedback by continuously comparing measured blood glucose values against expected values derived from insulin on board calculations. When deviations exceed thresholds, the system triggers compensation actions. This closed-loop feedback enables automatic detection and response to unannounced meals without requiring user input.
2Measurement precision
If the system integrates glycemic rise and area under the curve for meal detection, then detection accuracy improves, but estimation delay increases to around 20 minutes
Solution Approach 1:
The system segments the meal detection process into two independent components: detection (using glucose variation and expected glucose variation comparison) and estimation (using the same variation data). This segmentation allows detection to occur immediately when glucose patterns match criteria, while estimation can be performed concurrently without waiting for area under the curve integration, reducing overall delay.
Solution Approach 2:
The expectation module performs preliminary calculation of expected glucose values based on insulin on board and user-specific parameters before actual meal impact occurs. This allows the system to detect unannounced meals at the moment of detection rather than waiting for glycemic rise integration, significantly reducing estimation delay while maintaining accuracy.
3Stability of the object's composition
If the system uses PD controller for compensation, then control stability improves, but additional delays are introduced
Solution Approach 1:
The system performs preliminary detection and estimation of unannounced meals before traditional PD controller compensation would activate. By detecting glucose deviations early and estimating meal size immediately, the system can initiate compensation actions before the full glycemic impact occurs, reducing the effective delay despite using stable control algorithms.
Data Source
Figure 1~3
Figure 4~5
AI summary
A method for estimating a size of an unannounced meal ingested by a user, the method being implemented by a system, said system comprising: - a storage module (301), said storage module storing a time series of glucose value of the user in a glucose storage, - an expectation module (302), said expectation module (302) determining an expected glucose variation for a given time point, - an estimation module (11), said estimation module (11) estimating the size of the unannounced meal ingested based on: - a variation difference between - a measured glucose variation between a glucose value at the given time point and a glucose value at a time point of the time series anterior to the given time point, the glucose values being acquired by a glycemia acquisition system or stored in the glucose storage; and - the expected glucose variation between the glucose value at the given time point and the glucose value at the time point of the time series anterior to the given time point; - at least one user parameter relative and personalized to the user.