Closed-Loop Glucose Control Using Predicted Duration to Target
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current glucose monitoring and control systems for diabetic patients often fail to predict and manage blood glucose levels effectively, leading to dangerous glycemic extremes due to limitations in predicting future glycemic states and responding to deviations from target ranges.
Innovation Solution
A closed-loop glucose control system that uses a glucose sensor to monitor blood glucose levels, a controller to predict the duration until a target level is reached, and an insulin infusion pump to adjust insulin delivery based on predicted trajectories and cost expressions, minimizing the risk of hypoglycemia and hyperglycemia.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If continuous glucose monitoring and insulin delivery is implemented, then glycemic control is improved, but the system complexity increases
Solution Approach 1:
The system performs self-service by automatically monitoring glucose levels through the sensor, predicting future glycemic states using the prediction algorithm, and adjusting insulin delivery through the infusion pump without requiring continuous manual intervention from the patient or healthcare provider
Solution Approach 2:
The system implements feedback control by continuously measuring current glucose levels, comparing them against target ranges, predicting future deviations, and automatically adjusting insulin delivery based on these predictions and actual measurements to maintain glycemic control
2Reliability
If prediction algorithms are added to forecast blood glucose levels, then future glycemic states are better managed, but computational requirements and processing time increase
Solution Approach 1:
The system performs preliminary action by predicting future glycemic states before actual deviations occur, allowing the control system to proactively adjust insulin delivery to prevent hypoglycemic or hyperglycemic events rather than merely reacting to current measurements
Solution Approach 2:
The prediction algorithm dynamically adapts to individual patient physiology by continuously learning from historical glucose data and adjusting prediction parameters to match the patient's specific metabolic response patterns, improving accuracy over time
3Reliability
If automated insulin adjustment is implemented based on predictions, then glycemic control is enhanced, but the risk of control errors increases
Solution Approach 1:
The system applies beforehand cushioning by implementing safety checks and constraints on predicted insulin adjustments, preventing extreme or erroneous control actions before they can cause harm to the patient
Solution Approach 2:
The system performs preliminary anti-action by detecting potential control errors or unsafe predicted adjustments before executing them, and counteracting these potential harmful effects through validation rules and safety thresholds
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
Presented here are techniques for controlling glucose levels of a patient based on predicted time to a target glucose level. One methodology predicts a trajectory of the blood glucose level based on past observations of the blood glucose level, determines a cost expression based on the trajectory, and affects a future command to an infusion pump to affect a cost value according to the cost expression. Another methodology defines a target blood glucose concentration level for the patient, observes a current blood glucose concentration for the patient based on signals received from a blood-glucose sensor, and predicts a duration of time for the patient's blood glucose concentration to reach the target blood glucose concentration level based on the observed current blood glucose concentration.