Closed-Loop Artificial Pancreas Cost Function for Glycemic Excursion Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional closed loop insulin delivery systems fail to account for individual differences in daily insulin needs, leading to inadequate insulin dosages that can result in hypoglycemia or hyperglycemia for users with high or low insulin requirements.
Innovation Solution
A closed loop artificial pancreas system uses a customized cost function that adjusts penalty ratios based on a user's individual insulin needs, balancing glucose and insulin excursions to optimize insulin dosages.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed cost function with standard penalty ratios is used in closed loop insulin delivery, then the system structure is simple and easy to implement, but it cannot account for individual differences in daily insulin needs, leading to inadequate insulin dosages
Solution Approach 1:
The patent applies parameter changes by making the penalty ratios in the cost function user-specific rather than fixed. Each user has customized penalty ratios (first penalty ratio for glucose excursions, second penalty ratio for insulin deliveries) that are tailored to their individual insulin needs, sensitivity, and glucose patterns. This allows the system to adapt to individual differences while maintaining the same cost function structure.
Solution Approach 2:
The patent implements dynamics by allowing the penalty ratios to be adjusted and updated over time based on user response to insulin deliveries and glucose monitoring data. The system dynamically adapts the cost function parameters to match the user's changing insulin needs and sensitivity, making the system flexible and responsive to individual requirements.
2Reliability
If manually delivered boluses are used, then the system is simple to operate, but users may deliver improper amounts of insulin, putting the patient at risk of hypoglycemia
Solution Approach 1:
The patent implements feedback by continuously monitoring glucose levels and using this information to adjust insulin delivery decisions. The closed loop system receives glucose data, evaluates it against the customized cost function, and automatically adjusts subsequent insulin deliveries based on the observed response, creating a feedback mechanism that improves dosage accuracy over time.
Solution Approach 2:
The patent applies self-service by enabling the system to automatically determine and adjust insulin dosages without requiring manual user input for each decision. The customized cost function with user-specific penalty ratios allows the system to autonomously optimize insulin delivery based on individual needs, reducing reliance on user judgment while improving reliability.
3Reliability
If closed loop systems deliver smaller insulin doses more frequently, then the risk of hypoglycemia is reduced, but the system complexity increases compared to manual bolus delivery
Solution Approach 1:
The patent applies parameter changes by customizing the penalty ratios in the cost function to reflect individual user characteristics such as insulin sensitivity and glucose response patterns. This allows the system to optimize the balance between delivering sufficient insulin to prevent hyperglycemia and avoiding excessive insulin that could cause hypoglycemia, with each user having tailored parameters.
Solution Approach 2:
The patent implements preliminary action by pre-configuring user-specific penalty ratios based on initial assessments of insulin needs, sensitivity, and glucose patterns. This preliminary customization prepares the cost function to make more accurate insulin delivery decisions from the start, reducing the need for complex real-time adjustments and lowering overall system complexity.
Data Source
AI summary
Exemplary embodiments described herein relate to a closed loop artificial pancreas system. The artificial pancreas system seeks to automatically and continuously control the blood glucose level of a user by emulating the endocrine functionality of a healthy pancreas. The artificial pancreas system uses a closed loop control system with a cost function. The penalty function helps to bound the infusion rate of insulin to attempt to avoid hypoglycemia and hyperglycemia. However, unlike conventional systems that use a generic or baseline parameter for a user's insulin needs in a cost function, the exemplary embodiments may use a customized parameter in the cost function that reflects the individualized insulin needs of the user. The use of the customized parameter causes the cost function to result in insulin dosages over time better suited to the individualized insulin needs of the user. This helps to better avoid hypoglycemia and hyperglycemia.