CGM Metric Target Modeling for Automated Insulin Delivery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current blood glucose management systems lack universally agreed-upon international targets for continuous glucose monitoring (CGM) metrics, particularly for Type 1 diabetes, leading to trade-offs in achieving glycemic control and inconsistent insulin delivery.
Innovation Solution
A method for determining corresponding targets of one or more CGM metrics based on the target of another CGM metric using a classifier and dimensionality reduction techniques, such as principal component analysis (PCA) and Pearson correlation, to optimize glycemic control systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If automated insulin delivery systems use multiple CGM metrics with different targets, then glycemic control performance improves, but system complexity and difficulty of determining appropriate targets increases
Solution Approach 1:
The system pre-determines and stores optimal target values for multiple CGM metrics (TIR, TBR, TAR, MBG) based on population data and clinical guidelines. These pre-established targets are then applied automatically to individual patients, eliminating the need for clinicians to determine each target from scratch and reducing system complexity while maintaining reliable glycemic control.
Solution Approach 2:
The system establishes specific numerical target values for different CGM metrics (e.g., TIR >70%, TBR <4%, TAR <25%, MBG 70-180 mg/dL) that can be directly implemented in automated insulin delivery systems. These parameter changes provide concrete, actionable targets that improve glycemic control reliability without requiring complex clinical judgment during operation.
2Reliability
If CGM metric targets are customized for individual patients, then glycemic control effectiveness improves, but time and resources for determining appropriate targets increases
Solution Approach 1:
The system pre-establishes evidence-based target ranges for multiple CGM metrics before patient-specific customization is needed. These pre-determined targets serve as a foundation that can be quickly adapted to individual patients without requiring extensive time for target determination, thus reducing time loss while maintaining effectiveness.
Solution Approach 2:
The system provides a comprehensive set of target values for multiple CGM metrics that covers most clinical scenarios. Clinicians can selectively apply these pre-determined targets based on individual patient needs without having to determine all targets from scratch, reducing the time investment while achieving effective glycemic control.
3Reliability
If automated insulin delivery systems optimize for multiple CGM metrics simultaneously, then overall glycemic control improves, but trade-offs between metrics make target determination inconsistent
Solution Approach 1:
The system establishes specific, pre-determined target values for multiple CGM metrics that are designed to work together. By setting concrete parameters (TIR >70%, TBR <4%, TAR <25%, MBG 70-180 mg/dL), the system provides consistent targets that optimize overall glycemic control without requiring clinicians to navigate complex trade-offs, thus improving ease of operation and consistency.
Data Source
AI summary
Disclosed herein are techniques for blood glucose management. In one example, a processor-implemented method includes receiving an input of a target value of a first continuous glucose monitoring (CGM) metric, estimating a target value of at least a second CGM metric that corresponds to the target value of the first CGM metric, and providing the estimated target value of at least the second CGM metric to a user. In some examples, the processor-implemented method also includes determining that the estimated target value of at least the second CGM metric meets a predetermined criterion, and configuring an insulin delivery system based on the target value of the first CGM metric.