Personalized Glucose-Based Meal Detection for Infusion Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing infusion pump systems struggle with accurately regulating blood glucose levels due to variations in insulin response and patient-specific factors, and manual meal indications are burdensome and often missed, complicating glucose management.
Innovation Solution
A patient-specific meal detection model autonomously identifies meal occurrences based on historical glucose measurement statistics and correlation coefficients, flagging meal-related data without manual input, and adjusts infusion device operations accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual meal indication is required for glucose management, then patient-specific glucose responses can be tracked, but patient burden increases and meal indications are frequently missed
Solution Approach 1:
The system performs self-service by automatically detecting meals through analysis of glucose measurement patterns without requiring patient action. The processor identifies meal occurrences by detecting characteristic glucose response patterns, eliminating the need for manual patient input while maintaining accurate meal detection for glucose management
Solution Approach 2:
The patent replaces the mechanical/manual system of patient-induced meal indications with an automated detection system. Instead of relying on patients to manually input meal information, the system uses processors to analyze glucose measurement data and automatically identify meal events based on pattern recognition algorithms
2Loss of information
If continuous glucose monitoring is implemented, then understanding of patient condition improves, but data complexity and analysis burden increase
Solution Approach 1:
The system extracts only the most relevant information from continuous glucose monitoring data by focusing on pattern recognition for meal detection. Instead of requiring comprehensive analysis of all glucose data, the processor identifies specific patterns characteristic of meal responses, extracting key insights while filtering out unnecessary complexity
Solution Approach 2:
The patent introduces an intermediary processing layer that translates complex continuous glucose monitoring data into simplified meal detection events. The processor acts as an intermediary between the raw glucose data and the clinical decision-making process, converting complex time-series data into actionable meal occurrence indicators
3Measurement precision
If personalized meal detection models are used, then meal detection accuracy improves, but computational requirements and processing time increase
Solution Approach 1:
The system performs preliminary action by pre-processing glucose measurement data and maintaining running statistics as data arrives. The processor continuously updates glucose measurement statistics and pattern recognition parameters in real-time, preparing the data structure in advance so that meal detection can occur rapidly when patterns are identified, reducing actual detection processing time
Data Source
AI summary
Techniques for detection of occurrence of a meal are provided. In some embodiments, the techniques may involve obtaining a plurality of glucose measurements indicative of a glucose level in a body of a patient during an analysis interval. The techniques may further involve detecting an occurrence of a meal during the analysis interval based on the plurality of glucose measurements obtained during the analysis interval. The techniques may further involve updating a user interface to include an indication of the meal detected during the analysis interval.