Continuous Glucose Feature Analysis for Cardiovascular Risk Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical systems lack an integrated approach to accurately detect cardiovascular events by relying solely on cardiac parameters, which can lead to suboptimal detection and increased system complexity.
Innovation Solution
Utilizing a glucose sensor to monitor patient glucose levels and applying machine learning models to extract features such as time in glucose ranges, hypoglycemia and hyperglycemia events, and statistical metrics, to predict cardiovascular events, thereby integrating glucose data into cardiovascular risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If medical systems rely solely on cardiac parameters to detect cardiovascular events, then the system complexity is reduced, but the detection accuracy is suboptimal
Solution Approach 1:
The patent combines glucose sensing capabilities with existing cardiac monitoring functions in a single integrated medical device. The device simultaneously monitors cardiac parameters (electrical activity, hemodynamics) and glucose levels, merging previously separate monitoring systems into one unified platform that improves cardiovascular event detection without proportionally increasing system complexity
Solution Approach 2:
The medical device is designed with multi-functionality, serving both as a cardiac monitor and a glucose sensor. This universal device can detect cardiovascular events while also measuring glucose levels, providing dual diagnostic capabilities from a single implant that addresses multiple patient needs without requiring separate devices
2Measurement precision
If separate evaluations of risk based on separate parameters are used, then system complexity is reduced, but detection accuracy is improved
Solution Approach 1:
The device introduces glucose level monitoring as an intermediary parameter that mediates between cardiac function and cardiovascular risk assessment. By measuring glucose as an intermediate metabolic indicator, the system gains improved risk detection accuracy while maintaining relatively simple system architecture through a single integrated sensor rather than multiple separate evaluation systems
Data Source
AI summary
This disclosure is directed to systems and techniques for detecting change in patient health based upon patient data. In one example, a medical system comprising processing circuitry communicably coupled to a glucose sensor and configured to generate continuous glucose sensor measurements of a patient. The processing circuitry is further configured to: extract at least one feature from the continuous glucose sensor measurements over at least one time period, wherein the at least one feature comprises one or more of an amount of time within a pre-determined glucose level range, a number of hypoglycemia events, a number of hyperglycemia events, or one or more statistical metrics corresponding to the continuous glucose sensor measurements; apply a machine learning model to the at least one extracted feature to produce data indicative of a risk of a cardiovascular event; and generate output data based on the risk of the cardiovascular event.