Wearable Cardiac Detection Using Entropy Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing wearable devices face challenges in balancing battery life and accuracy when monitoring cardiovascular conditions, often resulting in false positives or false negatives due to the limitations of single-lead ECG or PPG sensors, which can lead to reduced data quality and delayed medical intervention.
Innovation Solution
A wearable device equipped with a first sensor for continuous monitoring and a second sensor for detailed data collection, utilizing a cardiovascular classifier to analyze entropy in inter-beat interval data and prompt users for higher-quality signal acquisition when anomalies are detected, with the classifier being trained and updated using cloud-based data from multiple sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If continuous monitoring using single-lead ECG or PPG sensors is implemented, then cardiovascular events can be detected, but false positives and false negatives occur reducing accuracy
Solution Approach 1:
The patent combines data from multiple sensors (ECG and PPG sensors) to improve detection accuracy. By merging the strengths of different sensor types, the system reduces false positives and false negatives that occur when using single-lead ECG or PPG sensors alone, thereby resolving the contradiction between reliability and measurement precision.
Solution Approach 2:
The wearable device incorporates multiple sensing capabilities (ECG and PPG) within a single device, enabling it to perform multiple detection functions. This multi-functionality allows the system to cross-validate signals and improve overall detection accuracy, addressing the limitation of single-sensor systems.
2Reliability
If detailed data collection using second sensor is performed continuously, then detection accuracy improves, but battery life is reduced
Solution Approach 1:
The system employs periodic sampling and event-triggered data collection rather than continuous monitoring. The second sensor is activated selectively based on detected cardiac events or anomalies, allowing detailed data collection only when needed. This periodic action maintains high detection accuracy while significantly reducing battery consumption compared to continuous operation.
Solution Approach 2:
The patent implements partial monitoring by using the first sensor for continuous basic monitoring and activating the second sensor only partially (when events are detected). This partial action approach provides sufficient detection accuracy for clinical purposes while minimizing energy usage, avoiding the excessive battery drain of continuous detailed monitoring.
3Measurement precision
If entropy analysis and cardiovascular classifier are used, then false positives and negatives are reduced, but computational complexity increases
Solution Approach 1:
The system performs preliminary filtering and preprocessing of sensor signals before applying complex entropy analysis and cardiovascular classification. By preparing and conditioning the data in advance, the system reduces the computational burden of subsequent complex analyses while maintaining high detection accuracy and reducing false positives and negatives.
Solution Approach 2:
The patent introduces intermediate processing steps (signal conditioning, feature extraction, preliminary filtering) that bridge the gap between raw sensor data and complex entropy analysis. These intermediary processes simplify the data structure and reduce computational complexity while preserving the information needed for accurate cardiovascular event detection.
Data Source
AI summary
In some embodiments, features related to inter-beat intervals (IBI) detected by a PPG sensor of a wearable device are extracted and provided to a cardiovascular classifier in order to detect likely instances of a cardiac condition such as atrial fibrillation. Some embodiments use features related to the entropy of the IBI data to improve the predictions generated by the cardiovascular classifier. In some embodiments, co-information between the IBI data and IBI data gathered from healthy and AF populations is determined in order to derive features that represent the probability that a given sample of IBI data represents AF or a normal sinus rhythm. In response to determining likely instances of AF based on these features, the wearable device may obtain clinically acceptable data, such as an ECG, to be transmitted to a separate device for review by a clinician.