Synchronous ECG, PPG, and PCG Fusion for Cardiac Disease Screening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting cardiac diseases, such as CAD, are inaccurate due to independent analysis of ECG, PPG, and PCG signals, failing to exploit the relational aspects among these signals, and often result in suboptimal performance.
Innovation Solution
A system that synchronously captures ECG, PPG, and PCG signals with time stamps, preprocesses them to discard noise, and uses a pretrained Machine Learning model for analysis, incorporating subject metadata for improved cardiac disease prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If ECG, PPG, and PCG signals are analyzed independently using existing methods, then the analysis process is simple, but the accuracy of cardiac disease detection deteriorates
Solution Approach 1:
The patent merges ECG, PPG, and PCG signals into a unified analysis framework by synchronously capturing all three signals and processing them together through a single machine learning model. This integration allows the system to exploit relational aspects among the signals, improving detection accuracy while maintaining manageable system complexity through centralized processing.
Solution Approach 2:
The patent employs a universal machine learning model that can process multiple types of physiological signals (ECG, PPG, PCG) simultaneously. This multi-functional approach allows a single system to analyze different signal types with their respective features, achieving high accuracy without requiring separate specialized analysis systems for each signal type.
2Measurement precision
If multiple physiological signals are captured asynchronously in sequential manner, then the capture process is simple, but the accuracy of disease diagnosis deteriorates
Solution Approach 1:
The patent applies preliminary action by synchronously capturing ECG, PPG, and PCG signals at the data acquisition stage before any analysis occurs. This synchronous capture ensures that all signals are time-aligned from the beginning, eliminating the need for complex post-capture synchronization and enabling accurate temporal relationship analysis throughout the processing pipeline.
3Measurement precision
If only ECG and PPG signals are captured synchronously, then the system complexity is reduced, but the accuracy of cardiac disease prediction deteriorates
Solution Approach 1:
The patent extends the synchronous signal capture capability to include three types of signals (ECG, PPG, PCG) rather than just two. This multi-functional approach allows the system to leverage additional physiological information from PCG signals while maintaining a unified processing framework, achieving higher accuracy without proportionally increasing system complexity.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Embodiments herein provide a system and method for screening and monitoring of cardiac diseases by analyzing acquired physiological signals. Unlike state of art approaches that consider only synchronized ECG and PPG signals for cardiac health analysis and do not consider PCG which is a critical signal for CAD analysis, the system synchronously captures physiological signals such as photo plethysmograph (PPG), phonocardiogram (PCG) and electrocardiogram (ECG) from subject(s) and builds an analytical model in the cloud for analyzing heart conditions from the captured physiological signals. The system and method provides a fusion based approach of combining the captured physiological signals such as PPG, PCG and ECG along with other details such as subject clinical information, demography information and so on. The analytical model is pretrained using ECG. PPG and PCG along with metadata associated with the subject such as demography and clinical information.