Atrial Fibrillation Detection Using PPG Scatter Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies face challenges in accurately detecting atrial fibrillation using wearable devices, as existing methods struggle to differentiate between normal heart rhythms and atrial fibrillation effectively.
Innovation Solution
The system employs photoplethysmographic (PPG) signal data from wearable devices to determine heartbeats and heart rhythm types. It utilizes metrics such as occupancy, distance, and interval variability to differentiate between normal heart rhythms and atrial fibrillation, and displays an alert when atrial fibrillation is detected.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional heart rhythm analysis methods are used, then the device complexity is low, but the measurement precision of atrial fibrillation detection is insufficient
Solution Approach 1:
The patent segments the heart rhythm analysis into multiple distinct metrics: occupancy metric (scatter analysis), distance metric (consecutive point distances), and interval variability metric (heartbeat interval changes). Each metric captures different aspects of rhythm irregularity, and their combined use improves detection accuracy while keeping individual metric calculations computationally simple
Solution Approach 2:
The patent transforms 1D heartbeat interval data into 2D scatter plots by plotting consecutive heartbeat intervals against each other. This dimensional transformation enables visualization and quantitative analysis of rhythm patterns that are not apparent in temporal sequences alone, improving atrial fibrillation detection through geometric properties of the scatter distribution
2Measurement precision
If multiple metrics are used for heart rhythm classification, then the measurement precision improves, but the loss of information increases due to complex data processing
Solution Approach 1:
The patent extracts three specific quantitative features from the PPG signal: occupancy (fraction of bins with points), distance (median distance between consecutive points), and interval variability (median absolute change in heartbeat intervals). By extracting only these essential features rather than processing entire signal waveforms, the system achieves high classification accuracy while minimizing information loss and processing complexity
Solution Approach 2:
The patent transforms raw heartbeat interval data into standardized metrics with defined statistical properties (medians, fractions). These parameter transformations normalize the data and highlight clinically relevant patterns, improving classification precision while maintaining data integrity through reversible mathematical operations
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables accurate detection of atrial fibrillation by analyzing PPG signal data with advanced metrics, improving the reliability of heart rhythm classification and facilitating timely alerts for users.
Implementation Method 1
photoplethysmographic (PPG) signal data may be received as communicated by a PPG sensor of a wearable device worn by a user
Data Source
AI summary
Systems, methods, and computer software for detecting atrial fibrillation are described. Photoplethysmographic (PPG) signal data may be received as communicated by a PPG sensor of a wearable device worn by a user. Heartbeats from a portion of the PPG signal data may be determined and a heart rhythm type may be determined based on at least the heartbeats. A determination of whether the heart rhythm type includes Atrial Fibrillation (AF) may be made, and, when AF is detected, an AF detection alert may be displayed at the wearable device.