Atrial Fibrillation Detection Using Heart Sound Variability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting atrial fibrillation often require long data collection windows and are not effective in detecting shorter episodes, leading to poor real-world performance.
Innovation Solution
A system and method that utilize heart sound variability, specifically amplitude and morphology variations of the first heart sound, to calculate an atrial fibrillation metric and detect atrial fibrillation episodes in a shorter time frame.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If long data collection windows are used for AF detection, then detection reliability is improved, but detection time is increased and short episodes are missed
Solution Approach 1:
The patent segments the detection process into multiple short intervals (e.g., 30-second or 1-minute windows) rather than using a single long data collection window. Each interval is independently analyzed for AF detection, allowing short episodes to be captured while maintaining reliability through multiple sampling opportunities throughout the day.
Solution Approach 2:
The system performs periodic AF detection at regular intervals (e.g., every 30 seconds or 1 minute) rather than continuous long-window analysis. This periodic sampling approach enables detection of brief AF episodes that occur between longer intervals while keeping each individual analysis window short.
2Device complexity
If R-R variability based methods are used, then device complexity is reduced, but detection precision for short episodes deteriorates
Solution Approach 1:
The detection algorithm segments heart sound signals into individual cardiac cycles and analyzes S1 variability within each short interval. This segmentation allows precise measurement of heart sound characteristics without requiring complex long-window analysis, maintaining algorithm simplicity while improving short episode detection precision.
Solution Approach 2:
The patent changes the detection parameter from R-R interval variability to S1 heart sound variability (amplitude and morphology). This parameter change enables more precise detection of short AF episodes because S1 variability exhibits greater discriminatory power for brief arrhythmia events while keeping the computational algorithm relatively simple.
Data Source
Figure 1
Figure 2A~2B
Figure 3~4
AI summary
This document discusses, among other things, systems and methods to determine amplitude and morphology variations of a first heart sound over a first number of cardiac cycles, and to calculate an atrial fibrillation metric indicative of an atrial fibrillation episode of the heart using the determined amplitude and morphology variations. The systems and methods can determine a variability score using the determined amplitude and morphology variations, and can calculate the atrial fibrillation metric using the variability score.