Why the study?
Improving continuous photoplethysmography-based AF detection for population screening faces challenges including a lack of large-scale labeled training data and label noise.
Does the cluster membership consistency (CMC) loss algorithm improve the accuracy of photoplethysmography-based atrial fibrillation detection using noisy labels compared to state-of-the-art methods?
Does the cluster membership consistency (CMC) loss algorithm improve the accuracy of photoplethysmography-based atrial fibrillation detection using noisy labels compared to state-of-the-art methods?
A novel cluster membership consistency loss algorithm improves the accuracy of AF detection from PPG signals trained on large-scale, noisy bedside monitor data.
Answers are grounded in this paper and cite their sources.
May aid noisy PPG-AF detection; leaves open prospective validation before clinical adoption.
Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, to improve continuous AF detection in ambulatory settings towards a population-wide screening use case, we face several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5 M 30-second records from 24,100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open-source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.
No takes yet. Share an insight, caveat, or question.
Ding et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: