Key result
Optimized 3-lead ECG deep learning model detects heart anomalies comparably to 12-lead models with 77% F1-score.
Why the study?
To explore the feasibility of using reduced-lead ECGs for automated detection of heart anomalies using deep learning as a more accessible, cost-effective alternative to 12-lead ECGs.
Does an optimized 3-lead ECG deep learning model provide comparable diagnostic accuracy to a 12-lead model for detecting heart anomalies?
Does an optimized 3-lead ECG deep learning model provide comparable diagnostic accuracy to a 12-lead model for detecting heart anomalies?
An optimized 3-lead ECG deep learning model achieves near-equivalent diagnostic accuracy to a 12-lead model, highlighting its potential for wearable devices.
Supports wearable ECG deployment for anomaly detection; extends 12-lead deep learning models to reduced-lead inputs.
Inspired by recent advances in clinical research and the growing adoption of wearable ECG devices, this study explores the feasibility of using reduced-lead ECGs for automated detection of heart anomalies using deep learning, providing a more accessible and cost-effective alternative to traditional 12-lead ECGs. This research adapts and evaluates a state-of-the-art 12-lead deep learning model (from Ribeiro et al. [1]) for 3-lead configurations. The 12-lead ECG model architecture was trained from scratch on the public database PTB-XL. It was then modified to use 3 leads by only changing the input layer. Despite a 75% reduction in input data, the 3-lead model showed only a subtle 3% performance drop. To address this gap, the 3-lead model was further optimized using a novel strategy that combines transfer learning and a One-vs-All classification approach. Using PTB-XL's five-class setup (normal vs. four pathologies: myocardial infarction, ST/T change, conduction disturbance, and hypertrophy), we report the micro-averaged F1-score across all test samples. The new optimized 3-lead model achieves a global (micro-averaged) F1-score of 77% (vs. 78% for the 12-lead model). These findings highlight the potential of simplified and cost-effective reduced-lead classification models to deliver near-equivalent diagnostic accuracy. This advancement could democratize access to early cardiac diagnostics, particularly in resource-limited settings.
No takes yet. Share an insight, caveat, or question.
González-Cabeza et al. (2025) studied Heart anomalies. 3-lead ECG deep learning model vs. 12-lead ECG deep learning model was evaluated on Global (micro-averaged) F1-score. An optimized 3-lead ECG deep learning model achieved a global micro-averaged F1-score of 77% for detecting heart anomalies, compared to 78% for a traditional 12-lead model.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: