2026-06-29T08:02:17Zhttps://docta.ucm.es/rest/oai/request

oai:docta.ucm.es:20.500.14352/1329292026-02-23T15:30:32Zcom_20.500.14352_14col_20.500.14352_15

Reducing leads, enhancing wearable practicality: A comparative study of 3-lead vs. 12-lead ECG classification González-Cabeza, Sergio Sanz-Guerrero, Mario Piñuel, Luis Buelga Suárez, Mauro Luis Alonso Salinas, Gonzalo Luis Diaz-Vicente, Marian Recas Piorno, Joaquín Deep learning Electrocardiography One-vs-All classification Reduced-lead ECG Transfer learning Informática (Informática) 33 Ciencias Tecnológicas 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. Depto. de Arquitectura de Computadores y Automática Fac. de Informática TRUE pub 2026-02-23T15:30:31Z 2026-02-23T15:30:31Z 2025 journal article AM https://hdl.handle.net/20.500.14352/132929 XXXX-XXXX 10.1016/j.medengphy.2025.104419 eng metadata only access