Pruned lightweight neural networks for arrhythmia classification with clinical 12-Lead ECGs

Yunqing Liu, Jinlei Liu, Yuanyuan Tian, Yanrui Jin, Zhiyuan Li, Liqun Zhao, Chengliang Liu

Abstract: Highlights•12-lead ECG data used for nonmalignant arrhythmia classification.•Model's generalization tested with noisy, varied hold-out dataset.•Lightweight neural network strategy merges selection, pruning, finetuning, and augmentation.•Method's accuracy and practicality confirmed with MIT-BIH database.•Approach tailored for wearable devices on monitoring arrhythmias.