Deep neural networks generalization and fine-tuning for 12-lead ECG classification

Aram Avetisyan, Shahane Tigranyan, Ariana A. Asatryan, Olga Mashkova, Sergey Skorik, Vladislav Ananev, Yury Markin

Abstract: Highlights•Models trained on distinct ECG records may notably differ in quality across datasets.•Pre-training models on various ECG datasets improves the classification performance.•Fine-tuning networks on smaller ECG datasets significantly improves performance.•Researchers can use pre-trained model weights to adapt them for their tasks and data.