A visually interpretable detection method combines 3-D ECG with a multi-VGG neural network for myocardial infarction identification

Rui Fang, Chih-Cheng Lu, Cheng-Ta Chuang, Wen-Han Chang

Abstract: Highlights•A visually interpretable method combines 3-D ECG with deep neural network for MI identification.•Multi-DNN architecture improves classification accuracy in both PTB and PTB-XL database.•Grad-CAM++ experiment boosts network visual interpretability for MI patients.•Promising work offers efficacy in assisting physicians for heart disease diagnosis.