A Novel Multi-Scale Convolutional Neural Network for Arrhythmia Classification on Reduced-lead ECGs

Pan Xia1, Zhengling He2, Yusi Zhu1, Zhongrui Bai3, Xianya Yu1, Yuqi Wang4, Fanglin Geng1, Lidong Du1, Xianxiang Chen1, Peng Wang1, Zhen Fang1
1Aerospace Information Research Institute, Chinese Academy of Sciences, 2University of Chinese Academy of Sciences, 3School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, 4Institute of Microelectronics of Chinese Academy of Sciences


The PhysioNet/Computing in Cardiology Challenge 2021 focused on exploring the utility of reduced-lead ECGs for arrhythmia classification. We proposed a novel multi-scale convolutional neural network that can classify 30 scored arrhythmias from 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead ECGs. The proposed network was achieved by multiple branch networks to effectively extract the pathological information from micro-scale to macro-scale via convolution kernels (filters). The backbone of each branch network was a carefully designed 2-D convolutional neural network (CNN) with residual connection and attention mechanism, and it can adapt to multi-lead ECGs as input. The first 10 seconds of records from corresponding leads were extracted and preprocessed as input for end-to-end training, and the prediction probabilities of 30 categories were output. The proposed algorithms were firstly evaluated on officially published datasets of 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead ECGs, and we achieved 5-fold cross-validation scores of 0.719, 0.687, 0.698, 0.695, and 0.678 by using the challenge metric. Finally, our team, AIRCAS_MEL1, achieved challenge validation scores of 0.63, 0.57, 0.58, 0.57, and 0.56 for 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead ECGs, respectively. Results showed that reduced-lead ECGs can indeed capture a wide range of arrhythmia diagnostic information, and some (4-lead, 3-lead) are even comparable to 12-lead ECGs in some limited contexts. Those reduced-lead ECGs (4-lead, 3-lead) are promising in developing smaller, lower-cost, and easier-to-use diagnostic devices that are comparable to the 12-lead standard diagnostic system.