ECG-Based Heart Arrhythmia Diagnosis Through Attentional Convolutional Neural Networks
Ziyu Liu, Xiang Zhang
Abstract
Electrocardiography (ECG) signal is a highly applied measurement of the heart electrical activity for individual heart function and condition. Among the heart diseases can be indicate by ECG monitoring, much effort have been endeavored towards automatic heart arrhythmia diagnosis based on machine learning methods. However, traditional machine learning models require time-consuming preprocessing and laborious feature extraction which highly depend on domain knowledge. Here, we propose a novel deep learning model, named Attention-Based Convolutional Neural Networks (ABCNN) that taking advantage of CNN and multi-head attention, to work straight on raw ECG data and extract the informative dependencies automatically for accurate arrhythmia detection. The proposed method is evaluated by extensive experiments over a public benchmark ECG dataset. Our main task is to find the arrhythmia from normal heartbeats and, at the meantime, accurately recognize the heart diseases from five arrhythmia types. We also provide convergence analysis of ABCNN and intuitively show the meaningfulness of extracted representation through visualization. The experimental results show that the proposed ABCNN outperforms the widely used baselines, which puts one step closer to intelligent heart disease diagnosis system.