Automatic ECG Diagnosis Using Convolutional Neural Network

TLDR

Cardiovascular disease is the leading chronic life‑threatening illness and a primary cause of mortality worldwide. This work proposes a novel convolutional neural network architecture for automatic heart‑disease diagnosis from electrocardiogram signals. The model was trained and evaluated on over 4,000 ECG recordings from 47 outpatient subjects, with raw signals fed directly into the CNN. The system achieved an overall accuracy of 98.33 %, correctly classifying 99 % of normal beats, 100 % of atrial premature beats, and 96 % of premature ventricular contractions, with sensitivity and specificity of 98.33 % and 98.35 %, respectively.

Abstract

Cardiovascular disease (CVD) is the most common class of chronic and life-threatening diseases and, therefore, considered to be one of the main causes of mortality. The proposed new neural architecture based on the recent popularity of convolutional neural networks (CNN) was a solution for the development of automatic heart disease diagnosis systems using electrocardiogram (ECG) signals. More specifically, ECG signals were passed directly to a properly trained CNN network. The database consisted of more than 4000 ECG signal instances extracted from outpatient ECG examinations obtained from 47 subjects: 25 males and 22 females. The confusion matrix derived from the testing dataset indicated 99% accuracy for the “normal” class. For the “atrial premature beat” class, ECG segments were correctly classified 100% of the time. Finally, for the “premature ventricular contraction” class, ECG segments were correctly classified 96% of the time. In total, there was an average classification accuracy of 98.33%. The sensitivity (SNS) and the specificity (SPC) were, respectively, 98.33% and 98.35%. The new approach based on deep learning and, in particular, on a CNN network guaranteed excellent performance in automatic recognition and, therefore, prevention of cardiovascular diseases.