Deep convolutional neural networks based ECG beats classification to diagnose cardiovascular conditions
Rashed-Al-Mahfuz Md., Moni Mohammad Ali, Lio’ Pietro, Islam Sheikh Mohammed Shariful, Berkovsky Shlomo, Khushi Matloob, Quinn Julian M. W.,
소속 상세정보
( Rashed-Al-Mahfuz Md. )
University of Rajshahi Department of Computer Science and Engineering
( Moni Mohammad Ali )
University of New South Wales School of Public Health and Community Medicine
( Lio’ Pietro )
University of Cambridge Computer Laboratory
( Islam Sheikh Mohammed Shariful )
Deakin University School of Exercise and Nutrition Sciences
( Berkovsky Shlomo )
Macquarie University Faculty of Medicine and Health Scince Australian Institute of Health Innovation
( Khushi Matloob )
University of Sydney School of Computer Science
( Quinn Julian M. W. )
Garvan Institute of Medical Research Healthy Ageing Theme
Abstract
Medical practitioners need to understand the critical features of ECG beats to diagnose and identify cardiovascular conditions accurately. This would be greatly facilitated by identifying the significant features of frequency components in temporal ECG wave-forms using computational methods. In this study, we have proposed a novel ECG beat classifier based on a customized VGG16-based Convolution Neural Network (CNN) that uses the time-frequency representation of temporal ECG, and a method to identify the contribution of interpretable ECG frequencies when classifying based on the SHapley Additive exPlanations (SHAP) values. We applied our model to the MIT-BIH arrhythmia dataset to classify the ECG beats and to characterise of the beats frequencies. This model was evaluated with two advanced time-frequency analysis methods. Our results indicated that for 2-4 classes our proposed model achieves a classification accuracy of 100% and for 5 classes it achieves a classification accuracy of 99.90%. We have also tested the proposed model using premature ventricular contraction beats from the American Heart Association (AHA) database and normal beats from Lobachevsky University Electrocardiography database (LUDB) and obtained a classification accuracy of 99.91% for the 5-classes case. In addition, SHAP value increased the interpretability of the ECG frequency features. Thus, this model could be applicable to the automation of the cardiovascular diagnosis system and could be used by clinicians.
키워드
ECG; CNN; VGG16; ECG beats classification; SHAP value; ECG frequencies
원문 및 링크아웃 정보
등재저널 정보