Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals

• Published in: Computers in biology and medicine Vol. 94; pp. 19 - 26
• Main Authors: Tan, Jen Hong, Hagiwara, Yuki, Pang, Winnie, Lim, Ivy, Oh, Shu Lih, Adam, Muhammad, Tan, Ru San, Chen, Ming, Acharya, U. Rajendra
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2018; Elsevier Limited
• Subjects: Accuracy; Artificial neural networks; Automation; Cardiology; Cardiovascular disease; Classification; Computer memory; Convolutional neural network; Coronary artery; Coronary artery disease; Coronary Artery Disease - diagnosis; Coronary Artery Disease - physiopathology; Coronary vessels; Decomposition; Deep learning; Diagnosis, Computer-Assisted - methods; Diagnostic software; Diagnostic systems; Echocardiography; EKG; Electrocardiogram signals; Electrocardiography; Female; Heart attacks; Heart diseases; Heart rate; Humans; Internal Medicine; Long short-term memory; Machine learning; Male; Neural networks; Neural Networks (Computer); Other; PhysioNet database; Short term; Signal Processing, Computer-Assisted; Deep learning; Long short-term memory; Electrocardiogram signals; PhysioNet database; Coronary artery disease; Convolutional neural network
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2017.12.023

Coronary artery disease (CAD) is the most common cause of heart disease globally. This is because there is no symptom exhibited in its initial phase until the disease progresses to an advanced stage. The electrocardiogram (ECG) is a widely accessible diagnostic tool to diagnose CAD that captures abnormal activity of the heart. However, it lacks diagnostic sensitivity. One reason is that, it is very challenging to visually interpret the ECG signal due to its very low amplitude. Hence, identification of abnormal ECG morphology by clinicians may be prone to error. Thus, it is essential to develop a software which can provide an automated and objective interpretation of the ECG signal. This paper proposes the implementation of long short-term memory (LSTM) network with convolutional neural network (CNN) to automatically diagnose CAD ECG signals accurately. Our proposed deep learning model is able to detect CAD ECG signals with a diagnostic accuracy of 99.85% with blindfold strategy. The developed prototype model is ready to be tested with an appropriate huge database before the clinical usage. [Display omitted] •Classification of normal and CAD ECG signals.•Implemented two deep learning approaches.•Subject-specific data classification.•Obtained accuracy of 99.85% using blindfold method.