A novel application of deep learning for single-lead ECG classification

• Published in: Computers in biology and medicine Vol. 99; pp. 53 - 62
• Main Authors: Mathews, Sherin M., Kambhamettu, Chandra, Barner, Kenneth E.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.08.2018; Elsevier Limited
• Subjects: Abnormalities; Accuracy; Algorithms; Artificial intelligence; Artificial neural networks; Belief networks; Blood pressure; Cardiac arrhythmia; Classification; Computer simulation; Datasets; Deep belief networks (DBN); Deep learning; Echocardiography; EKG; Electromyography; Feature extraction; Heart rate; Heartbeat classification; MIT-BIH database; Morphology; Nerve conduction; Neural networks; Restricted Boltzmann machine; Sampling; Signal classification; single-lead ECG recognition; Ventricle; Restricted Boltzmann machine; Deep learning; single-lead ECG recognition; Deep belief networks (DBN); Heartbeat classification; MIT-BIH database
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2018.05.013

Detecting and classifying cardiac arrhythmias is critical to the diagnosis of patients with cardiac abnormalities. In this paper, a novel approach based on deep learning methodology is proposed for the classification of single-lead electrocardiogram (ECG) signals. We demonstrate the application of the Restricted Boltzmann Machine (RBM) and deep belief networks (DBN) for ECG classification following detection of ventricular and supraventricular heartbeats using single-lead ECG. The effectiveness of this proposed algorithm is illustrated using real ECG signals from the widely-used MIT-BIH database. Simulation results demonstrate that with a suitable choice of parameters, RBM and DBN can achieve high average recognition accuracies of ventricular ectopic beats (93.63%) and of supraventricular ectopic beats (95.57%) at a low sampling rate of 114 Hz. Experimental results indicate that classifiers built into this deep learning-based framework achieved state-of-the art performance models at lower sampling rates and simple features when compared to traditional methods. Further, employing features extracted at a sampling rate of 114 Hz when combined with deep learning provided enough discriminatory power for the classification task. This performance is comparable to that of traditional methods and uses a much lower sampling rate and simpler features. Thus, our proposed deep neural network algorithm demonstrates that deep learning-based methods offer accurate ECG classification and could potentially be extended to other physiological signal classifications, such as those in arterial blood pressure (ABP), nerve conduction (EMG), and heart rate variability (HRV) studies. •Deep learning framework using Restricted Boltzmann Machine & Deep Belief Networks is proposed for ECG arrhythmia classification.•The proposed methodology performs robust features extraction for ECG signals at a very low sampling rate of 114 Hz.•Results demonstrate state-of-the-art accuracies at lower sampling rates using proposed framework & simple features.