Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review

• Published in: Computers in biology and medicine Vol. 122; p. 103801
• Main Authors: Hong, Shenda, Zhou, Yuxi, Shang, Junyuan, Xiao, Cao, Sun, Jimeng
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.07.2020; Elsevier Limited
• Subjects: Annotations; Artificial intelligence; Artificial neural networks; Biomedical engineering; Biometric Identification; Biometrics; Cardiac arrhythmia; Cardiology; Classification; Data mining; Deep Learning; Deep neural network(s); Diagnostic software; Diagnostic systems; EKG; Electrocardiogram (ECG/EKG); Electrocardiography; Engineering; Health care; Health informatics; Humans; Identification; International conferences; Keywords; Localization; Machine learning; Neural networks; Neural Networks, Computer; Noise reduction; Physiology; Recurrent neural networks; Scientific papers; Signal processing; Sleep; Sleep Stages; Systematic review; Deep learning; Systematic review; Deep neural network(s); Electrocardiogram (ECG/EKG)
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2020.103801

The electrocardiogram (ECG) is one of the most commonly used diagnostic tools in medicine and healthcare. Deep learning methods have achieved promising results on predictive healthcare tasks using ECG signals. This paper presents a systematic review of deep learning methods for ECG data from both modeling and application perspectives. We extracted papers that applied deep learning (deep neural network) models to ECG data that were published between January 1st of 2010 and February 29th of 2020 from Google Scholar, PubMed, and the Digital Bibliography & Library Project. We then analyzed each article according to three factors: tasks, models, and data. Finally, we discuss open challenges and unsolved problems in this area. The total number of papers extracted was 191. Among these papers, 108 were published after 2019. Different deep learning architectures have been used in various ECG analytics tasks, such as disease detection/classification, annotation/localization, sleep staging, biometric human identification, and denoising. The number of works on deep learning for ECG data has grown explosively in recent years. Such works have achieved accuracy comparable to that of traditional feature-based approaches and ensembles of multiple approaches can achieve even better results. Specifically, we found that a hybrid architecture of a convolutional neural network and recurrent neural network ensemble using expert features yields the best results. However, there are some new challenges and problems related to interpretability, scalability, and efficiency that must be addressed. Furthermore, it is also worth investigating new applications from the perspectives of datasets and methods. This paper summarizes existing deep learning research using ECG data from multiple perspectives and highlights existing challenges and problems to identify potential future research directions. •A systematic review of deep learning methods on Electrocardiogram data.•Including 191 papers from multiple research fields from 2010 to 2020.•Analyzing papers from perspectives of task, model and data.•Discussing 7 aspects of challenges and potential opportunities for future works.