TY - JOUR
T1 - Opportunities and challenges of deep learning methods for electrocardiogram data
T2 - A systematic review
AU - Hong, Shenda
AU - Zhou, Yuxi
AU - Shang, Junyuan
AU - Xiao, Cao
AU - Sun, Jimeng
N1 - Funding Information:
This work was partially supported by the National Science Foundation awards IIS-1418511 , CCF-1533768 and IIS-1838042 , and the National Institute of Health awards NIH R01 1R01NS107291–01 and R56HL138415 .
Publisher Copyright:
© 2020
PY - 2020/7
Y1 - 2020/7
N2 - Background: 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. Objective: This paper presents a systematic review of deep learning methods for ECG data from both modeling and application perspectives. Methods: 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. Results: 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. Conclusion: 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. Significance: 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.
AB - Background: 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. Objective: This paper presents a systematic review of deep learning methods for ECG data from both modeling and application perspectives. Methods: 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. Results: 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. Conclusion: 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. Significance: 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.
KW - Deep learning
KW - Deep neural network(s)
KW - Electrocardiogram (ECG/EKG)
KW - Systematic review
UR - http://www.scopus.com/inward/record.url?scp=85086066646&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85086066646&partnerID=8YFLogxK
U2 - 10.1016/j.compbiomed.2020.103801
DO - 10.1016/j.compbiomed.2020.103801
M3 - Review article
C2 - 32658725
AN - SCOPUS:85086066646
SN - 0010-4825
VL - 122
JO - Computers in Biology and Medicine
JF - Computers in Biology and Medicine
M1 - 103801
ER -