Background: Electrocardiogram (ECG) is one of the most commonly used diagnostic tools in medicine and healthcare. Deep learning methods have achieved promising results predictive healthcare tasks using ECG signals. Objective: This paper conducts a systematic review of deep learning methods on ECG data from both model and application perspectives. Methods: We extracted papers that deploy deep learning (deep neural networks) models on ECG data that published between January 1st 2010 and February 29th 2020 from Google Scholar, PubMed, and DBLP. We then analyze them in three aspects, including task, model, and data. Last we discuss open challenges and unsolved problems in this area. Results: The total number of papers is 191; among them, 108 papers are published after the year 2019. Almost all kinds of common deep learning architectures have been used in ECG analytics tasks like disease detection/classification, annotation/localization, sleep staging, biometric human identification, denoising, and so on.
Conclusion:The number of works about deep learning on Electrocardiogram data is growing explosively in recent years. Indeed, these works have achieved a far better performance in terms of accuracy. However, there are some new challenges and problems like interpretability, scalability, efficiency, which need to be addressed and paid more attention. Moreover, it is also worth investigating by discovering new interesting applications from both the dataset view and the method view. Significance: This paper summarizes existing deep learning methods on modeling ECG data from multiple views while also point out existing challenges and problems while it can become a potential research direction in the future.