1
|
Xie J, Stavrakis S, Yao B. Automated identification of atrial fibrillation from single-lead ECGs using multi-branching ResNet. Front Physiol 2024; 15:1362185. [PMID: 38655032 PMCID: PMC11035782 DOI: 10.3389/fphys.2024.1362185] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2023] [Accepted: 03/25/2024] [Indexed: 04/26/2024] Open
Abstract
Introduction: Atrial fibrillation (AF) is the most common cardiac arrhythmia, which is clinically identified with irregular and rapid heartbeat rhythm. AF puts a patient at risk of forming blood clots, which can eventually lead to heart failure, stroke, or even sudden death. Electrocardiography (ECG), which involves acquiring bioelectrical signals from the body surface to reflect heart activity, is a standard procedure for detecting AF. However, the occurrence of AF is often intermittent, costing a significant amount of time and effort from medical doctors to identify AF episodes. Moreover, human error is inevitable, as even experienced medical professionals can overlook or misinterpret subtle signs of AF. As such, it is of critical importance to develop an advanced analytical model that can automatically interpret ECG signals and provide decision support for AF diagnostics. Methods: In this paper, we propose an innovative deep-learning method for automated AF identification using single-lead ECGs. We first extract time-frequency features from ECG signals using continuous wavelet transform (CWT). Second, the convolutional neural networks enhanced with residual learning (ReNet) are employed as the functional approximator to interpret the time-frequency features extracted by CWT. Third, we propose to incorporate a multi-branching structure into the ResNet to address the issue of class imbalance, where normal ECGs significantly outnumber instances of AF in ECG datasets. Results and Discussion: We evaluate the proposed Multi-branching Resnet with CWT (CWT-MB-Resnet) with two ECG datasets, i.e., PhysioNet/CinC challenge 2017 and ECGs obtained from the University of Oklahoma Health Sciences Center (OUHSC). The proposed CWT-MB-Resnet demonstrates robust prediction performance, achieving an F1 score of 0.8865 for the PhysioNet dataset and 0.7369 for the OUHSC dataset. The experimental results signify the model's superior capability in balancing precision and recall, which is a desired attribute for ensuring reliable medical diagnoses.
Collapse
Affiliation(s)
- Jianxin Xie
- School of Data Science, University of Virginia, Charlottesville, VA, United States
| | - Stavros Stavrakis
- Health Sciences Center, University of Oklahoma, Oklahoma City, OK, United States
| | - Bing Yao
- Department of Industrial and Systems Engineering, University of Tennessee at Knoxville, Knoxville, TN, United States
| |
Collapse
|
2
|
Ullah H, Heyat MBB, Akhtar F, Muaad AY, Ukwuoma CC, Bilal M, Miraz MH, Bhuiyan MAS, Wu K, Damaševičius R, Pan T, Gao M, Lin Y, Lai D. An Automatic Premature Ventricular Contraction Recognition System Based on Imbalanced Dataset and Pre-Trained Residual Network Using Transfer Learning on ECG Signal. Diagnostics (Basel) 2022; 13:diagnostics13010087. [PMID: 36611379 PMCID: PMC9818233 DOI: 10.3390/diagnostics13010087] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2022] [Revised: 12/05/2022] [Accepted: 12/23/2022] [Indexed: 12/29/2022] Open
Abstract
The development of automatic monitoring and diagnosis systems for cardiac patients over the internet has been facilitated by recent advancements in wearable sensor devices from electrocardiographs (ECGs), which need the use of patient-specific approaches. Premature ventricular contraction (PVC) is a common chronic cardiovascular disease that can cause conditions that are potentially fatal. Therefore, for the diagnosis of likely heart failure, precise PVC detection from ECGs is crucial. In the clinical settings, cardiologists typically employ long-term ECGs as a tool to identify PVCs, where a cardiologist must put in a lot of time and effort to appropriately assess the long-term ECGs which is time consuming and cumbersome. By addressing these issues, we have investigated a deep learning method with a pre-trained deep residual network, ResNet-18, to identify PVCs automatically using transfer learning mechanism. Herein, features are extracted by the inner layers of the network automatically compared to hand-crafted feature extraction methods. Transfer learning mechanism handles the difficulties of required large volume of training data for a deep model. The pre-trained model is evaluated on the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia and Institute of Cardiological Technics (INCART) datasets. First, we used the Pan-Tompkins algorithm to segment 44,103 normal and 6423 PVC beats, as well as 106,239 normal and 9987 PVC beats from the MIT-BIH Arrhythmia and IN-CART datasets, respectively. The pre-trained model employed the segmented beats as input after being converted into 2D (two-dimensional) images. The method is optimized with the using of weighted random samples, on-the-fly augmentation, Adam optimizer, and call back feature. The results from the proposed method demonstrate the satisfactory findings without the using of any complex pre-processing and feature extraction technique as well as design complexity of model. Using LOSOCV (leave one subject out cross-validation), the received accuracies on MIT-BIH and INCART are 99.93% and 99.77%, respectively, suppressing the state-of-the-art methods for PVC recognition on unseen data. This demonstrates the efficacy and generalizability of the proposed method on the imbalanced datasets. Due to the absence of device-specific (patient-specific) information at the evaluating stage on the target datasets in this study, the method might be used as a general approach to handle the situations in which ECG signals are obtained from different patients utilizing a variety of smart sensor devices.
Collapse
Affiliation(s)
- Hadaate Ullah
- State Key Laboratory of Electronic Thin Films and Integrated Devices, School of Materials and Energy, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Md Belal Bin Heyat
- IoT Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
- Correspondence: (M.B.B.H.); (R.D.); (Y.L.); (D.L.)
| | - Faijan Akhtar
- School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
| | | | - Chiagoziem C. Ukwuoma
- School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Muhammad Bilal
- College of Pharmacy, Liaquat University of Medical and Health Sciences, Jamshoro 76090, Pakistan
| | - Mahdi H. Miraz
- School of Computing and Data Science, Xiamen University Malaysia, Bandar Sunsuria, Sepang 43900, Malaysia
- School of Computing, Glyndŵr University, Wrexham LL11 2AW, UK
| | | | - Kaishun Wu
- IoT Research Center, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, China
| | - Robertas Damaševičius
- Department of Software Engineering, Kaunas University of Technology, 44249 Kaunas, Lithuania
- Correspondence: (M.B.B.H.); (R.D.); (Y.L.); (D.L.)
| | - Taisong Pan
- State Key Laboratory of Electronic Thin Films and Integrated Devices, School of Materials and Energy, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Min Gao
- State Key Laboratory of Electronic Thin Films and Integrated Devices, School of Materials and Energy, University of Electronic Science and Technology of China, Chengdu 610054, China
| | - Yuan Lin
- State Key Laboratory of Electronic Thin Films and Integrated Devices, School of Materials and Energy, University of Electronic Science and Technology of China, Chengdu 610054, China
- Medico-Engineering Corporation on Applied Medicine Research Center, University of Electronic Science and Technology of China, Chengdu 610054, China
- Correspondence: (M.B.B.H.); (R.D.); (Y.L.); (D.L.)
| | - Dakun Lai
- Biomedical Imaging and Electrophysiology Laboratory, School of Electronic Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, China
- Correspondence: (M.B.B.H.); (R.D.); (Y.L.); (D.L.)
| |
Collapse
|
3
|
Zhang H, Liu C, Tang F, Li M, Zhang D, Xia L, Zhao N, Li S, Crozier S, Xu W, Liu F. Cardiac Arrhythmia classification based on 3D recurrence plot analysis and deep learning. Front Physiol 2022; 13:956320. [PMID: 35936913 PMCID: PMC9352947 DOI: 10.3389/fphys.2022.956320] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2022] [Accepted: 06/27/2022] [Indexed: 11/29/2022] Open
Abstract
Artificial intelligence (AI) aided cardiac arrhythmia (CA) classification has been an emerging research topic. Existing AI-based classification methods commonly analyze electrocardiogram (ECG) signals in lower dimensions, using one-dimensional (1D) temporal signals or two-dimensional (2D) images, which, however, may have limited capability in characterizing lead-wise spatiotemporal correlations, which are critical to the classification accuracy. In addition, existing methods mostly assume that the ECG data are linear temporal signals. This assumption may not accurately represent the nonlinear, nonstationary nature of the cardiac electrophysiological process. In this work, we have developed a three-dimensional (3D) recurrence plot (RP)-based deep learning algorithm to explore the nonlinear recurrent features of ECG and Vectorcardiography (VCG) signals, aiming to improve the arrhythmia classification performance. The 3D ECG/VCG images are generated from standard 12 lead ECG and 3 lead VCG signals for neural network training, validation, and testing. The superiority and effectiveness of the proposed method are validated by various experiments. Based on the PTB-XL dataset, the proposed method achieved an average F1 score of 0.9254 for the 3D ECG-based case and 0.9350 for the 3D VCG-based case. In contrast, recently published 1D and 2D ECG-based CA classification methods yielded lower average F1 scores of 0.843 and 0.9015, respectively. Thus, the improved performance and visual interpretability make the proposed 3D RP-based method appealing for practical CA classification.
Collapse
Affiliation(s)
- Hua Zhang
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD, Australia
| | - Chengyu Liu
- School of Instrument Science and Engineering, Southeast University, Nanjing, China
| | - Fangfang Tang
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD, Australia
| | - Mingyan Li
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD, Australia
| | - Dongxia Zhang
- Zhejiang Provincial Centre for Disease Control and Prevention CN, Hangzhou, China
| | - Ling Xia
- Department of Biomedical Engineering, Zhejiang University, Hangzhou, China
| | - Nan Zhao
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD, Australia
| | - Sheng Li
- The College of Science, Xijing University, Xi’an, China
| | - Stuart Crozier
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD, Australia
| | - Wenlong Xu
- Department of Biomedical Engineering, China Jiliang University, Hangzhou, China
- *Correspondence: Wenlong Xu, ; Feng Liu,
| | - Feng Liu
- School of Information Technology and Electrical Engineering, University of Queensland, Brisbane, QLD, Australia
- *Correspondence: Wenlong Xu, ; Feng Liu,
| |
Collapse
|
4
|
Interpatient ECG Arrhythmia Detection by Residual Attention CNN. COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE 2022; 2022:2323625. [PMID: 35432590 PMCID: PMC9012615 DOI: 10.1155/2022/2323625] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 01/04/2022] [Revised: 03/04/2022] [Accepted: 03/07/2022] [Indexed: 11/18/2022]
Abstract
The precise identification of arrhythmia is critical in electrocardiogram (ECG) research. Many automatic classification methods have been suggested so far. However, efficient and accurate classification is still a challenge due to the limited feature extraction and model generalization ability. We integrate attention mechanism and residual skip connection into the U-Net (RA-UNET); besides, a skip connection between the RA-UNET and a residual block is executed as a residual attention convolutional neural network (RA-CNN) for accurate classification. The model was evaluated using the MIT-BIH arrhythmia database and achieved an accuracy of 98.5% and F1 scores for the classes S and V of 82.8% and 91.7%, respectively, which is far superior to other approaches.
Collapse
|
5
|
Cai Z, Wang T, Shen Y, Xing Y, Yan R, Li J, Liu C. Robust PVC Identification by Fusing Expert System and Deep Learning. BIOSENSORS 2022; 12:185. [PMID: 35448245 PMCID: PMC9025768 DOI: 10.3390/bios12040185] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/27/2022] [Revised: 03/18/2022] [Accepted: 03/18/2022] [Indexed: 06/14/2023]
Abstract
Premature ventricular contraction (PVC) is one of the common ventricular arrhythmias, which may cause stroke or sudden cardiac death. Automatic long-term electrocardiogram (ECG) analysis algorithms could provide diagnosis suggestion and even early warning for physicians. However, they are mutually exclusive in terms of robustness, generalization and low complexity. In this study, a novel PVC recognition algorithm that combines deep learning-based heartbeat template clusterer and expert system-based heartbeat classifier is proposed. A long short-term memory-based auto-encoder (LSTM-AE) network was used to extract features from ECG heartbeats for K-means clustering. Thus, the templates were constructed and determined based on clustering results. Finally, the PVC heartbeats were recognized based on a combination of multiple rules, including template matching and rhythm characteristics. Three quantitative parameters, sensitivity (Se), positive predictive value (P+) and accuracy (ACC), were used to evaluate the performances of the proposed method on the MIT-BIH Arrhythmia database and the St. Petersburg Institute of Cardiological Technics database. Se on the two test databases was 87.51% and 87.92%, respectively; P+ was 92.47% and 93.18%, respectively; and ACC was 98.63% and 97.89%, respectively. The PVC scores on the third China Physiological Signal Challenge 2020 training set and hidden test set were 36,256 and 46,706, respectively, which could rank first in the open-source codes. The results showed that the combination strategy of expert system and deep learning can provide new insights for robust and generalized PVC identification from long-term single-lead ECG recordings.
Collapse
Affiliation(s)
- Zhipeng Cai
- School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China; (Z.C.); (T.W.); (Y.S.); (Y.X.)
| | - Tiantian Wang
- School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China; (Z.C.); (T.W.); (Y.S.); (Y.X.)
| | - Yumin Shen
- School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China; (Z.C.); (T.W.); (Y.S.); (Y.X.)
| | - Yantao Xing
- School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China; (Z.C.); (T.W.); (Y.S.); (Y.X.)
| | - Ruqiang Yan
- School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China; (Z.C.); (T.W.); (Y.S.); (Y.X.)
- School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 714009, China;
| | - Jianqing Li
- School of Mechanical Engineering, Xi’an Jiaotong University, Xi’an 714009, China;
| | - Chengyu Liu
- School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China; (Z.C.); (T.W.); (Y.S.); (Y.X.)
| |
Collapse
|
6
|
Mathunjwa BM, Lin YT, Lin CH, Abbod MF, Sadrawi M, Shieh JS. ECG Recurrence Plot-Based Arrhythmia Classification Using Two-Dimensional Deep Residual CNN Features. SENSORS 2022; 22:s22041660. [PMID: 35214561 PMCID: PMC8877903 DOI: 10.3390/s22041660] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/22/2021] [Revised: 02/10/2022] [Accepted: 02/16/2022] [Indexed: 11/26/2022]
Abstract
In this paper, an effective electrocardiogram (ECG) recurrence plot (RP)-based arrhythmia classification algorithm that can be implemented in portable devices is presented. Public databases from PhysioNet were used to conduct this study including the MIT-BIH Atrial Fibrillation Database, the MIT-BIH Arrhythmia Database, the MIT-BIH Malignant Ventricular Ectopy Database, and the Creighton University Ventricular Tachyarrhythmia Database. ECG time series were segmented and converted using an RP, and two-dimensional images were used as inputs to the CNN classifiers. In this study, two-stage classification is proposed to improve the accuracy. The ResNet-18 architecture was applied to detect ventricular fibrillation (VF) and noise during the first stage, whereas normal, atrial fibrillation, premature atrial contraction, and premature ventricular contractions were detected using ResNet-50 in the second stage. The method was evaluated using 5-fold cross-validation which improved the results when compared to previous studies, achieving first and second stage average accuracies of 97.21% and 98.36%, sensitivities of 96.49% and 97.92%, positive predictive values of 95.54% and 98.20%, and F1-scores of 95.96% and 98.05%, respectively. Furthermore, a 5-fold improvement in the memory requirement was achieved when compared with a previous study, making this classifier feasible for use in resource-constricted environments such as portable devices. Even though the method is successful, first stage training requires combining four different arrhythmia types into one label (other), which generates more data for the other category than for VF and noise, thus creating a data imbalance that affects the first stage performance.
Collapse
Affiliation(s)
| | - Yin-Tsong Lin
- AI R&D Department, New Era AI Robotic Inc., Taipei 10571, Taiwan; (Y.-T.L.); (C.-H.L.)
| | - Chien-Hung Lin
- AI R&D Department, New Era AI Robotic Inc., Taipei 10571, Taiwan; (Y.-T.L.); (C.-H.L.)
| | - Maysam F. Abbod
- Department of Electronics and Electrical Engineering, Brunel University London, London UB8 3PH, UK;
| | - Muammar Sadrawi
- Department of Bioinformatics, School of Life Sciences, Indonesia International Institute for Life Sciences, Jl. Pulomas Barat Kav 88, Jakarta 13210, Indonesia;
| | - Jiann-Shing Shieh
- Department of Mechanical Engineering, Yuan Ze University, Taoyuan 32003, Taiwan;
- Correspondence:
| |
Collapse
|
7
|
Nasimi F, Khayyambashi MR, Movahhedinia N. Redundancy cancellation of compressed measurements by QRS complex alignment. PLoS One 2022; 17:e0262219. [PMID: 35134070 PMCID: PMC8824321 DOI: 10.1371/journal.pone.0262219] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2021] [Accepted: 12/20/2021] [Indexed: 11/18/2022] Open
Abstract
The demand for long-term continuous care has led healthcare experts to focus on development challenges. On-chip energy consumption as a key challenge can be addressed by data reduction techniques. In this paper, the pseudo periodic nature of ElectroCardioGram(ECG) signals has been used to completely remove redundancy from frames. Compressing aligned QRS complexes by Compressed Sensing (CS), result in highly redundant measurement vectors. By removing this redundancy, a high cluster of near zero samples is gained. The efficiency of the proposed algorithm is assessed using the standard MIT-BIH database. The results indicate that by aligning ECG frames, the proposed technique can achieve superior reconstruction quality compared to state-of-the-art techniques for all compression ratios. This study proves that by aligning ECG frames with a 0.05% unaligned frame rate(R-peak detection error), more compression could be gained for PRD > 5% when 5-bit non-uniform quantizer is used. Furthermore, analysis done on power consumption of the proposed technique, indicates that a very good recovery performance can be gained by only consuming 4.9μW more energy per frame compared to traditional CS.
Collapse
Affiliation(s)
- Fahimeh Nasimi
- Faculty of Computer Engineering, University of Isfahan, Isfahan, Iran
| | | | | |
Collapse
|
8
|
An Intelligent Heartbeat Classification System Based on Attributable Features with AdaBoost+Random Forest Algorithm. JOURNAL OF HEALTHCARE ENGINEERING 2021; 2021:9913127. [PMID: 34336169 PMCID: PMC8289583 DOI: 10.1155/2021/9913127] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/20/2021] [Revised: 05/20/2021] [Accepted: 05/27/2021] [Indexed: 12/02/2022]
Abstract
Arrhythmia is a common cardiovascular disease that can threaten human life. In order to assist doctors in accurately diagnosing arrhythmia, an intelligent heartbeat classification system based on the selected optimal feature sets and AdaBoost + Random Forest model is developed. This system can acquire ECG signals through the Holter and transmit them to the cloud platform for preprocessing and feature extraction, and the features are input into AdaBoost + Random Forest for heartbeat classification. The analysis results are output in the form of reports. In this system, by comparing and analyzing the classification accuracy of different feature sets and classifiers, the optimal classification algorithm is obtained and applied to the system. The algorithm accuracy of the system is tested based on the MIT-BIH data set. The result shows that AdaBoost + Random Forest achieved 99.11% accuracy with optimal feature sets. The intelligent heartbeat classification system based on this algorithm has also achieved good results on clinical data.
Collapse
|
9
|
Huang Y, Li H, Yu X. A multiview feature fusion model for heartbeat classification. Physiol Meas 2021; 42. [PMID: 33984841 DOI: 10.1088/1361-6579/ac010f] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2021] [Accepted: 05/13/2021] [Indexed: 11/11/2022]
Abstract
Objective.An electrocardiogram (ECG) is one of the most common means to diagnose arrhythmia according to different waveforms clinically. Although there are advanced classification methods such as deep learning, the single view feature cannot meet the demand of classification accuracy for new individuals. To this end, a classification model based on multiview fusion was proposed.Approach.First, handcrafted view features were extracted from heartbeats and then deep view features were obtained from the deep learning model. The features of two different perspectives were fused in the fully connected layer, and the random forest classifier was used instead of the Softmax classifier for classification. Notably, Bayesian optimization was utilized in the hyper-parameter tuning of the classifier. The proposed method employed the MIT-BIH database to classify five classes: normal heartbeat (N), left bundle branch block heartbeat (LB), right bundle branch block heartbeat (RB), atrial premature contraction (APC) and premature ventricular contraction (PVC).Main results.The experimental results achieved a higher average accuracy of 98.93%, average precision of 96.92%, average sensitivity of 96.46%, and average specificity of 99.33% in five types of heartbeat classification for inter-patient.Significance.The proposed framework improves the performance of ECG detection for new individuals. And it provides an feasible algorithmic model for single-lead wearable devices with multiview fusion.
Collapse
Affiliation(s)
- Youhe Huang
- College of Information Sciences and Engineering, Northeastern University, Shenyang, People's Republic of China
| | - Hongru Li
- College of Information Sciences and Engineering, Northeastern University, Shenyang, People's Republic of China
| | - Xia Yu
- College of Information Sciences and Engineering, Northeastern University, Shenyang, People's Republic of China
| |
Collapse
|
10
|
Hong S, Zhou Y, Shang J, Xiao C, Sun J. Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review. Comput Biol Med 2020; 122:103801. [PMID: 32658725 DOI: 10.1016/j.compbiomed.2020.103801] [Citation(s) in RCA: 108] [Impact Index Per Article: 27.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2019] [Revised: 04/30/2020] [Accepted: 04/30/2020] [Indexed: 12/15/2022]
Abstract
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.
Collapse
Affiliation(s)
- Shenda Hong
- Department of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, USA.
| | - Yuxi Zhou
- School of Electronics Engineering and Computer Science, Peking University, Beijing, China; Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China.
| | - Junyuan Shang
- School of Electronics Engineering and Computer Science, Peking University, Beijing, China; Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, China.
| | - Cao Xiao
- Analytics Center of Excellence, IQVIA, Cambridge, USA.
| | - Jimeng Sun
- Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, USA.
| |
Collapse
|