Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020
Cardiovascular diseases (CVDs) are one of the most fatal disease groups worldwide. Electrocardiogram (ECG) is a widely used tool for automatically detecting cardiac abnormalities, thereby helping to control and manage CVDs. To encourage more multidisciplinary researches, PhysioNet/Computing in Cardi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-01-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2021.811661/full |
| _version_ | 1798013882454769664 |
|---|---|
| author | Shenda Hong Shenda Hong Wenrui Zhang Chenxi Sun Chenxi Sun Yuxi Zhou Yuxi Zhou Hongyan Li Hongyan Li |
| author_facet | Shenda Hong Shenda Hong Wenrui Zhang Chenxi Sun Chenxi Sun Yuxi Zhou Yuxi Zhou Hongyan Li Hongyan Li |
| author_sort | Shenda Hong |
| collection | DOAJ |
| description | Cardiovascular diseases (CVDs) are one of the most fatal disease groups worldwide. Electrocardiogram (ECG) is a widely used tool for automatically detecting cardiac abnormalities, thereby helping to control and manage CVDs. To encourage more multidisciplinary researches, PhysioNet/Computing in Cardiology Challenge 2020 (Challenge 2020) provided a public platform involving multi-center databases and automatic evaluations for ECG classification tasks. As a result, 41 teams successfully submitted their solutions and were qualified for rankings. Although Challenge 2020 was a success, there has been no in-depth methodological meta-analysis of these solutions, making it difficult for researchers to benefit from the solutions and results. In this study, we aim to systematically review the 41 solutions in terms of data processing, feature engineering, model architecture, and training strategy. For each perspective, we visualize and statistically analyze the effectiveness of the common techniques, and discuss the methodological advantages and disadvantages. Finally, we summarize five practical lessons based on the aforementioned analysis: (1) Data augmentation should be employed and adapted to specific scenarios; (2) Combining different features can improve performance; (3) A hybrid design of different types of deep neural networks (DNNs) is better than using a single type; (4) The use of end-to-end architectures should depend on the task being solved; (5) Multiple models are better than one. We expect that our meta-analysis will help accelerate the research related to ECG classification based on machine-learning models. |
| first_indexed | 2024-04-11T15:09:35Z |
| format | Article |
| id | doaj.art-9ae0b5c211244e718a11e705006f1736 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-04-11T15:09:35Z |
| publishDate | 2022-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-9ae0b5c211244e718a11e705006f17362022-12-22T04:16:42ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2022-01-011210.3389/fphys.2021.811661811661Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020Shenda Hong0Shenda Hong1Wenrui Zhang2Chenxi Sun3Chenxi Sun4Yuxi Zhou5Yuxi Zhou6Hongyan Li7Hongyan Li8National Institute of Health Data Science, Peking University, Beijing, ChinaInstitute of Medical Technology, Peking University Health Science Center, Beijing, ChinaDepartment of Mathematics, National University of Singapore, Singapore, SingaporeKey Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, ChinaSchool of Electronics Engineering and Computer Science, Peking University, Beijing, ChinaSchool of Computer Science and Engineering, Tianjin University of Technology, Tianjin, ChinaRIIT, TNList, Department of Computer Science and Technology, Tsinghua University, Beijing, ChinaKey Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, ChinaSchool of Electronics Engineering and Computer Science, Peking University, Beijing, ChinaCardiovascular diseases (CVDs) are one of the most fatal disease groups worldwide. Electrocardiogram (ECG) is a widely used tool for automatically detecting cardiac abnormalities, thereby helping to control and manage CVDs. To encourage more multidisciplinary researches, PhysioNet/Computing in Cardiology Challenge 2020 (Challenge 2020) provided a public platform involving multi-center databases and automatic evaluations for ECG classification tasks. As a result, 41 teams successfully submitted their solutions and were qualified for rankings. Although Challenge 2020 was a success, there has been no in-depth methodological meta-analysis of these solutions, making it difficult for researchers to benefit from the solutions and results. In this study, we aim to systematically review the 41 solutions in terms of data processing, feature engineering, model architecture, and training strategy. For each perspective, we visualize and statistically analyze the effectiveness of the common techniques, and discuss the methodological advantages and disadvantages. Finally, we summarize five practical lessons based on the aforementioned analysis: (1) Data augmentation should be employed and adapted to specific scenarios; (2) Combining different features can improve performance; (3) A hybrid design of different types of deep neural networks (DNNs) is better than using a single type; (4) The use of end-to-end architectures should depend on the task being solved; (5) Multiple models are better than one. We expect that our meta-analysis will help accelerate the research related to ECG classification based on machine-learning models.https://www.frontiersin.org/articles/10.3389/fphys.2021.811661/fullelectrocardiogrammachine learningdeep learningclassificationpractical lessonsphysionet challenge |
| spellingShingle | Shenda Hong Shenda Hong Wenrui Zhang Chenxi Sun Chenxi Sun Yuxi Zhou Yuxi Zhou Hongyan Li Hongyan Li Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020 Frontiers in Physiology electrocardiogram machine learning deep learning classification practical lessons physionet challenge |
| title | Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020 |
| title_full | Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020 |
| title_fullStr | Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020 |
| title_full_unstemmed | Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020 |
| title_short | Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020 |
| title_sort | practical lessons on 12 lead ecg classification meta analysis of methods from physionet computing in cardiology challenge 2020 |
| topic | electrocardiogram machine learning deep learning classification practical lessons physionet challenge |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2021.811661/full |
| work_keys_str_mv | AT shendahong practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 AT shendahong practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 AT wenruizhang practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 AT chenxisun practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 AT chenxisun practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 AT yuxizhou practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 AT yuxizhou practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 AT hongyanli practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 AT hongyanli practicallessonson12leadecgclassificationmetaanalysisofmethodsfromphysionetcomputingincardiologychallenge2020 |