Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From Holter
Artificial intelligence is increasingly being used on the clinical electrocardiogram workflows. Few electrocardiograms based on artificial intelligence algorithms have focused on detecting myocardial ischemia using long-term electrocardiogram data. A main reason for this is that interference signals...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-06-01
|
| Series: | Frontiers in Physiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2022.912739/full |
| _version_ | 1811332896183549952 |
|---|---|
| author | Shuang Wu Qing Cao Qiaoran Chen Qi Jin Zizhu Liu Lingfang Zhuang Jingsheng Lin Gang Lv Ruiyan Zhang Kang Chen |
| author_facet | Shuang Wu Qing Cao Qiaoran Chen Qi Jin Zizhu Liu Lingfang Zhuang Jingsheng Lin Gang Lv Ruiyan Zhang Kang Chen |
| author_sort | Shuang Wu |
| collection | DOAJ |
| description | Artificial intelligence is increasingly being used on the clinical electrocardiogram workflows. Few electrocardiograms based on artificial intelligence algorithms have focused on detecting myocardial ischemia using long-term electrocardiogram data. A main reason for this is that interference signals generated from daily activities while wearing the Holter monitor lowered the ability of artificial intelligence to detect myocardial ischemia. In this study, an automatic system combining denoising and segmentation modules was developed to detect the deviation of the ST-segment and J point. We proposed a ECG Bidirectional Transformer network that applied in both denoising and segmentation tasks. The denoising model achieved RMSEde, SNRimp, and PRD values of 0.074, 10.006, and 16.327, respectively. The segmentation model achieved precision, sensitivity (recall), and F1-score of 96.00, 93.06, and 94.51%, respectively. The system’s ability to distinguish the depression and elevation of the ST-segment and J point was also verified by cardiologists as well. From our ECG dataset, 103 patients with ST-segment depression and 10 patients with ST-segment elevation were detected with positive predictive values of 80.6 and 60% respectively. Using Holter ECG and transformer-based deep neural networks, we can detect subtle ST-segment changes in noisy ECG signals. This system has the potential to improve the efficacy of daily medicine and to provide a broader population-level screening for asymptomatic myocardial ischemia. |
| first_indexed | 2024-04-13T16:43:55Z |
| format | Article |
| id | doaj.art-9ef9f03d47aa4e8db8ad4ab138fc0fb2 |
| institution | Directory Open Access Journal |
| issn | 1664-042X |
| language | English |
| last_indexed | 2024-04-13T16:43:55Z |
| publishDate | 2022-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Physiology |
| spelling | doaj.art-9ef9f03d47aa4e8db8ad4ab138fc0fb22022-12-22T02:39:08ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2022-06-011310.3389/fphys.2022.912739912739Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From HolterShuang Wu0Qing Cao1Qiaoran Chen2Qi Jin3Zizhu Liu4Lingfang Zhuang5Jingsheng Lin6Gang Lv7Ruiyan Zhang8Kang Chen9Department of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaShanghai Digital Medicine Innovation Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaCenter for Translational Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaCenter for Translational Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaDepartment of Cardiovascular Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, ChinaArtificial intelligence is increasingly being used on the clinical electrocardiogram workflows. Few electrocardiograms based on artificial intelligence algorithms have focused on detecting myocardial ischemia using long-term electrocardiogram data. A main reason for this is that interference signals generated from daily activities while wearing the Holter monitor lowered the ability of artificial intelligence to detect myocardial ischemia. In this study, an automatic system combining denoising and segmentation modules was developed to detect the deviation of the ST-segment and J point. We proposed a ECG Bidirectional Transformer network that applied in both denoising and segmentation tasks. The denoising model achieved RMSEde, SNRimp, and PRD values of 0.074, 10.006, and 16.327, respectively. The segmentation model achieved precision, sensitivity (recall), and F1-score of 96.00, 93.06, and 94.51%, respectively. The system’s ability to distinguish the depression and elevation of the ST-segment and J point was also verified by cardiologists as well. From our ECG dataset, 103 patients with ST-segment depression and 10 patients with ST-segment elevation were detected with positive predictive values of 80.6 and 60% respectively. Using Holter ECG and transformer-based deep neural networks, we can detect subtle ST-segment changes in noisy ECG signals. This system has the potential to improve the efficacy of daily medicine and to provide a broader population-level screening for asymptomatic myocardial ischemia.https://www.frontiersin.org/articles/10.3389/fphys.2022.912739/fullholterelectrocardiogramST-Segmentdeep learningmulti-task learning |
| spellingShingle | Shuang Wu Qing Cao Qiaoran Chen Qi Jin Zizhu Liu Lingfang Zhuang Jingsheng Lin Gang Lv Ruiyan Zhang Kang Chen Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From Holter Frontiers in Physiology holter electrocardiogram ST-Segment deep learning multi-task learning |
| title | Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From Holter |
| title_full | Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From Holter |
| title_fullStr | Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From Holter |
| title_full_unstemmed | Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From Holter |
| title_short | Using Multi-Task Learning-Based Framework to Detect ST-Segment and J-Point Deviation From Holter |
| title_sort | using multi task learning based framework to detect st segment and j point deviation from holter |
| topic | holter electrocardiogram ST-Segment deep learning multi-task learning |
| url | https://www.frontiersin.org/articles/10.3389/fphys.2022.912739/full |
| work_keys_str_mv | AT shuangwu usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT qingcao usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT qiaoranchen usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT qijin usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT zizhuliu usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT lingfangzhuang usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT jingshenglin usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT ganglv usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT ruiyanzhang usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter AT kangchen usingmultitasklearningbasedframeworktodetectstsegmentandjpointdeviationfromholter |