A Multi-Level Multiple Contrastive Learning Method for Single-Lead Electrocardiogram Atrial Fibrillation Detection
Atrial fibrillation (AF) is the most common persistent arrhythmia, and it is crucial to develop generalizable automatic AF detection methods. However, supervised AF detection is often limited in performance due to the difficulty in obtaining labeled data. To address the gap between limited labeled d...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/12/1/44 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589087402360832 |
|---|---|
| author | Yonggang Zou Peng Wang Lidong Du Xianxiang Chen Zhenfeng Li Junxian Song Zhen Fang |
| author_facet | Yonggang Zou Peng Wang Lidong Du Xianxiang Chen Zhenfeng Li Junxian Song Zhen Fang |
| author_sort | Yonggang Zou |
| collection | DOAJ |
| description | Atrial fibrillation (AF) is the most common persistent arrhythmia, and it is crucial to develop generalizable automatic AF detection methods. However, supervised AF detection is often limited in performance due to the difficulty in obtaining labeled data. To address the gap between limited labeled data and the requirements for model robustness and generalization in single-lead ECG AF detection, we proposed a semi-supervised contrastive learning method named MLMCL for AF detection. The MLMCL method utilizes the multi-level feature representations of the encoder to perform multiple contrastive learning to fully exploit temporal consistency, channel consistency, and label consistency. Meanwhile, it combines labeled and unlabeled data for pre-training to obtain robust features for downstream tasks. In addition, it uses the domain knowledge in the field of AF diagnosis for domain knowledge augmentation to generate hard samples and improve the distinguishability of ECG representations. In the cross-dataset testing mode, MLMCL had better performance and good stability on different test sets, demonstrating its effectiveness and robustness in the AF detection task. The comparison results with existing studies show that MLMCL outperformed existing methods in external tests. The MLMCL method can be extended and applied to multi-lead scenarios and has reference significance for the development of contrastive learning methods for other arrhythmia. |
| format | Article |
| id | doaj-art-f5d9eaec63794b58b9ed7ed84ffd05d4 |
| institution | Kabale University |
| issn | 2306-5354 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj-art-f5d9eaec63794b58b9ed7ed84ffd05d42025-01-24T13:23:04ZengMDPI AGBioengineering2306-53542025-01-011214410.3390/bioengineering12010044A Multi-Level Multiple Contrastive Learning Method for Single-Lead Electrocardiogram Atrial Fibrillation DetectionYonggang Zou0Peng Wang1Lidong Du2Xianxiang Chen3Zhenfeng Li4Junxian Song5Zhen Fang6Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaDepartment of Cardiology, Peking University People’s Hospital, Beijing 100044, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaAtrial fibrillation (AF) is the most common persistent arrhythmia, and it is crucial to develop generalizable automatic AF detection methods. However, supervised AF detection is often limited in performance due to the difficulty in obtaining labeled data. To address the gap between limited labeled data and the requirements for model robustness and generalization in single-lead ECG AF detection, we proposed a semi-supervised contrastive learning method named MLMCL for AF detection. The MLMCL method utilizes the multi-level feature representations of the encoder to perform multiple contrastive learning to fully exploit temporal consistency, channel consistency, and label consistency. Meanwhile, it combines labeled and unlabeled data for pre-training to obtain robust features for downstream tasks. In addition, it uses the domain knowledge in the field of AF diagnosis for domain knowledge augmentation to generate hard samples and improve the distinguishability of ECG representations. In the cross-dataset testing mode, MLMCL had better performance and good stability on different test sets, demonstrating its effectiveness and robustness in the AF detection task. The comparison results with existing studies show that MLMCL outperformed existing methods in external tests. The MLMCL method can be extended and applied to multi-lead scenarios and has reference significance for the development of contrastive learning methods for other arrhythmia.https://www.mdpi.com/2306-5354/12/1/44atrial fibrillationdeep learningelectrocardiogram (ECG)contrastive learning (CL) |
| spellingShingle | Yonggang Zou Peng Wang Lidong Du Xianxiang Chen Zhenfeng Li Junxian Song Zhen Fang A Multi-Level Multiple Contrastive Learning Method for Single-Lead Electrocardiogram Atrial Fibrillation Detection Bioengineering atrial fibrillation deep learning electrocardiogram (ECG) contrastive learning (CL) |
| title | A Multi-Level Multiple Contrastive Learning Method for Single-Lead Electrocardiogram Atrial Fibrillation Detection |
| title_full | A Multi-Level Multiple Contrastive Learning Method for Single-Lead Electrocardiogram Atrial Fibrillation Detection |
| title_fullStr | A Multi-Level Multiple Contrastive Learning Method for Single-Lead Electrocardiogram Atrial Fibrillation Detection |
| title_full_unstemmed | A Multi-Level Multiple Contrastive Learning Method for Single-Lead Electrocardiogram Atrial Fibrillation Detection |
| title_short | A Multi-Level Multiple Contrastive Learning Method for Single-Lead Electrocardiogram Atrial Fibrillation Detection |
| title_sort | multi level multiple contrastive learning method for single lead electrocardiogram atrial fibrillation detection |
| topic | atrial fibrillation deep learning electrocardiogram (ECG) contrastive learning (CL) |
| url | https://www.mdpi.com/2306-5354/12/1/44 |
| work_keys_str_mv | AT yonggangzou amultilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT pengwang amultilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT lidongdu amultilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT xianxiangchen amultilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT zhenfengli amultilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT junxiansong amultilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT zhenfang amultilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT yonggangzou multilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT pengwang multilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT lidongdu multilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT xianxiangchen multilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT zhenfengli multilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT junxiansong multilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection AT zhenfang multilevelmultiplecontrastivelearningmethodforsingleleadelectrocardiogramatrialfibrillationdetection |