Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.00711 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912255372689408 |
|---|---|
| author | Wan, Zhijiang Yu, Qianhao Mao, Jia Duan, Wenfeng Ding, Cheng |
| author_facet | Wan, Zhijiang Yu, Qianhao Mao, Jia Duan, Wenfeng Ding, Cheng |
| contents | This study introduces OpenECG, a large-scale benchmark of 1.2 million 12-lead ECG recordings from nine centers, to evaluate ECG foundation models (ECG-FMs) trained on public datasets. We investigate three self-supervised learning methods (SimCLR, BYOL, MAE) with ResNet-50 and Vision Transformer architectures, assessing model generalization through leave-one-dataset-out experiments and data scaling analysis. Results show that pre-training on diverse datasets significantly improves generalization, with BYOL and MAE outperforming SimCLR, highlighting the efficacy of feature-consistency and generative learning over contrastive approaches. Data scaling experiments reveal that performance saturates at 60-70% of total data for BYOL and MAE, while SimCLR requires more data. These findings demonstrate that publicly available ECG data can match or surpass proprietary datasets in training robust ECG-FMs, paving the way for scalable, clinically meaningful AI-driven ECG analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_00711 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records Wan, Zhijiang Yu, Qianhao Mao, Jia Duan, Wenfeng Ding, Cheng Machine Learning Artificial Intelligence This study introduces OpenECG, a large-scale benchmark of 1.2 million 12-lead ECG recordings from nine centers, to evaluate ECG foundation models (ECG-FMs) trained on public datasets. We investigate three self-supervised learning methods (SimCLR, BYOL, MAE) with ResNet-50 and Vision Transformer architectures, assessing model generalization through leave-one-dataset-out experiments and data scaling analysis. Results show that pre-training on diverse datasets significantly improves generalization, with BYOL and MAE outperforming SimCLR, highlighting the efficacy of feature-consistency and generative learning over contrastive approaches. Data scaling experiments reveal that performance saturates at 60-70% of total data for BYOL and MAE, while SimCLR requires more data. These findings demonstrate that publicly available ECG data can match or surpass proprietary datasets in training robust ECG-FMs, paving the way for scalable, clinically meaningful AI-driven ECG analysis. |
| title | OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.00711 |