OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records
This work addresses the need for scalable and clinically meaningful AI-driven ECG analysis by showing that public data can match proprietary datasets, though it is incremental as it benchmarks existing methods.
This study tackled the problem of evaluating ECG foundation models by introducing OpenECG, a benchmark with 1.2 million ECG recordings, and found that pre-training on diverse public datasets improves generalization, with BYOL and MAE outperforming SimCLR and performance saturating at 60-70% of total data for some methods.
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.