ECG-FM: An Open Electrocardiogram Foundation Model
This provides an open, label-efficient tool for ECG analysis, addressing adoption barriers in medical research, though it is incremental as it applies existing foundation model concepts to ECG data.
The authors tackled the problem of limited annotated ECG data by developing ECG-FM, an open foundation model that outperforms task-specific models in small-to-medium data regimes, achieving high AUROC scores such as 0.996 for atrial fibrillation and 0.929 for reduced left ventricular ejection fraction.
Conventional task-specific electrocardiogram (ECG) analysis models require large annotated datasets to train. Foundation models mitigate this burden by leveraging self-supervised pretraining; however, the scarcity of open-weight ECG foundation models hinders adoption and cross-study comparability. We present ECG-FM, an open foundation model for ECG analysis, and conduct a study using a dataset of 1.5 million ECGs. ECG-FM is a transformer-based model pretrained using a hybrid contrastive and generative self-supervised learning approach. Our downstream tasks include predicting reduced left ventricular ejection fraction (LVEF) and ECG interpretation labels, where we release a benchmark task on the MIMIC-IV-ECG dataset. We affirm that ECG-FM is robust, label-efficient, and functionally discriminative by showcasing data scaling experiments, performing a latent space analysis, and generating saliency maps. ECG-FM markedly outperforms task-specific models in the small-to-medium-scale data regime and demonstrates cross-dataset generalizability, achieving high AUROC on many clinically salient labels such as atrial fibrillation (0.996) and LVEF<=40% (0.929). We release our code, model weights, and benchmark task at https://github.com/bowang-lab/ECG-FM/.