ECG-FM: An Open Electrocardiogram Foundation Model

TL;DR

ECG-FM is an open, transformer-based ECG foundation model trained on 1.5 million ECGs, demonstrating robustness, label efficiency, and superior performance over task-specific models in various clinical tasks.

Contribution

This work introduces ECG-FM, the first open ECG foundation model using hybrid self-supervised learning, enabling improved ECG analysis and cross-dataset generalization.

Findings

ECG-FM outperforms task-specific models in small-to-medium data regimes.

Achieves high AUROC scores on key clinical labels like atrial fibrillation and LVEF<=40%.

Demonstrates robustness, label efficiency, and cross-dataset generalizability.

Abstract

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/.