Pith. sign in

REVIEW 7 cited by

ECG-FM: An Open Electrocardiogram Foundation Model

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.05178 v2 pith:7Q3IGBH6 submitted 2024-08-09 cs.LG

classification cs.LG
keywords ecg-fmfoundationmodelmodelsanalysisbenchmarkdatadataset
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CADENCE: A Cardiac Atom Dictionary for Interpretable Neural Concept Extraction from ECG Foundation Models

    cs.AI 2026-07 conditional novelty 6.0 of 10

    A sparse dictionary learned from an ECG foundation model's embeddings recovers interpretable cardiac concepts—PVCs, atrial fibrillation, bundle branch blocks, ST/T-wave segments—and transfers to an external dataset wi...

  2. Modeling Day-Long ECG Signals to Predict Heart Failure Risk with Explainable AI

    eess.SP 2025-12 conditional novelty 6.0 of 10

    DeepHHF, trained on day-long single-lead Holter ECGs from 40,174 patients, predicted incident heart failure within five years with AUROC 0.80 and external AUROC 0.81.

  3. Data distribution impacts the performance and generalisability of contrastive learning-based foundation models of electrocardiograms

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Pretraining on mixed ECG cohorts improves in-distribution accuracy but hurts out-of-distribution transfer, and sampling single-cohort batches during pretraining mitigates this.

  4. Domain Knowledge is Power: Leveraging Physiological Priors for Self Supervised Representation Learning in Electrocardiography

    cs.LG 2025-09 conditional novelty 6.0 of 10

    PhysioCLR adds physiology-based positive/negative pair selection, heartbeat shuffling, and peak-aware reconstruction to ECG contrastive learning, improving downstream arrhythmia AUROC on Chapman, Georgia, and private ...

  5. Self-DANA: A Resource-Efficient Channel-Adaptive Self-Supervised Approach for ECG Foundation Models

    eess.SP 2025-07 conditional novelty 6.0 of 10

    Self-DANA combines dimension-adaptive pooling with random lead selection to fine-tune ECG foundation models on reduced-lead inputs, cutting memory and time while maintaining diagnostic accuracy.

  6. From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining

    eess.SP 2025-06 conditional novelty 6.0 of 10

    MELP pretrains ECG and text encoders with token-, beat-, and rhythm-level cross-modal supervision and beats prior baselines on several ECG classification benchmarks.

  7. QualityFM: a Multimodal Physiological Signal Foundation Model with Self-Distillation for Signal Quality Challenges in Critically Ill Patients

    cs.LG 2025-09 conditional novelty 5.0 of 10

    QualityFM, a multimodal ECG/PPG foundation model using self-distillation from clean to noisy signals, outperforms task-specific baselines on three ICU monitoring tasks.

Pith tools