arXiv:2607. 27404v1 Announce Type: new Abstract: Existing benchmarks for electrocardiogram foundation models primarily evaluate downstream predictive performance, providing limited insight into whether their internal representations can be faithfully decomposed, clinically interpreted, or reproduced across independent analyses.
arXiv:2608. 03597v1 Announce Type: new Abstract: Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and is associated with increased risks of stroke, heart failure, and mortality.
arXiv:2607. 23412v1 Announce Type: new Abstract: Electrocardiograms (ECGs) are widely used for cardiovascular risk prediction, yet models often fail to transfer across hospitals because of protocol, population, and measurement differences.
arXiv:2608. 05893v1 Announce Type: new Abstract: Electrocardiography (ECG) is one of the most widely used non-invasive tools for diagnosing cardiovascular disease, but transforming multi-lead ECG recordings into reliable clinical reports remains challenging.
arXiv:2607. 25244v1 Announce Type: new Abstract: Foundation models for 12-lead electrocardiograms (ECGs) transfer well across clinical tasks, but the physiological knowledge encoded in their representations remains opaque.
ECGQuest is a new benchmark that evaluates language models on the contextual knowledge required for electrocardiogram interpretation, featuring 10,904 True/False questions derived from 23 ECG references and 2003‑2025 Computing in Cardiology proceedings. The study tested 23 commercial and open‑source models, finding that zero‑shot accuracy ranged from 49.5% to 74.4% and that fine‑tuning with Low‑Rank Adaptation improved all open‑source models by 6.5–14.1%, with the best fine‑tuned model achieving 76.3% accuracy and a five‑model ensemble reaching 78.5%. ECGQuest demonstrates that parameter‑efficient fine‑tuning can enable smaller models to compete with larger commercial ones on ECG‑specific tasks.
arXiv:2607. 16323v1 Announce Type: cross Abstract: Electrocardiography (ECG) is an inexpensive, standard-of-care test for cardiac symptoms, but front-line triage often lacks immediate access to definitive imaging such as echocardiography (ECHO) or cardiac magnetic resonance (CMR).
arXiv:2608. 12695v1 Announce Type: new Abstract: Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences.
NeuroECG is a deep learning framework that repurposes a pretrained ECG foundation model to predict neurological outcomes after cardiac arrest without using electroencephalography (EEG). The model fine‑tunes the backbone with a gradual unfreezing strategy on single‑channel bedside ECG, aggregates multiple ECG segments via quantile pooling and PCA, and achieves an AUROC of 0.7333 using ECG alone. When combined with static clinical covariates, NeuroECG improves performance to an AUROC of 0.8077 and an AUPRC of 0.8970, demonstrating that bedside ECG can serve as a low‑cost, auxiliary prognostic tool in an EEG‑free setting.
The paper introduces representative‑morphology heatmaps, a deterministic ECG‑to‑image representation that averages the five beats closest to the block mean within each ten‑beat block, producing either a conventional trace or a dense cardiac‑time‑by‑lead heatmap. Experiments on PTB, ECG‑ID, and MIMIC‑IV‑ECG‑DEMO show that heatmaps consistently improve verification and identification performance across 15 compact models, reducing EER by an average of 9.59 percentage points and increasing Rank‑1 by 24.69 points. The study also demonstrates that ImageNet initialization benefits multilead datasets, that performance does not scale monotonically with model size, and that useful channel combinations vary by cohort and biometric task.
Electrocardiography (ECG) contains subject-specific morphology that supports biometric recognition, yet image-based performance depends on how the waveform is rendered. We introduce representative-mor...
The study investigates whether ECG representations derived from a β-variational autoencoder (VAE) can distinguish patients with myocardial scar (LGE+) from those without (LGE-) using routine ECG data. In a cohort of 300 cardiomyopathic patients, the β-VAE achieved an AUC of 0.577 (sensitivity 0.775) with Gradient Boosting, while the foundation ECGx.AI model reached an AUC of 0.686 with Random Forest. Dynamic Time Warping reconstruction errors differed significantly between classes in most leads and improved classification to an AUC of 0.643 with Logistic Regression, suggesting these errors could serve as markers of scar-related ECG changes.
arXiv:2609.23460v1 Announce Type: new Abstract: Deep learning has advanced automated electrocardiogram (ECG) diagnosis, but the field's most accurate models, foundation models pretrained on millions...