A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography

• URL: http://arxiv.org/abs/2605.25446v1
• Date: Mon, 25 May 2026 05:51:44 GMT
• Title: A Signal-Language Foundation Model for Broad-Spectrum Cardiovascular Assessment from Routine Electrocardiography
• Abstract summary: We developed ECG Contrastive Language-Image Pre-training (ECGCLIP)<n>ECGCLIP is a signal-language contrastive learning framework that aligns ECG waveforms with expert diagnostic reports.<n>We evaluated ECGCLIP on 2,837,962 ECG studies from 1,324,856 patients.
• Score: 11.95199497112656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Electrocardiography (ECG) is central to cardiovascular care, but conventional AI models are often restricted to common arrhythmias and may generalize poorly across populations or clinically subtle diseases. We developed ECG Contrastive Language-Image Pre-training (ECGCLIP), a signal-language contrastive learning framework that aligns ECG waveforms with expert diagnostic reports. ECGCLIP was pre-trained on 2,837,962 ECG studies from 1,324,856 patients and evaluated on a held-out internal test set plus nine independent external cohorts comprising about 1.5 million ECGs. Evaluation covered 89 downstream tasks, including 45 ECG diagnoses, 39 echocardiographic targets, and 5 rare cardiac diseases, using PRAUC as the primary metric. ECGCLIP consistently improved performance over random initialization and Merl-R18 baselines. On the internal test set, ECGCLIP-R34 achieved strong performance for atrial fibrillation (PRAUC 0.900) and ST-segment elevation myocardial infarction (PRAUC 0.383), with robust generalization across all external cohorts. It also improved low-prevalence and diagnostically elusive diseases, including Ebstein anomaly, constrictive pericarditis, dextrocardia, and cardiac amyloidosis, with internal PRAUC values of 0.253, 0.175, 0.121, and 0.201, respectively. ECGCLIP was data efficient, matching or exceeding full-dataset baseline performance with only 10% of training data. Feature visualization and saliency analysis suggested clinically meaningful representations aligned with established electrocardiographic criteria. These findings indicate that large-scale ECG-report contrastive pre-training can expand routine ECG interpretation beyond common arrhythmias toward broad cardiovascular assessment and opportunistic screening of echocardiographic and rare conditions.

Related papers

• ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning [50.82313761980655]
  ECG-LLM is an ECG-conditioned large language model trained across four cohorts 679,112 ECG studies from 186,409 patients.<n>It is trained on clinically structured question-answer pairs derived from ECG signals, clinical context, CMR, and ECHO.<n>It successfully recovers conventional ECG measurements, such as heart rate, and strongly predicts complex CMR-derived phenotypes.
  arXiv  Detail & Related papers  (2026-07-15T11:06:35Z)
• Learning Cardiac Latent Representations in Vectorcardiogram Space [54.12639543496968]
  Existing methods operate almost exclusively in the observable ECG signal space.<n>We propose learning a unified latent representation of cardiac electrical activity directly in the VCG space.<n>We introduce LVCG, the first general self-supervised representation learning framework designed to operate in this physically grounded latent space.
  arXiv  Detail & Related papers  (2026-05-29T12:48:12Z)
• Cross-Modal Contrastive Learning of ECG and Angiography Representations for Severe Stenosis Classification [79.18126160626093]
  Coronary artery stenosis is a common cardiovascular disease, with severe, untreated cases posing significant risks of heart attack.<n>We introduce StenCE, a pretraining framework, allowing stratification of patients based on features derived directly from ECGs.<n>The obtained models successfully detect signals for stenosis diagnosis in ECGs and are the first to achieve high performance in severe stenosis classification.
  arXiv  Detail & Related papers  (2026-05-23T14:50:22Z)
• Associations between echocardiographic traits and AI-ECG predictions of heart failure [0.0]
  Artificial intelligence-enabled electrocardiography (AI-ECG) can detect heart failure (HF), including disease not captured by left ventricular ejection fraction (LVEF)<n>We investigated whether AI-ECG-predicted HF risk aligns with established echocardiographic measures of myocardial dysfunction, remodelling, and filling pressures.
  arXiv  Detail & Related papers  (2026-05-23T13:37:36Z)
• Demographic-Aware Self-Supervised Anomaly Detection Pretraining for Equitable Rare Cardiac Diagnosis [45.00216485193071]
  Rare cardiac anomalies are difficult to detect from electrocardiograms due to their long-tailed distribution.<n>We developed an AI-assisted two-stage ECG framework integrating self-supervised anomaly detection and demographic-aware representation learning.<n>Our method achieves an AUROC of 94.7% for rare anomalies and reduces the common-rare performance gap by 73%.
  arXiv  Detail & Related papers  (2026-03-20T07:04:00Z)
• Echo2ECG: Enhancing ECG Representations with Cardiac Morphology from Multi-View Echos [53.368813255127115]
  Existing self-supervised methods suffer from a representational mismatch by aligning ECGs to single-view Echos.<n>We propose Echo2ECG, a multimodal self-supervised learning framework that enriches ECG representations with the heart's morphological structure captured in multi-view Echos.<n>We evaluate Echo2ECG as an ECG feature extractor on two clinically relevant tasks.
  arXiv  Detail & Related papers  (2026-03-09T15:39:57Z)
• Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generation [52.19347532840774]
  We propose SE-Diff, a novel physiological simulator and experience enhanced diffusion model for ECG generation.<n> SE-Diff integrates a lightweight ordinary differential equation (ODE)-based ECG simulator into the diffusion process via a beat decoder.<n>Extensive experiments on real-world ECG datasets demonstrate that SE-Diff improves both signal fidelity and text-ECG semantic alignment.
  arXiv  Detail & Related papers  (2025-11-13T02:57:10Z)
• LGE-Guided Cross-Modality Contrastive Learning for Gadolinium-Free Cardiomyopathy Screening in Cine CMR [51.11296719862485]
  We propose a Contrastive Learning and Cross-Modal alignment framework for gadolinium-free cardiomyopathy screening using cine CMR sequences.<n>By aligning the latent spaces of cine CMR and Late Gadolinium Enhancement (LGE) sequences, our model encodes fibrosis-specific pathology into cine CMR embeddings.
  arXiv  Detail & Related papers  (2025-08-23T07:21:23Z)
• Translating Electrocardiograms to Cardiac Magnetic Resonance Imaging Useful for Cardiac Assessment and Disease Screening: A Multi-Center Study AI for ECG to CMR Translation Study [30.84196213860778]
  Cardiovascular diseases (CVDs) are the leading cause of global mortality, necessitating accessible and accurate diagnostic tools.<n>We propose CardioNets, a deep learning framework that translates 12-lead ECG signals into CMR-level functional parameters and synthetic images.<n>In a reader study, ECG-only CardioNets achieved 13.9% higher accuracy than human physicians using both ECG and real CMR.
  arXiv  Detail & Related papers  (2024-11-19T09:09:14Z)
• Self-supervised inter-intra period-aware ECG representation learning for detecting atrial fibrillation [41.82319894067087]
  We propose an inter-intra period-aware ECG representation learning approach. Considering ECGs of atrial fibrillation patients exhibit the irregularity in RR intervals and the absence of P-waves, we develop specific pre-training tasks for interperiod and intraperiod representations. Our approach demonstrates remarkable AUC performances on the BTCH dataset, textiti.e., 0.953/0.996 for paroxysmal/persistent atrial fibrillation detection.
  arXiv  Detail & Related papers  (2024-10-08T10:03:52Z)
• Estimation of Cardiac and Non-cardiac Diagnosis from Electrocardiogram Features [1.068128849363198]
  We use publicly available datasets to investigate the feasibility of inferring general diagnostic conditions from ECG features. We train a tree-based model (XGBoost) based on ECG features and basic demographic features to estimate a wide range of diagnoses.
  arXiv  Detail & Related papers  (2024-08-30T14:42:03Z)
• MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation [28.35107188450758]
  Electrocardiogram (ECG) is the primary non-invasive diagnostic tool for monitoring cardiac conditions.<n>Recent studies have concentrated on classifying cardiac conditions using ECG data but have overlooked ECG report generation.<n>We propose the Multimodal ECG Instruction Tuning (MEIT) framework, the first attempt to tackle ECG report generation with LLMs and multimodal instructions.
  arXiv  Detail & Related papers  (2024-03-07T23:20:56Z)
• PPG-to-ECG Signal Translation for Continuous Atrial Fibrillation Detection via Attention-based Deep State-Space Modeling [11.617950008187366]
  Photoplethysmography ( PPG) is a cost-effective and non-invasive technique that utilizes optical methods to measure cardiac physiology. Here, we propose a subject-independent attention-based deep state-space model (ADSSM) to translate PPG signals to corresponding ECG waveforms.
  arXiv  Detail & Related papers  (2023-09-27T03:07:46Z)
• IMLE-Net: An Interpretable Multi-level Multi-channel Model for ECG Classification [0.9449650062296824]
  In clinical settings, a cardiologist makes a diagnosis based on the standard 12-channel ECG recording. We propose a model that leverages the multiple-channel information available in the standard ECG recordings and learns patterns at the beat, rhythm, and channel level. The experimental results show that our model achieved a macro-averaged ROC-AUC score of 0.9216, mean accuracy of 88.85%, and a maximum F1 score of 0.8057 on the PTB-XL dataset.
  arXiv  Detail & Related papers  (2022-04-06T16:29:10Z)
• Estimation of atrial fibrillation from lead-I ECGs: Comparison with cardiologists and machine learning model (CurAlive), a clinical validation study [0.0]
  This study presents a method to detect atrial fibrillation with lead-I ECGs using artificial intelligence. The aim of the study is to compare the accuracy of the diagnoses estimated by cardiologists and artificial intelligence over lead-I ECGs.
  arXiv  Detail & Related papers  (2021-04-15T12:50:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.