CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models

• URL: http://arxiv.org/abs/2512.02180v1
• Date: Mon, 01 Dec 2025 20:21:44 GMT
• Title: CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models
• Authors: Yuxuan Shu, Peter H. Charlton, Fahim Kawsar, Jussi Hernesniemi, Mohammad Malekzadeh,
• Abstract summary: Single-lead ECG recording is integrated into both clinical-grade and consumer wearables.<n>While self-supervised pretraining of foundation models on unlabeled ECGs improves diagnostic performance, existing approaches do not incorporate domain knowledge from clinical metadata.<n>We introduce a novel contrastive learning approach that utilizes an established clinical risk score to adaptively weight negative pairs.
• Score: 13.613519337591507
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The electrocardiogram (ECG) is a key diagnostic tool in cardiovascular health. Single-lead ECG recording is integrated into both clinical-grade and consumer wearables. While self-supervised pretraining of foundation models on unlabeled ECGs improves diagnostic performance, existing approaches do not incorporate domain knowledge from clinical metadata. We introduce a novel contrastive learning approach that utilizes an established clinical risk score to adaptively weight negative pairs: clinically-guided contrastive learning. It aligns the similarities of ECG embeddings with clinically meaningful differences between subjects, with an explicit mechanism to handle missing metadata. On 12-lead ECGs from 161K patients in the MIMIC-IV dataset, we pretrain single-lead ECG foundation models at three scales, collectively called CLEF, using only routinely collected metadata without requiring per-sample ECG annotations. We evaluate CLEF on 18 clinical classification and regression tasks across 7 held-out datasets, and benchmark against 5 foundation model baselines and 3 self-supervised algorithms. When pretrained on 12-lead ECG data and tested on lead-I data, CLEF outperforms self-supervised foundation model baselines: the medium-sized CLEF achieves average AUROC improvements of at least 2.6% in classification and average reductions in MAEs of at least 3.2% in regression. Comparing with existing self-supervised learning algorithms, CLEF improves the average AUROC by at least 1.8%. Moreover, when pretrained only on lead-I data for classification tasks, CLEF performs comparably to the state-of-the-art ECGFounder, which was trained in a supervised manner. Overall, CLEF enables more accurate and scalable single-lead ECG analysis, advancing remote health monitoring. Code and pretrained CLEF models are available at: github.com/Nokia-Bell-Labs/ecg-foundation-model.

Related papers

• Position: Evaluation of ECG Representations Must Be Fixed [1.567009619451362]
  This position paper argues that current benchmarking practice in 12-lead ECG representation learning must be fixed to ensure progress is reliable and aligned with clinically meaningful objectives.<n>We argue that downstream evaluation should expand to include an assessment of structural heart disease and patient-level forecasting, in addition to other evolving ECG-related endpoints, as relevant clinical targets.
  arXiv  Detail & Related papers  (2026-02-19T16:42:46Z)
• Sensing Cardiac Health Across Scenarios and Devices: A Multi-Modal Foundation Model Pretrained on Heterogeneous Data from 1.7 Million Individuals [36.08910150609342]
  We present a cardiac sensing foundation model (CSFM) that learns unified representations from vast, heterogeneous health records.<n>Our model is pretrained on an innovative multi-modal integration of data from multiple large-scale datasets.<n> CSFM consistently outperforms traditional one-modal-one-task approaches.
  arXiv  Detail & Related papers  (2025-06-23T20:58:12Z)
• Multimodal Latent Fusion of ECG Leads for Early Assessment of Pulmonary Hypertension [30.124231086488976]
  We propose a lead-specific electrocardiogram multimodal variational autoencoder (textscLS-EMVAE)<n>textscLS-EMVAE incorporates a hierarchical modality expert (HiME) fusion mechanism and a latent representation alignment loss.<n>We validate textscLS-EMVAE across two retrospective cohorts in a 6L-ECG setting.
  arXiv  Detail & Related papers  (2025-03-03T16:16:38Z)
• rECGnition_v2.0: Self-Attentive Canonical Fusion of ECG and Patient Data using deep learning for effective Cardiac Diagnostics [0.56337958460022]
  This study uses MIT-BIH Arrhythmia dataset to evaluate the efficiency of rECGnition_v2.0 for various classes of arrhythmias.<n>The compact architectural footprint of the rECGnition_v2.0, characterized by its lesser trainable parameters, unfurled several advantages including interpretability and scalability.
  arXiv  Detail & Related papers  (2025-02-22T15:16:46Z)
• ECG-FM: An Open Electrocardiogram Foundation Model [3.8270632390229777]
  We present ECG-FM, an open foundation model for ECG analysis, and conduct a study using a dataset of 1.5 million ECGs.<n>ECG-FM is a transformer-based model pretrained using a hybrid contrastive and generative self-supervised learning approach.<n>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.
  arXiv  Detail & Related papers  (2024-08-09T17:06:49Z)
• TACCO: Task-guided Co-clustering of Clinical Concepts and Patient Visits for Disease Subtyping based on EHR Data [42.96821770394798]
  TACCO is a novel framework that jointly discovers clusters of clinical concepts and patient visits based on a hypergraph modeling of EHR data. We conduct experiments on the public MIMIC-III dataset and Emory internal CRADLE dataset over the downstream clinical tasks of phenotype classification and cardiovascular risk prediction. In-depth model analysis, clustering results analysis, and clinical case studies further validate the improved utilities and insightful interpretations delivered by TACCO.
  arXiv  Detail & Related papers  (2024-06-14T14:18:38Z)
• Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement [10.611952462532908]
  Multimodal ECG Representation Learning (MERL) is capable of performing zero-shot ECG classification with text prompts. We propose the Clinical Knowledge Enhanced Prompt Engineering (CKEPE) approach to exploit external expert-verified clinical knowledge databases. MERL achieves an average AUC score of 75.2% in zero-shot classification (without training data), 3.2% higher than linear probed eSSL methods with 10% annotated training data, averaged across all six datasets.
  arXiv  Detail & Related papers  (2024-03-11T12:28:55Z)
• 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)
• Frozen Language Model Helps ECG Zero-Shot Learning [12.974685769614062]
  We propose Multimodal ECG-Text Self-supervised pre-training (METS) We use a trainable ECG encoder and a frozen language model to embed paired ECG and automatically machine-generated clinical reports separately. In downstream classification tasks, METS achieves around 10% improvement in performance without using any annotated data.
  arXiv  Detail & Related papers  (2023-03-22T05:01:14Z)
• Successive Subspace Learning for Cardiac Disease Classification with Two-phase Deformation Fields from Cine MRI [36.044984400761535]
  This work proposes a lightweight successive subspace learning framework for CVD classification. It is based on an interpretable feedforward design, in conjunction with a cardiac atlas. Compared with 3D CNN-based approaches, our framework achieves superior classification performance with 140$times$ fewer parameters.
  arXiv  Detail & Related papers  (2023-01-21T15:00:59Z)
• SEVGGNet-LSTM: a fused deep learning model for ECG classification [38.747030782394646]
  The input ECG signals are firstly segmented and normalized, and then fed into the combined VGG and LSTM network for feature extraction and classification. An attention mechanism (SE block) is embedded into the core network for increasing the weight of important features.
  arXiv  Detail & Related papers  (2022-10-31T07:36:48Z)
• Self-supervised contrastive learning of echocardiogram videos enables label-efficient cardiac disease diagnosis [48.64462717254158]
  We developed a self-supervised contrastive learning approach, EchoCLR, to catered to echocardiogram videos. When fine-tuned on small portions of labeled data, EchoCLR pretraining significantly improved classification performance for left ventricular hypertrophy (LVH) and aortic stenosis (AS) EchoCLR is unique in its ability to learn representations of medical videos and demonstrates that SSL can enable label-efficient disease classification from small, labeled datasets.
  arXiv  Detail & Related papers  (2022-07-23T19:17:26Z)
• ECG-DelNet: Delineation of Ambulatory Electrocardiograms with Mixed Quality Labeling Using Neural Networks [69.25956542388653]
  Deep learning (DL) algorithms are gaining weight in academic and industrial settings. We demonstrate DL can be successfully applied to low interpretative tasks by embedding ECG detection and delineation onto a segmentation framework. The model was trained using PhysioNet's QT database, comprised of 105 ambulatory ECG recordings.
  arXiv  Detail & Related papers  (2020-05-11T16:29:12Z)

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.