RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detection

• URL: http://arxiv.org/abs/2602.23060v1
• Date: Thu, 26 Feb 2026 14:45:29 GMT
• Title: RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detection
• Abstract summary: Electrocardiogram (ECG) analysis is crucial for diagnosing heart disease.<n>Most self-supervised learning methods treat ECG as a generic time series.<n>We propose RhythmBERT, a generative ECG language model that considers ECG as a language paradigm.
• Score: 8.583942286312135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Electrocardiogram (ECG) analysis is crucial for diagnosing heart disease, but most self-supervised learning methods treat ECG as a generic time series, overlooking physiologic semantics and rhythm-level structure. Existing contrastive methods utilize augmentations that distort morphology, whereas generative approaches employ fixed-window segmentation, which misaligns cardiac cycles. To address these limitations, we propose RhythmBERT, a generative ECG language model that considers ECG as a language paradigm by encoding P, QRS, and T segments into symbolic tokens via autoencoder-based latent representations. These discrete tokens capture rhythm semantics, while complementary continuous embeddings retain fine-grained morphology, enabling a unified view of waveform structure and rhythm. RhythmBERT is pretrained on approximately 800,000 unlabeled ECG recordings with a masked prediction objective, allowing it to learn contextual representations in a label-efficient manner. Evaluations show that despite using only a single lead, RhythmBERT achieves comparable or superior performance to strong 12-lead baselines. This generalization extends from prevalent conditions such as atrial fibrillation to clinically challenging cases such as subtle ST-T abnormalities and myocardial infarction. Our results suggest that considering ECG as structured language offers a scalable and physiologically aligned pathway for advancing cardiac analysis.

Related papers

• Diagnosing as Cardiologists Do: ECG Agents with Doctor-Grounded Priors for Clinical Reasoning Across Diseases and Populations [18.282452158790257]
  Cardiologists interpret electrocardiograms by localizing waveform components, measuring rhythm and interval patterns, and translating these structured observations into diagnostic evidence.<n>We introduce LuminaECG, a clinically structured ECG reasoning framework that reformulates ECG interpretation as measurement-grounded visual reading.<n> ECG signals are rendered on standard electrocardiographic grid paper to preserve the spatial and scale cues used in clinical reading.
  arXiv  Detail & Related papers  (2026-08-10T03:00:35Z)
• 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)
• PG-LRF: Physiology-Guided Latent Rectified Flow for Electro-Hemodynamic PPG-to-ECG Generation [51.79176059799321]
  Photoplethysmography is ubiquitous in wearables but lacks ECG-specific diagnostic morphology.<n>Existing methods rely on statistical alignment and data-driven generation.<n>We propose PG-LRF, a physiology-guided latent flow framework.
  arXiv  Detail & Related papers  (2026-05-09T07:39:58Z)
• 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)
• ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation [36.244601234085856]
  Existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation.<n>ECG-R1 is the first reasoning MLLM designed for reliable ECG interpretation.<n>Code and data are publicly available at hrefhttp://ai.heartvoice.com.cn/ECG-R1here.
  arXiv  Detail & Related papers  (2026-02-04T07:17:55Z)
• 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)
• Global and Local Contrastive Learning for Joint Representations from Cardiac MRI and ECG [40.407824759778784]
  PTACL (Patient and Temporal Alignment Contrastive Learning) is a multimodal contrastive learning framework that enhances ECG representations by integrating-temporal information from CMR.<n>We evaluate PTACL on paired ECG-CMR data from 27,951 subjects in the UK Biobank.<n>Our results highlight the potential of PTACL to enhance non-invasive cardiac diagnostics using ECG.
  arXiv  Detail & Related papers  (2025-06-24T17:19:39Z)
• CardioPatternFormer: Pattern-Guided Attention for Interpretable ECG Classification with Transformer Architecture [0.40964539027092906]
  We present CardioPatternFormer, a Transformer-based model for interpretable ECG classification.<n>It employs a sophisticated attention mechanism to precisely identify and classify diverse cardiac patterns.<n>It excels at discerning subtle anomalies and distinguishing multiple co-occurring conditions.
  arXiv  Detail & Related papers  (2025-05-26T19:36:58Z)
• Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model [25.131870247201636]
  We introduce a novel perspective on ECG signals, treating heartbeats as words and rhythms as sentences.<n>We then propose HeartLang, a novel self-supervised learning framework for ECG language processing.<n>We construct the largest heartbeat-based ECG vocabulary to date, which will further advance the development of ECG language processing.
  arXiv  Detail & Related papers  (2025-02-15T07:40:57Z)
• AnyECG: Foundational Models for Multitask Cardiac Analysis in Real-World Settings [34.078819572852446]
  Electrocardiogram (ECG) is highly sensitive in detecting acute heart attacks.<n>This paper introduces AnyECG, a foundational model designed to extract robust representations from any real-world ECG data.
  arXiv  Detail & Related papers  (2024-11-17T17:32:58Z)
• 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)
• ECG-SL: Electrocardiogram(ECG) Segment Learning, a deep learning method for ECG signal [19.885905393439014]
  We propose a novel ECG-Segment based Learning (ECG-SL) framework to explicitly model the periodic nature of ECG signals. Based on the structural features, a temporal model is designed to learn the temporal information for various clinical tasks. The proposed method outperforms the baseline model and shows competitive performances compared with task-specific methods in three clinical applications.
  arXiv  Detail & Related papers  (2023-10-01T23:17:55Z)
• Digital twinning of cardiac electrophysiology models from the surface ECG: a geodesic backpropagation approach [39.36827689390718]
  We introduce a novel method, Geodesic-BP, to solve the inverse eikonal problem. We show that Geodesic-BP can reconstruct a simulated cardiac activation with high accuracy in a synthetic test case. Given the future shift towards personalized medicine, Geodesic-BP has the potential to help in future functionalizations of cardiac models.
  arXiv  Detail & Related papers  (2023-08-16T14:57:12Z)
• Deep learning based ECG segmentation for delineation of diverse arrhythmias [0.0]
  We introduce a U-Net-like segmentation model for ECG delineation with a particular focus on diverse arrhythmias. This is followed by a post-processing algorithm which removes noise and automatically determines the boundaries of P, QRS, and T waves. Our model has been trained on a diverse dataset and evaluated against the LUDB and QTDB datasets to show strong performance, with F1-scores exceeding 99% for QRS and T waves, and over 97% for P waves in the LUDB dataset.
  arXiv  Detail & Related papers  (2023-04-13T03:20:45Z)
• A lightweight hybrid CNN-LSTM model for ECG-based arrhythmia detection [0.0]
  This paper introduces a light deep learning approach for high accuracy detection of 8 different cardiac arrhythmias and normal rhythm. A trained model for arrhythmia classification using diverse ECG signals were successfully developed and tested.
  arXiv  Detail & Related papers  (2022-08-29T05:01:04Z)

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.