# Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model

arXiv: https://arxiv.org/abs/2502.10707 · HTML: https://mlsanity.com/paper/2502.10707/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 15 Feb 2025.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI](https://mlsanity.com/paper/2405.18765/) (2024)
- [BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers](https://mlsanity.com/paper/2208.06366/) (2022)
- [CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients](https://mlsanity.com/paper/2005.13249/) (2020)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion](https://mlsanity.com/paper/2202.04770/) (2022)
- [Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram](https://mlsanity.com/paper/2402.09450/) (2024)
- [Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement](https://mlsanity.com/paper/2403.06659/) (2024)
- [Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer](https://mlsanity.com/paper/2205.09928/) (2022)
- [Lead-agnostic Self-supervised Learning for Local and Global Representations of Electrocardiogram](https://mlsanity.com/paper/2203.06889/) (2022)
- [Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals](https://mlsanity.com/paper/2109.08908/) (2021)
- [MINA: Multilevel Knowledge-Guided Attention for Modeling Electrocardiography Signals](https://mlsanity.com/paper/1905.11333/) (2019)
- [ECGBERT: Understanding Hidden Language of ECGs with Self-Supervised Representation Learning](https://mlsanity.com/paper/2306.06340/) (2023)
- [ECG Language Processing (ELP): a New Technique to Analyze ECG Signals](https://mlsanity.com/paper/2006.08841/) (2020)
- [A Simple Self-Supervised ECG Representation Learning Method via Manipulated Temporal-Spatial Reverse Detection](https://mlsanity.com/paper/2202.12458/) (2022)

## Built on by (most cited first, 30 of 36)

- [CodeBrain: Bridging Decoupled Tokenizer and Multi-Scale Architecture for EEG Foundation Model](https://mlsanity.com/paper/2506.09110/) (2025)
- [From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining](https://mlsanity.com/paper/2506.21803/) (2025)
- [Towards Robust Multimodal Physiological Foundation Models: Handling Arbitrary Missing Modalities](https://mlsanity.com/paper/2504.19596/) (2025)
- [ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation](https://mlsanity.com/paper/2602.04279/) (2026)
- [CLEF: Clinically-Guided Contrastive Learning for Electrocardiogram Foundation Models](https://mlsanity.com/paper/2512.02180/) (2025)
- [SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learning](https://mlsanity.com/paper/2502.19668/) (2025)
- [Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs](https://mlsanity.com/paper/2502.17900/) (2025)
- [UniECG: Understanding and Generating ECG in One Unified Model](https://mlsanity.com/paper/2509.18588/) (2025)
- [Self-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECG](https://mlsanity.com/paper/2509.19397/) (2025)
- [Signal, Image, or Symbolic: Exploring the Best Input Representation for Electrocardiogram-Language Models Through a Unified Framework](https://mlsanity.com/paper/2505.18847/) (2025)
- [HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding](https://mlsanity.com/paper/2506.05831/) (2025)
- [RhythmBERT: A Self-Supervised Language Model Based on Latent Representations of ECG Waveforms for Heart Disease Detection](https://mlsanity.com/paper/2602.23060/) (2026)
- [CardioState-JEPA: Delay-Aware Cross-Modal Learning of a Shared Cardiac Representation](https://mlsanity.com/paper/2608.12944/) (2026)
- [Tracing the Heart's Pathways: ECG Representation Learning from a Cardiac Conduction Perspective](https://mlsanity.com/paper/2512.24002/) (2025)
- [Foundation Model for Cardiac Time Series via Masked Latent Attention](https://mlsanity.com/paper/2603.26475/) (2026)
- [How Do Electrocardiogram Models Scale?](https://mlsanity.com/paper/2605.17276/) (2026)
- [LVCG: Learning ECG Representations in the Latent Vectorcardiogram Space](https://mlsanity.com/paper/2605.31249/) (2026)
- [Approaching Low-Cost Cardiac Intelligence with Semi-Supervised Knowledge Distillation](https://mlsanity.com/paper/2511.02851/) (2025)
- [BEAT-Net: Injecting Biomimetic Spatio-Temporal Priors for Interpretable ECG Diagnosis](https://mlsanity.com/paper/2601.07316/) (2026)
- [ELF: A Family of Encoder-Free ECG-Language Models](https://mlsanity.com/paper/2601.18798/) (2026)
- [Position: Evaluation of ECG Representations Must Be Fixed](https://mlsanity.com/paper/2602.17531/) (2026)
- [Learning ECG Image Representations via Dual Physiological-Aware Alignments](https://mlsanity.com/paper/2604.01526/) (2026)
- [PanLUNA: An Efficient and Robust Query-Unified Multimodal Model for Edge Biosignal Intelligence](https://mlsanity.com/paper/2604.04297/) (2026)
- [CoRe-ECG: Advancing Self-Supervised Representation Learning for 12-Lead ECG via Contrastive and Reconstructive Synergy](https://mlsanity.com/paper/2604.11359/) (2026)
- [From Muscle Bursts to Motor Intent: Self-Supervised Token Modeling for Heterogeneous EMG](https://mlsanity.com/paper/2605.03462/) (2026)
- [Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classification](https://mlsanity.com/paper/2605.17308/) (2026)
- [Information-theoretic Multimodal Representation Learning for Electrocardiogram Signals](https://mlsanity.com/paper/2605.27583/) (2026)
- [MyoSem: Aligning Electromyography with Natural-Language Action Semantics](https://mlsanity.com/paper/2606.00174/) (2026)
- [SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signal Self-supervised Learning](https://mlsanity.com/paper/2606.21973/) (2026)
- [EchoBridge: Long-Tail-Aware ECG-Echocardiography Text Alignment for Echocardiography-Derived Cardiac Findings](https://mlsanity.com/paper/2607.24553/) (2026)

## Abstract (arXiv)

Electrocardiogram (ECG) is essential for the clinical diagnosis of arrhythmias and other heart diseases, but deep learning methods based on ECG often face limitations due to the need for high-quality annotations. Although previous ECG self-supervised learning (eSSL) methods have made significant progress in representation learning from unannotated ECG data, they typically treat ECG signals as ordinary time-series data, segmenting the signals using fixed-size and fixed-step time windows, which often ignore the form and rhythm characteristics and latent semantic relationships in ECG signals. In this work, we introduce a novel perspective on ECG signals, treating heartbeats as words and rhythms as sentences. Based on this perspective, we first designed the QRS-Tokenizer, which generates semantically meaningful ECG sentences from the raw ECG signals. Building on these, we then propose HeartLang, a novel self-supervised learning framework for ECG language processing, learning general representations at form and rhythm levels. Additionally, we construct the largest heartbeat-based ECG vocabulary to date, which will further advance the development of ECG language processing. We evaluated HeartLang across six public ECG datasets, where it demonstrated robust competitiveness against other eSSL methods. Our data and code are publicly available at https://github.com/PKUDigitalHealth/HeartLang.