# ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological Text

arXiv: https://arxiv.org/abs/2405.19366 · HTML: https://mlsanity.com/paper/2405.19366/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 68 references that are in the map.
- First posted on arXiv 26 May 2024.

## Builds on (most cited first, 30 of 39)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework](https://mlsanity.com/paper/2202.03052/) (2022)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [LinkBERT: Pretraining Language Models with Document Links](https://mlsanity.com/paper/2203.15827/) (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)
- [Self-supervised ECG Representation Learning for Emotion Recognition](https://mlsanity.com/paper/2002.03898/) (2020)
- [CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training](https://mlsanity.com/paper/2310.13292/) (2023)
- [Self-supervised representation learning from 12-lead ECG data](https://mlsanity.com/paper/2103.12676/) (2021)
- [Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement](https://mlsanity.com/paper/2403.06659/) (2024)
- [Frozen Language Model Helps ECG Zero-Shot Learning](https://mlsanity.com/paper/2303.12311/) (2023)
- [Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias](https://mlsanity.com/paper/2305.19894/) (2023)
- [Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer](https://mlsanity.com/paper/2205.09928/) (2022)

## Built on by (most cited first, 26 of 26)

- [An Electrocardiogram Foundation Model Built on over 10 Million Recordings with External Evaluation across Multiple Domains](https://mlsanity.com/paper/2410.04133/) (2024)
- [How Can Time Series Analysis Benefit From Multiple Modalities? A Survey and Outlook](https://mlsanity.com/paper/2503.11835/) (2025)
- [Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners](https://mlsanity.com/paper/2410.02131/) (2024)
- [Large Language Model Benchmarks in Medical Tasks](https://mlsanity.com/paper/2410.21348/) (2024)
- [From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining](https://mlsanity.com/paper/2506.21803/) (2025)
- [BEDTime: A Unified Benchmark for Automatically Describing Time Series](https://mlsanity.com/paper/2509.05215/) (2025)
- [MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning](https://mlsanity.com/paper/2406.06620/) (2024)
- [OpenECG: Benchmarking ECG Foundation Models with Public 1.2 Million Records](https://mlsanity.com/paper/2503.00711/) (2025)
- [anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task Understanding](https://mlsanity.com/paper/2506.00942/) (2025)
- [Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputs](https://mlsanity.com/paper/2502.17900/) (2025)
- [HeartcareGPT: A Unified Multimodal ECG Suite for Dual Signal-Image Modeling and Understanding](https://mlsanity.com/paper/2506.05831/) (2025)
- [TolerantECG: A Foundation Model for Imperfect Electrocardiogram](https://mlsanity.com/paper/2507.09887/) (2025)
- [Self-DANA: A Resource-Efficient Channel-Adaptive Self-Supervised Approach for ECG Foundation Models](https://mlsanity.com/paper/2507.14151/) (2025)
- [CardioState-JEPA: Delay-Aware Cross-Modal Learning of a Shared Cardiac Representation](https://mlsanity.com/paper/2608.12944/) (2026)
- [FOCAL: Fine-Grained Optimal-Transport-Driven Contrastive Alignment of Language and ECGs with Waveform Enhancement](https://mlsanity.com/paper/2505.11939/) (2025)
- [UniPACT: A Multimodal Framework for Prognostic Question Answering on Raw ECG and Structured EHR](https://mlsanity.com/paper/2601.17916/) (2026)
- [Contrastive Learning for Multi Label ECG Classification with Jaccard Score Based Sigmoid Loss](https://mlsanity.com/paper/2602.10553/) (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)
- [PRISM-CTG: A Foundation Model for Cardiotocography Analysis with Multi-View SSL](https://mlsanity.com/paper/2605.02917/) (2026)
- [Extending Pretrained 10-Second ECG Foundation Models to Longer Horizons](https://mlsanity.com/paper/2605.16975/) (2026)
- [Information-theoretic Multimodal Representation Learning for Electrocardiogram Signals](https://mlsanity.com/paper/2605.27583/) (2026)
- [EchoBridge: Long-Tail-Aware ECG-Echocardiography Text Alignment for Echocardiography-Derived Cardiac Findings](https://mlsanity.com/paper/2607.24553/) (2026)
- [Holtercare-Bench: A Multimodal Benchmark for Evaluating Long-Term Dynamic ECG Analysis](https://mlsanity.com/paper/2608.19297/) (2026)
- [Large language models in medical time series analysis](https://mlsanity.com/paper/2609.22262/) (2026)
- [Retrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical Prognosis](https://mlsanity.com/paper/2610.13510/) (2026)

## Abstract (arXiv)

The utilization of deep learning on electrocardiogram (ECG) analysis has brought the advanced accuracy and efficiency of cardiac healthcare diagnostics. By leveraging the capabilities of deep learning in semantic understanding, especially in feature extraction and representation learning, this study introduces a new multimodal contrastive pretaining framework that aims to improve the quality and robustness of learned representations of 12-lead ECG signals. Our framework comprises two key components, including Cardio Query Assistant (CQA) and ECG Semantics Integrator(ESI). CQA integrates a retrieval-augmented generation (RAG) pipeline to leverage large language models (LLMs) and external medical knowledge to generate detailed textual descriptions of ECGs. The generated text is enriched with information about demographics and waveform patterns. ESI integrates both contrastive and captioning loss to pretrain ECG encoders for enhanced representations. We validate our approach through various downstream tasks, including arrhythmia detection and ECG-based subject identification. Our experimental results demonstrate substantial improvements over strong baselines in these tasks. These baselines encompass supervised and self-supervised learning methods, as well as prior multimodal pretraining approaches.