# Frozen Language Model Helps ECG Zero-Shot Learning

arXiv: https://arxiv.org/abs/2303.12311 · HTML: https://mlsanity.com/paper/2303.12311/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 36 references that are in the map.
- First posted on arXiv 22 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Publicly Available Clinical BERT Embeddings](https://mlsanity.com/paper/1904.03323/) (2019)
- [Florence: A New Foundation Model for Computer Vision](https://mlsanity.com/paper/2111.11432/) (2021)
- [Multimodal Few-Shot Learning with Frozen Language Models](https://mlsanity.com/paper/2106.13884/) (2021)
- [LiT: Zero-Shot Transfer with Locked-image text Tuning](https://mlsanity.com/paper/2111.07991/) (2021)
- [MedCLIP: Contrastive Learning from Unpaired Medical Images and Text](https://mlsanity.com/paper/2210.10163/) (2022)
- [A Survey on Contrastive Self-supervised Learning](https://mlsanity.com/paper/2011.00362/) (2020)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Zero-Shot Learning Through Cross-Modal Transfer](https://mlsanity.com/paper/1301.3666/) (2013)
- [A Review of Generalized Zero-Shot Learning Methods](https://mlsanity.com/paper/2011.08641/) (2020)
- [Self-supervised representation learning from 12-lead ECG data](https://mlsanity.com/paper/2103.12676/) (2021)
- [HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units](https://mlsanity.com/paper/2008.04063/) (2020)
- [Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signals](https://mlsanity.com/paper/2109.08908/) (2021)
- [A Personalized Zero-Shot ECG Arrhythmia Monitoring System: From Sparse Representation Based Domain Adaption to Energy Efficient Abnormal Beat Detection for Practical ECG Surveillance](https://mlsanity.com/paper/2207.07089/) (2022)
- [LETS-GZSL: A Latent Embedding Model for Time Series Generalized Zero Shot Learning](https://mlsanity.com/paper/2207.12007/) (2022)

## Built on by (most cited first, 30 of 62)

- [TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting](https://mlsanity.com/paper/2310.04948/) (2023)
- [TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series](https://mlsanity.com/paper/2308.08241/) (2023)
- [A Survey of Large Language Models in Medicine: Progress, Application, and Challenge](https://mlsanity.com/paper/2311.05112/) (2023)
- [Large Language Models for Time Series: A Survey](https://mlsanity.com/paper/2402.01801/) (2024)
- [Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook](https://mlsanity.com/paper/2310.10196/) (2023)
- [Time-MMD: Multi-Domain Multimodal Dataset for Time Series Analysis](https://mlsanity.com/paper/2406.08627/) (2024)
- [Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancement](https://mlsanity.com/paper/2403.06659/) (2024)
- [Empowering Time Series Analysis with Large Language Models: A Survey](https://mlsanity.com/paper/2402.03182/) (2024)
- [Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias](https://mlsanity.com/paper/2305.19894/) (2023)
- [Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation](https://mlsanity.com/paper/2306.04811/) (2023)
- [Position: What Can Large Language Models Tell Us about Time Series Analysis](https://mlsanity.com/paper/2402.02713/) (2024)
- [M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry Optimization](https://mlsanity.com/paper/2307.08347/) (2023)
- [TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop](https://mlsanity.com/paper/2503.01013/) (2025)
- [GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Images](https://mlsanity.com/paper/2503.06073/) (2025)
- [ETP: Learning Transferable ECG Representations via ECG-Text Pre-training](https://mlsanity.com/paper/2309.07145/) (2023)
- [Teach Multimodal LLMs to Comprehend Electrocardiographic Images](https://mlsanity.com/paper/2410.19008/) (2024)
- [An Electrocardiogram Foundation Model Built on over 10 Million Recordings with External Evaluation across Multiple Domains](https://mlsanity.com/paper/2410.04133/) (2024)
- [ECG Semantic Integrator (ESI): A Foundation ECG Model Pretrained with LLM-Enhanced Cardiological Text](https://mlsanity.com/paper/2405.19366/) (2024)
- [Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey](https://mlsanity.com/paper/2405.02358/) (2024)
- [Large Language Models are Zero-Shot Next Location Predictors](https://mlsanity.com/paper/2405.20962/) (2024)
- [Boosting Masked ECG-Text Auto-Encoders as Discriminative Learners](https://mlsanity.com/paper/2410.02131/) (2024)
- [Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation](https://mlsanity.com/paper/2308.09917/) (2023)
- [Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Images](https://mlsanity.com/paper/2310.07027/) (2023)
- [From Token to Rhythm: A Multi-Scale Approach for ECG-Language Pretraining](https://mlsanity.com/paper/2506.21803/) (2025)
- [GPT-PPG: A GPT-based Foundation Model for Photoplethysmography Signals](https://mlsanity.com/paper/2503.08015/) (2025)
- [Self-Supervised Pre-Training with Joint-Embedding Predictive Architecture Boosts ECG Classification Performance](https://mlsanity.com/paper/2410.13867/) (2024)
- [A Survey on Mathematical Reasoning and Optimization with Large Language Models](https://mlsanity.com/paper/2503.17726/) (2025)
- [Towards Cross-Modality Modeling for Time Series Analytics: A Survey in the LLM Era](https://mlsanity.com/paper/2505.02583/) (2025)
- [MedualTime: A Dual-Adapter Language Model for Medical Time Series-Text Multimodal Learning](https://mlsanity.com/paper/2406.06620/) (2024)
- [A Survey on Multimodal Wearable Sensor-based Human Action Recognition](https://mlsanity.com/paper/2404.15349/) (2024)

## Abstract (arXiv)

The electrocardiogram (ECG) is one of the most commonly used non-invasive, convenient medical monitoring tools that assist in the clinical diagnosis of heart diseases. Recently, deep learning (DL) techniques, particularly self-supervised learning (SSL), have demonstrated great potential in the classification of ECG. SSL pre-training has achieved competitive performance with only a small amount of annotated data after fine-tuning. However, current SSL methods rely on the availability of annotated data and are unable to predict labels not existing in fine-tuning datasets. To address this challenge, we propose Multimodal ECG-Text Self-supervised pre-training (METS), the first work to utilize the auto-generated clinical reports to guide ECG SSL pre-training. We use a trainable ECG encoder and a frozen language model to embed paired ECG and automatically machine-generated clinical reports separately. The SSL aims to maximize the similarity between paired ECG and auto-generated report while minimize the similarity between ECG and other reports. In downstream classification tasks, METS achieves around 10% improvement in performance without using any annotated data via zero-shot classification, compared to other supervised and SSL baselines that rely on annotated data. Furthermore, METS achieves the highest recall and F1 scores on the MIT-BIH dataset, despite MIT-BIH containing different classes of ECG compared to the pre-trained dataset. The extensive experiments have demonstrated the advantages of using ECG-Text multimodal self-supervised learning in terms of generalizability, effectiveness, and efficiency.