ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
Authors:
- Yingying ZhangYZYingying Zhang
- Xian WuXWXian Wu
- Hongyan LiHLHongyan Li
- Shenda HongSHShenda Hong
Preprint
Abstract
Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first reasoning MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using \textit{Protocol-Guided Instruction Data Generation}, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with \textit{Interleaved Modality Dropout} to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present \textit{Reinforcement Learning with ECG Diagnostic Evidence Rewards} to strengthen evidence-grounded ECG interpretation. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe hallucinations are widespread, suggesting that the public should not directly trust these outputs without independent verification. Code and data are publicly available at \href{https://github.com/PKUDigitalHealth/ECG-R1}{here}, and an online platform can be accessed at \href{http://ai.heartvoice.com.cn/ECG-R1/}{here}.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Teaching multimodal LLMs to comprehend 12-lead electrocardiographic imagesnpj Digital Medicine, 2026
- MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning2025
- DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learningNature, 2025
- Visual Instruction Tuning towards General-Purpose Multimodal Large Language Model: A SurveyInternational Journal of Computer Vision, 2025
- ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosis2025
- An Electrocardiogram Foundation Model Built on over 10 Million RecordingsNEJM AI, 2025
- ECG-Image-Kit: a synthetic image generation toolbox to facilitate deep learning-based electrocardiogram digitizationPhysiological Measurement, 2024
- Deep learning in ECG diagnosis: A reviewKnowledge-Based Systems, 2021
- Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic reviewComputers in Biology and Medicine, 2020
- Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordingsPhysiological Measurement, 2019