mlsanityData to 7 Oct 2026

ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation

arXiv 2602.04279 ↗First posted 4 Feb 2026cs.CLcited by 8

Not on the map. Why?

Abstract (arXiv)

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 ECG MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using textitProtocol-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 textitInterleaved Modality Dropout to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present textitReinforcement 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 is available at hrefhttps://github.com/PKUDigitalHealth/ECG-R1here.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 26 of its 59 references that are in the map. First posted on arXiv 4 Feb 2026.

Builds on

26 of 59 references.

References · 26

  1. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  2. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  3. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,769
  4. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
  5. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
  6. 2025GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learningcited by 439
  7. 2025MedGemma Technical Reportcited by 398
  8. 2025R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimizationcited by 296
  9. 2024HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scalecited by 194
  10. 2025MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipecited by 174
  11. 2020CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patientscited by 170
  12. 2024Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogramcited by 84
14 more
  1. 2024Zero-Shot ECG Classification with Multimodal Learning and Test-time Clinical Knowledge Enhancementcited by 66
  2. 2023Frozen Language Model Helps ECG Zero-Shot Learningcited by 62
  3. 2025QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Trainingcited by 38
  4. 2024ECG-Chat: A Large ECG-Language Model for Cardiac Disease Diagnosiscited by 37
  5. 2025Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Modelcited by 36
  6. 2021Intra-Inter Subject Self-supervised Learning for Multivariate Cardiac Signalscited by 35
  7. 2025GEM: Empowering MLLM for Grounded ECG Understanding with Time Series and Imagescited by 35
  8. 2024Teach Multimodal LLMs to Comprehend Electrocardiographic Imagescited by 25
  9. 2023ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitizationcited by 20
  10. 2025Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Searchcited by 16
  11. 2025anyECG-chat: A Generalist ECG-MLLM for Flexible ECG Input and Multi-Task Understandingcited by 9
  12. 2025Simulator and Experience Enhanced Diffusion Model for Comprehensive ECG Generationcited by 8
  13. 2025UniECG: Understanding and Generating ECG in One Unified Modelcited by 4
  14. 2025Self-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECGcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretationcited by 2
  2. 2026DeepArrhythmia: Segment-Contextualized ECG Arrhythmia Classification via Selective Evidence Acquisitioncited by 1
  3. 2026Knowledge Knows, Verbalization Tells: Disentangling Latent Directions for Mathematical Solvability in LLMscited by 1
  4. 2026Reasoning Before Diagnosis: Physician-Inspired Structured Thinking for ECG Classificationcited by 0
  5. 2026EchoBridge: Long-Tail-Aware ECG-Echocardiography Text Alignment for Echocardiography-Derived Cardiac Findingscited by 0
  6. 2026Cardiologent: Multi-Agent Clinical Decision Support for Patient-Level Arrhythmia Assessment, Urgency, and Managementcited by 0
  7. 2026Diagnosing as Cardiologists Do: ECG Agents with Doctor-Grounded Priors for Clinical Reasoning Across Diseases and Populationscited by 0
  8. 2026ECG-Scroll: A Long-Horizon, Streaming Benchmark and Agent Environment for Interpretation of Ambulatory Electrocardiogramscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026How Well Do Multimodal Models Reason on ECG Signals?
  2. 2026CARE-ECG: Causal Agent-based Reasoning for Explainable and Counterfactual ECG Interpretation
  3. 2026ECGQuest: Benchmarking and Fine-Tuning Language Models for Electrocardiography
  4. 2026ECG-LLM: Foundation Model for ECG-Based Cardiac Reasoning
  5. 2024De-biased Multimodal Electrocardiogram Analysis
  6. 2026Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs
  7. 2025Interpretable Multimodal Zero-Shot ECG Diagnosis via Structured Clinical Knowledge Alignment
  8. 2026Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers