ECG-R1 Differentiates Ischemic and Nonischemic T-Wave Inversion

Researchers from Peking University developed ECG-R1, a multimodal vision-language model trained with reinforcement learning to differentiate ischemic from nonischemic T-wave inversion on ECGs. The model, accepted at ICML 2026, outperforms standard supervised fine-tuning and exposes widespread hallucinations in existing medical MLLMs including GPT-5.1 and MedGemma. Model weights and a 30,000-sample dataset are publicly available, though results are preprint-stage and lack regulatory clearance.

ECG-R1 Differentiates Ischemic and Nonischemic T-Wave Inversion Researchers from Peking University report ECG-R1, a multimodal vision-language model trained with reinforcement learning to differentiate primary ischemic from secondary nonischemic T-wave inversion on ECGs. A JMIR Preprint states the RL-based framework 'successfully differentiates ischemic from non-ischemic TWI and demonstrates significantly better generalization than standard supervised fine-tuning.' The related arXiv preprint, accepted at ICML 2026, describes ECG-R1 as the first reasoning ECG MLLM and benchmarks current MLLMs including GPT-5.1 and MedGemma, finding 'severe hallucinations are widespread' in ECG interpretation across all tested models. Model weights ECG-R1-8B and a 30,000-sample training dataset are publicly available. Results are preprint-stage and do not constitute regulatory clearance or clinical deployment. What happened Per a JMIR Preprint and ResearchGate listing April 2026 , researchers developed ECG-R1, a multimodal vision-language model trained with reinforcement learning to differentiate primary ischemic from secondary nonischemic T-wave inversion on ECGs. The JMIR abstract states the RL-based framework "successfully differentiates ischemic from non-ischemic TWI and demonstrates significantly better generalization than standard SFT supervised fine-tuning ." The related arXiv preprint 2602.04279 , accepted at ICML 2026 per the project GitHub repository, describes the same model as "the first reasoning ECG MLLM designed for reliable ECG interpretation," per the paper's abstract. Architecture ECG-R1 combines Qwen3-VL-8B as the language-vision backbone with ECG-CoCa as a dedicated time-series encoder, using decoupled projectors for each modality to avoid shared-capacity bottlenecks in earlier ECG MLLMs. Training follows a two-stage pipeline: supervised fine-tuning on 30,000 protocol-guided samples from MIMIC-IV-ECG - where the five-phase interpretation protocol is derived from a clinical cardiology monograph - followed by reinforcement learning with ECG Diagnostic Evidence Rewards EDER . Unlike general reasoning LLMs such as DeepSeek-R1, EDER rewards structured intermediate clinical reasoning steps, not only final-answer correctness. An Interleaved Modality Dropout training strategy improves robustness when ECG signal or image data is missing at inference time. Why it matters T-wave inversion requires rapid triage between ischemia and secondary causes such as bundle branch block or ventricular hypertrophy. Per the arXiv paper, existing MLLMs including GPT-5.1 and MedGemma produce "plausible but clinically incorrect" ECG analyses, with the paper providing "the first quantitative evidence that severe hallucinations are widespread" in current models across proprietary, open-source, and medical MLLM categories. Licensed cardiologist evaluation is included in the ICML paper's experiments. Availability Code, model weights ECG-R1-8B-RL , and a 30,000-sample protocol-guided training dataset are publicly released on GitHub PKUDigitalHealth/ECG-R1 and HuggingFace. A live demo is accessible at ai.heartvoice.com.cn/ECG-R1. The work is led by Shenda Hong's group at Peking University; two co-authors are Tencent employees, as disclosed in the paper. Caveat The T-wave inversion differentiation results originate from a JMIR preprint pending peer review. The broader ECG-R1 paper is accepted at ICML 2026 for ML peer review but neither represents clinical regulatory clearance nor validated deployment in a hospital setting. Scoring Rationale ECG-R1 is a substantive research contribution - the first reasoning MLLM for ECG interpretation, accepted at ICML 2026, with public model weights and the first systematic hallucination benchmark across medical MLLMs. The T-wave inversion application is clinically relevant but validation is preprint-stage and the work is specialized within medical AI, placing it in the solid research tier rather than a major industry event. Practice with real Health & Insurance data 90 SQL & Python problems · 15 industry datasets 250 free problems · No credit card See all Health & Insurance problems /problems/datasets/health