Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning
Abstract
The clinical adoption of artificial intelligence (AI) in medical diagnostics is critically hampered by its black-box nature, which prevents clinicians from verifying the rationale behind automated decisions. To overcome this fundamental barrier, we introduce DeepMedix-R1, a foundation model (FM) for chest X-ray (CXR) interpretation that generates not only accurate diagnoses but also a transparent, step-by-step reasoning process grounded in specific visual evidence. Our methodology employs a sequential training strategy, beginning with instruction fine-tuning, followed by a cold-start phase to elicit reasoning capabilities. Critically, we then implement reinforcement learning with grounded rewards to meticulously refine the model, aligning both its diagnostic outputs and its reasoning pathways with clinical plausibility. Quantitative assessments show that DeepMedix-R1 substantially outperforms advanced FMs, achieving improvements in report generation and visual question answering tasks. We also introduce Report Arena, a novel LLM-based benchmark that ranks DeepMedix-R1 first among competing models for output quality. Most significantly, a formal review by clinical experts reveals a profound preference for DeepMedix-R1's generated reasoning over the broadly adopted Qwen2.5-VL-7B model, confirming its superior interpretability and clinical utility.
Keywords
Cite
@article{arxiv.2509.03906,
title = {Toward Clinically Explainable AI for Medical Diagnosis: A Foundation Model with Human-Compatible Reasoning via Reinforcement Learning},
author = {Qika Lin and Yifan Zhu and Bin Pu and Ling Huang and Haoran Luo and Jingying Ma and Feng Wu and Kai He and Jiaxing Xu and Zhen Peng and Tianzhe Zhao and Fangzhi Xu and Jian Zhang and Zhonghong Ou and Erik Cambria and Swapnil Mishra and Mengling Feng},
journal= {arXiv preprint arXiv:2509.03906},
year = {2026}
}
Comments
35 pages