Although large language models (LLMs) have demonstrated impressive reasoning capabilities across general domains, their effectiveness in real-world clinical practice remains limited. This is likely due to their insufficient exposure to real-world clinical data during training, as such data is typically not included due to privacy concerns. To address this, we propose enhancing the clinical reasoning capabilities of LLMs by leveraging real-world clinical data. We constructed reasoning-intensive questions from a nationwide sepsis registry and fine-tuned Phi-4 on these questions using reinforcement learning, resulting in C-Reason. C-Reason exhibited strong clinical reasoning capabilities on the in-domain test set, as evidenced by both quantitative metrics and expert evaluations. Furthermore, its enhanced reasoning capabilities generalized to a sepsis dataset involving different tasks and patient cohorts, an open-ended consultations on antibiotics use task, and other diseases. Future research should focus on training LLMs with large-scale, multi-disease clinical datasets to develop more powerful, general-purpose clinical reasoning models.
View on arXiv@article{kim2025_2505.02722,
title={ Enhancing LLMs' Clinical Reasoning with Real-World Data from a Nationwide Sepsis Registry },
author={ Junu Kim and Chaeeun Shim and Sungjin Park and Su Yeon Lee and Gee Young Suh and Chae-Man Lim and Seong Jin Choi and Song Mi Moon and Kyoung-Ho Song and Eu Suk Kim and Hong Bin Kim and Sejoong Kim and Chami Im and Dong-Wan Kang and Yong Soo Kim and Hee-Joon Bae and Sung Yoon Lim and Han-Gil Jeong and Edward Choi },
journal={arXiv preprint arXiv:2505.02722},
year={ 2025 }
}