Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Kim, Junu, Shim, Chaeeun, Park, Sungjin, Lee, Su Yeon, Suh, Gee Young, Lim, Chae-Man, Choi, Seong Jin, Moon, Song Mi, Song, Kyoung-Ho, Kim, Eu Suk, Kim, Hong Bin, Kim, Sejoong, Im, Chami, Kang, Dong-Wan, Kim, Yong Soo, Bae, Hee-Joon, Lim, Sung Yoon, Jeong, Han-Gil, Choi, Edward
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.02722
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915273813000192
author Kim, Junu
Shim, Chaeeun
Park, Sungjin
Lee, Su Yeon
Suh, Gee Young
Lim, Chae-Man
Choi, Seong Jin
Moon, Song Mi
Song, Kyoung-Ho
Kim, Eu Suk
Kim, Hong Bin
Kim, Sejoong
Im, Chami
Kang, Dong-Wan
Kim, Yong Soo
Bae, Hee-Joon
Lim, Sung Yoon
Jeong, Han-Gil
Choi, Edward
author_facet Kim, Junu
Shim, Chaeeun
Park, Sungjin
Lee, Su Yeon
Suh, Gee Young
Lim, Chae-Man
Choi, Seong Jin
Moon, Song Mi
Song, Kyoung-Ho
Kim, Eu Suk
Kim, Hong Bin
Kim, Sejoong
Im, Chami
Kang, Dong-Wan
Kim, Yong Soo
Bae, Hee-Joon
Lim, Sung Yoon
Jeong, Han-Gil
Choi, Edward
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_02722
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enhancing LLMs' Clinical Reasoning with Real-World Data from a Nationwide Sepsis Registry
Kim, Junu
Shim, Chaeeun
Park, Sungjin
Lee, Su Yeon
Suh, Gee Young
Lim, Chae-Man
Choi, Seong Jin
Moon, Song Mi
Song, Kyoung-Ho
Kim, Eu Suk
Kim, Hong Bin
Kim, Sejoong
Im, Chami
Kang, Dong-Wan
Kim, Yong Soo
Bae, Hee-Joon
Lim, Sung Yoon
Jeong, Han-Gil
Choi, Edward
Artificial Intelligence
Machine Learning
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.
title Enhancing LLMs' Clinical Reasoning with Real-World Data from a Nationwide Sepsis Registry
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.02722