analiza aiqbench
This study demonstrates a practical pathway to bridging the gap between general LLM capabilities and specialized clinical reasoning by fine-tuning models on real-world, privacy-compliant sepsis registry data. By applying reinforcement learning with constructed reasoning-intensive questions, researchers successfully created C-Reason, which shows robust performance across diverse medical tasks including antibiotic consultation for different diseases. The work highlights that targeted training on large-scale, multi-disease datasets is essential for developing general-purpose AI models capable of safe and effective deployment in healthcare environments.
Enhancing LLMs' Clinical Reasoning with Real-World Data from a Nationwide Sepsis Registry
arXiv:2505.02722v2 Announce Type: replace Abstract: 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.
Abstract: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.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2505.02722 [cs.AI]
(or arXiv:2505.02722v2 [cs.AI] for this version)
Text integral sub licența deschisă a publicației · 164 cuvinte
Subiecte conexe
Amazon Research Awards recipients announced
Amazon Science · 27 mai 2026
34 Amazon Research Awards Build on Trainium recipients announced
Amazon Science · 5 aug. 2026
Amazon is investing in the Lean Focused Research Organization
Amazon Science · 26 iul. 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026