From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911542786654208 |
|---|---|
| author | Luo, Chanyong Dai, Jirui Wang, Zhendong Chen, Kui Yang, Jiaxi Lu, Bingjie Wang, Jing Hao, Jiaxin Li, Bing He, Ruiyang Qiao, Yiyu Zhang, Chenkai Wang, Kaiyu Liu, Zhi Zheng, Zeyu Li, Yan Gu, Xiaohong |
| author_facet | Luo, Chanyong Dai, Jirui Wang, Zhendong Chen, Kui Yang, Jiaxi Lu, Bingjie Wang, Jing Hao, Jiaxin Li, Bing He, Ruiyang Qiao, Yiyu Zhang, Chenkai Wang, Kaiyu Liu, Zhi Zheng, Zeyu Li, Yan Gu, Xiaohong |
| contents | Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic competence through repeated cycles of application, reflection, and improvement, forming individualized methodologies. Yet outcomes vary widely, and master physicians' knowledge systems are slow to develop and hard to transmit at scale, contributing to the scarcity of high-quality clinical expertise. To address this, we propose Med-Shicheng, a general framework that enables large language models to systematically learn and transfer distinguished physicians' diagnostic-and-therapeutic philosophy and case-dependent adaptation rules in a standardized way. Built on Tianyi, Med-Shicheng consists of five stages. We target five National Masters of Chinese Medicine or distinguished TCM physicians, curate multi-source materials, and train a single model to internalize all five knowledge systems across seven tasks, including etiology-pathogenesis analysis, syndrome diagnosis, treatment principle selection, prescription generation, prescription explanation, symptom evolution with regimen adjustment, and clinical advice. Implemented on Qwen2.5-1.5B-Base, Med-Shicheng runs on resource-constrained GPUs while achieving performance comparable to DeepSeek-R1 and GPT-5. We also examine the reliability of LLM-as-a-judge versus physician evaluation: automated judging tracks overall trends but shows bias on fine-grained individualized distinctions, highlighting the need for physician involvement when ground truth is unavailable and for domain-adapted judge models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_23520 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM Luo, Chanyong Dai, Jirui Wang, Zhendong Chen, Kui Yang, Jiaxi Lu, Bingjie Wang, Jing Hao, Jiaxin Li, Bing He, Ruiyang Qiao, Yiyu Zhang, Chenkai Wang, Kaiyu Liu, Zhi Zheng, Zeyu Li, Yan Gu, Xiaohong Computation and Language Artificial Intelligence Medicine is an empirical discipline refined through long-term observation and the messy, high-variance reality of clinical practice. Physicians build diagnostic and therapeutic competence through repeated cycles of application, reflection, and improvement, forming individualized methodologies. Yet outcomes vary widely, and master physicians' knowledge systems are slow to develop and hard to transmit at scale, contributing to the scarcity of high-quality clinical expertise. To address this, we propose Med-Shicheng, a general framework that enables large language models to systematically learn and transfer distinguished physicians' diagnostic-and-therapeutic philosophy and case-dependent adaptation rules in a standardized way. Built on Tianyi, Med-Shicheng consists of five stages. We target five National Masters of Chinese Medicine or distinguished TCM physicians, curate multi-source materials, and train a single model to internalize all five knowledge systems across seven tasks, including etiology-pathogenesis analysis, syndrome diagnosis, treatment principle selection, prescription generation, prescription explanation, symptom evolution with regimen adjustment, and clinical advice. Implemented on Qwen2.5-1.5B-Base, Med-Shicheng runs on resource-constrained GPUs while achieving performance comparable to DeepSeek-R1 and GPT-5. We also examine the reliability of LLM-as-a-judge versus physician evaluation: automated judging tracks overall trends but shows bias on fine-grained individualized distinctions, highlighting the need for physician involvement when ground truth is unavailable and for domain-adapted judge models. |
| title | From Physician Expertise to Clinical Agents: Preserving, Standardizing, and Scaling Physicians' Medical Expertise with Lightweight LLM |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.23520 |