亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

CARE: A clinical agentic reasoning engine to enhance real-World diagnostic accuracy via structured medical reasoning

作者
Wenjie Li,Yujie Zhang,C R Wang,Yueqi Li,Xingqi He,Angela Lin Wang,Mengzhe Xu,Fanrui Zhang,Haoran Sun,Kailing Wang,Renhao Yang,Shiyi Yao,Yidong Xu,Hanyu Wang,Yilin Huang,Chen Shi,Gen Li,Carlos Gutiérrez Sanromán,Lei Wang
出处
期刊:Expert Systems With Applications [Elsevier BV]
卷期号:313: 131476-131476 被引量:3
标识
DOI:10.1016/j.eswa.2026.131476
摘要

Recent advancements in large language models (LLMs) have improved performance on standardized medical benchmarks. However, existing benchmarks often rely on truncated context and idealized scenarios. In practice, clinical diagnosis requires synthesizing patient history, physical examination, laboratory tests, and imaging under time constraints, and LLMs can struggle with accuracy and may hallucinate when confronted with authentic cases. To address this challenge, we propose the Clinical Agentic Reasoning Engine (CARE) , a physician-inspired workflow that structures diagnosis into retrieval, preliminary diagnosis, final diagnosis, and confidence-gated recheck, with intermediate outputs serialized in JSON for verifiable, training-free inference. Using CARE as a data-generation pipeline with clinician-prepared diagnostic criteria, we curate 2,000 de-identified real-world cases across 15 abdominal disease categories and produce stepwise CARE annotations under a fixed schema. We adopt Dual-stage Alignment for Reasoning Enhancement (DARE) , which trains on these CARE-annotated trajectories, uses supervised fine-tuning on physician-structured long-form demonstrations and then applies group relative policy optimization to refine policy and promote self-correction. Finally, we introduce CARE-Dx , the resulting diagnosis model obtained by applying DARE to an instruction-tuned backbone, while CARE also remains a training-free inference protocol that can be applied to other LLMs. Experiments show that, under DARE, CARE-Dx achieves strong in-domain and zero-shot out-of-domain performance and approaches leading closed-source accuracy on evaluations, with clinician assessment by 12 experienced physicians from multiple departments confirming that its reasoning aligns with real clinical workflows. Moreover, on the de-identified private cohort Rui-EHR , which covers a broader set of diseases, the CARE pipeline maintains diagnostic quality.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
18秒前
31秒前
干净寄松完成签到,获得积分10
40秒前
48秒前
孝顺的筮完成签到,获得积分10
49秒前
null的应助被科研通管家采纳,获得10
56秒前
null的应助被科研通管家采纳,获得10
57秒前
null的应助被科研通管家采纳,获得10
57秒前
呆萌保温杯完成签到,获得积分10
1分钟前
水water完成签到 ,获得积分10
1分钟前
和谐寻云完成签到,获得积分10
1分钟前
dnpl完成签到,获得积分10
1分钟前
1分钟前
1分钟前
诚心的志泽完成签到,获得积分10
1分钟前
Richard发布了新的文献求助30
1分钟前
1分钟前
健康的忘幽完成签到,获得积分10
1分钟前
温不胜的破木吉他完成签到 ,获得积分10
1分钟前
善良士晋完成签到,获得积分10
2分钟前
2分钟前
2分钟前
xiaobai123456完成签到,获得积分10
2分钟前
高高笙完成签到,获得积分10
2分钟前
2分钟前
2分钟前
2分钟前
null的应助被科研通管家采纳,获得10
2分钟前
渡人舟的应助被科研通管家采纳,获得10
2分钟前
醉熏的孤云完成签到,获得积分10
3分钟前
852的应助被liuqiwei采纳,获得200
3分钟前
3分钟前
彩色白竹完成签到,获得积分10
3分钟前
3分钟前
3分钟前
bwx发布了新的文献求助200
3分钟前
3分钟前
傻傻的含莲完成签到,获得积分10
3分钟前
3分钟前
3分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8158848
求助须知:如何正确求助?哪些是违规求助? 9554492
关于积分的说明 21719333
捐赠科研通 7748419
什么是DOI,文献DOI怎么找? 3427099
关于科研通互助平台的介绍 2552006
邀请新用户注册赠送积分活动 2471370