arXiv：cs.AI· Yuanfan Lin, Jie Di, Xujin He, Zhenzhe Lin, Jialing Chen, Ruiyang Li, Changyu Zheng, Yuanrui Shang, Weiqin Peng, Jingxi Qin, Xiong Wang, Dongxin Ye, Yining Huang, Guoqiang Li, Andi Xu, Sijia Yu, Ruixin Wang, Yahan Yang, Xiaohang Wu, Duoru Lin, Jingjing Chen, Zhenzhen Liu, Wenben Chen, Haotian Lin·· 16 小时前
GUIDE：用多智能体共识生成可信临床实践指南
GUIDE: Computationally Augmented Consensus for Trustworthy Clinical Practice Guidelines
AI 导读
GUIDE 是一个用于人机协作生成与更新临床实践指南的多智能体 copilot 系统，在 12 个 NICE 眼科数据集上实现 88.85% 文献召回率、86.06% 证据确定性评级一致性和 91.67% 推荐意见一致率，平均每个数据集耗时 162.17 分钟，人工干预占比 28.68%。
正文
Authors:Yuanfan Lin, Jie Di, Xujin He, Zhenzhe Lin, Jialing Chen, Ruiyang Li, Changyu Zheng, Yuanrui Shang, Weiqin Peng, Jingxi Qin, Xiong Wang, Dongxin Ye, Yining Huang, Guoqiang Li, Andi Xu, Sijia Yu, Ruixin Wang, Yahan Yang, Xiaohang Wu, Duoru Lin, Jingjing Chen, Zhenzhen Liu, Wenben Chen, Haotian Lin
Abstract:Maintaining up-to-date clinical practice guidelines (CPGs) is essential for evidence-based medicine, but rapid evidence growth and complex expert consensus formation limit timely updates. We developed GUIDE, a multi-agent copilot system for human-AI collaborative guideline generation and updating. GUIDE delegates labor-intensive tasks to specialized AI agents while preserving expert judgment and final arbitration. In 12 NICE ophthalmology datasets, GUIDE achieved 88.85% literature recall, 86.06% alignment in certainty-of-evidence ratings, and 91.67% recommendation agreement, requiring 162.17 minutes per dataset on average (28.68% human intervention). Performance remained stable across 20 additional datasets from cardiology, endocrinology, gastroenterology, and respiratory medicine. Ablation analysis showed that removing expert intervention reduced performance in judgment-intensive steps such as Risk-of-Bias assessment. In six post-cutoff datasets, GUIDE maintained robust end-to-end performance on unseen evidence. Prospective real-world validation showed that GUIDE reduced expert workload and produced more clinically acceptable recommendations than the original decade-old guideline (mean score, 3.73 vs. 1.53; agreement, 66.7% vs. 13.3%), with outcomes comparable to human-only updating (P = 0.588) but substantially less time and effort. GUIDE offers a practical framework for timely, trustworthy, expert-centric guideline development and validates computationally augmented consensus.
| Comments: | 108 pages total, 28 pages main text, 5 figures, 4 supplementary figures, 8 supplementary tables. Research article |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Human-Computer Interaction (cs.HC); Multiagent Systems (cs.MA) |
| ACM classes: | I.2.11; I.2.7; J.3 |
| Cite as: | arXiv:2610.16108 [cs.AI] |
| (or arXiv:2610.16108v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16108 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xujin He [view email]
[v1]
Mon, 12 Oct 2026 03:16:18 UTC (4,596 KB)
来源：arXiv：cs.AI · arxiv.org