复杂肺癌开放决策的可审计条件策略框架

中文摘要 AI 辅助

复杂肺癌决策可能涉及多条可辩护的路径，其资格、顺序和安全性取决于尚未解决的信息。有效的支持必须明确说明患者状况如何决定路径的资格、延迟和重定向。MedGPT临床探索者（MCE）将备选方案、决策改变性未知因素、安全约束和回退组织成供临床医生审查的条件策略。为了评估这种表示在医生撰写的策略中的效果，多学科专家在有意选取的100例病例语料库中为40例建立了病例特定参考，来自98个机构的250名医生在无辅助、检索参考和MCE辅助条件下产生了2,250条策略。MCE辅助策略表达了更多适用的临床要求，以可允许路径达成评分（APAS；0-100）衡量，优于无辅助策略（调整后差异，12.87；95%置信区间，11.18-14.55）和检索参考策略（5.22；3.52-6.93）。在检索参考和MCE辅助条件下提供相同知识库时，额外内容集中在候选路径、决策关键信息和安全约束上。医生的整体策略可接受性判断与APAS相关（Spearman's rho = 0.671），而补充的关系审计评估了候选、条件和后续行动是否连贯连接。这些发现共同确定了开放决策支持的两个互补维度：临床相关内容的覆盖以及路径、条件和后续行动之间的连贯联系。MCE提供了一个共享的决策对象，使行动前的重要遗漏和路径偶然性可见；前瞻性研究应评估其对临床工作流程和患者结果的影响。

英文摘要

Complex lung cancer decisions can involve several defensible pathways whose eligibility, sequencing and safety depend on unresolved information. Effective support must make explicit how patient conditions govern pathway eligibility, deferral and redirection. MedGPT Clinical Explorer (MCE) organizes alternatives, decision-changing unknowns, safety constraints and fallback into a conditional strategy for clinician review. To evaluate this representation in physician-authored strategies, multidisciplinary experts established case-specific references for 40 cases within a purposive 100-case corpus, and 250 physicians from 98 institutions produced 2,250 strategies under unaided, retrieval-reference and MCE-assisted conditions. MCE-assisted strategies expressed more applicable clinical requirements, measured by the Admissible Pathway Attainment Score (APAS; 0-100), than unaided strategies (adjusted difference, 12.87; 95% CI, 11.18-14.55) and retrieval-reference strategies (5.22; 3.52-6.93). With the same knowledge base available in the retrieval-reference and MCE-assisted conditions, the additional content centered on candidate pathways, decision-critical information and safety constraints. Physicians' whole-strategy acceptability judgments correlated with APAS (Spearman's rho = 0.671), while a complementary relationship audit assessed whether candidates, conditions and subsequent actions were coherently connected. Together, these findings identify two complementary dimensions of open-ended decision support: coverage of clinically relevant content and coherent links among pathways, conditions and subsequent actions. MCE provides a shared decision object that makes consequential omissions and pathway contingencies visible before action; prospective studies should evaluate its effects on clinical workflow and patient outcomes.

发表机构

• Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College（北京协和医院，中国医学科学院 北京协和医学院）
• Medlinker Intelligent and Digital Technology Co. Ltd.（医联智能数字科技有限公司）
• National Clinical Research Center for Dermatologic and Immunologic Diseases（国家皮肤与免疫疾病临床医学研究中心）
• Institute of Intelligent Medicine, Chinese Academy of Medical Sciences（中国医学科学院智能医学研究所）
• Tianjin Medical University General Hospital（天津医科大学总医院）
• Lung Cancer Institute, Tianjin Medical University General Hospital（天津医科大学总医院肺癌研究所）

机构由 AI 辅助整理，请以论文原文为准。