发表机构
Arizona State University; Mayo Clinic（亚利桑那州立大学; 梅奥诊所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出FD-SCoPE框架，结合可执行查询与专家反馈，使语言模型能回答证据表内外的临床问题，并显著提升检索与推导性能。
AI 中文摘要
系统综述将临床试验浓缩为证据表，但临床医生只能通过数据库查询来检索这些表格，而许多问题涉及表格未记录的属性，如药物的靶点类别或统一终点。在此，我们引入FD-SCoPE，一个语言模型框架，它能回答这两类问题，并展示每个答案背后的查询、所选试验和推导规则，且能从专家纠正中学习。在包含159条免疫检查点抑制剂试验记录的肿瘤学证据表上，FD-SCoPE完成了全部140项临床医生式任务（替代方案，90.7-97.9%）。对于需要推导属性的问题，它以89.8%的阳性预测值检索了99.3%的相关试验记录，并优于四种替代方法（推导值F1为77.7%，对比64.8-73.4%）。基于参考答案模拟的299个问题的纠正，将1201个未见问题的F1从77.9%提升至84.9%。语言模型与可执行查询、验证程序及专家反馈相结合，可为临床医生提供对试验证据的可审计访问。
英文摘要
Systematic reviews condense clinical trials into evidence tables, yet clinicians can interrogate these tables only through database queries, and many questions concern attributes that the table does not record, such as a drug's target class or a harmonised endpoint. Here we introduce FD-SCoPE, a language-model framework that answers both kinds of question, exposes the query, the selected trials and the derivation rule behind every answer, and learns from expert corrections. On an oncology evidence table of 159 immune checkpoint inhibitor trial records, FD-SCoPE completed all 140 clinician-style tasks (alternatives, 90.7-97.9%). For questions needing derived attributes it retrieved 99.3% of relevant trial records at a positive predictive value of 89.8% and outperformed four alternative approaches (derived-value F1 77.7% versus 64.8-73.4%). Corrections on 299 questions, simulated from reference answers, raised F1 on 1,201 unseen questions from 77.9% to 84.9%. Language models coupled with executable queries, verified programs and expert feedback can give clinicians auditable access to trial evidence.
