arXiv：cs.AI· Manan Roy Choudhury, Suparno Roy Chowdhury, Swastik Sahoo, Muhammad Ali Khan, Kaneez Zahra Rubab Khakwani, Mohamad Bassam Sonbol, Irbaz Bin Riaz, Vivek Gupta·· 5 小时前AI 评分41
FD-SCoPE：用可验证、反馈驱动的语言模型回答临床医生对试验证据表的提问
Answering clinicians' questions over trial evidence tables with verifiable, feedback-driven language models
AI 导读
FD-SCoPE 是一个语言模型框架，可回答临床医生对系统综述证据表的提问，并展示查询、所选试验与推导规则，还能从专家纠正中学习。
正文
Abstract: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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.02576 [cs.AI] |
| (or arXiv:2610.02576v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02576 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Suparno Roy Chowdhury [view email]
[v1]
Thu, 1 Oct 2026 23:12:22 UTC (2,876 KB)
来源：arXiv：cs.AI · arxiv.org