Tag
该论文提出 FD-SCoPE 框架，利用可验证、可反馈的语言模型与可执行查询，回答临床医生对临床试验证据表格的提问，包括无法直接通过数据库查询得出的派生属性问题，并在肿瘤学免疫检查点抑制剂试验数据上验证其可审计性与有效性。
This paper introduces PRISMA-LLM, an empirically grounded framework for reporting AI-assisted systematic reviews, addressing inconsistencies in how LLMs and AI software are documented in review workflows.
BioInsight is a multi-agent system that transforms static biomedical reports into interactive, evidence-centered interfaces by organizing disease-specific evidence through structured artifacts and deterministic citation normalization.
MEDSYN is a multilingual multimodal benchmark for evaluating MLLMs on complex clinical cases with up to 7 distinct visual evidence types per case. The study reveals that while frontier models match human experts on differential diagnosis generation, all MLLMs show significant gaps in final diagnosis selection due to poor synthesis of heterogeneous clinical evidence.