arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.08172stat.AP
收藏

从文献中学习:整合大语言模型和贝叶斯分层建模用于肿瘤试验设计

Learning from Literature: Integrating LLMs and Bayesian Hierarchical Modeling for Oncology Trial Design

Yale Cancer Center, Yale School of Medicine(耶鲁癌症中心,耶鲁医学院);Pfizer Inc(辉瑞公司);Public Health Sciences Division, Fred Hutchinson Cancer Center(弗雷德·哈钦森癌症中心公共卫生科学部)

Guannan Gong, Satrajit Roychoudhury, Allison Meisner, Lajos Pusztai, Sarah B Goldberg, Wei Wei

AI总结:

LEAD-ONC通过整合大语言模型和贝叶斯分层建模,利用文献数据优化肿瘤试验设计,预测生存差异和治疗益处。

摘要:

设计现代肿瘤试验需要综合先前研究的证据以指导假设生成和样本量确定。基于不完整或不精确的摘要设计的试验可能导致假定错误和低统计效力的试验,导致假阳性或假阴性结论。为了解决这一挑战,我们开发了LEAD-ONC(文献到证据用于肿瘤分析和设计),这是一个辅助人工智能的框架,将发表的临床试验报告转化为定量、设计相关的证据。给定经过专家筛选的试验出版物,这些出版物符合预设的资格标准,LEAD-ONC使用大型语言模型提取基线特征,并从Kaplan-Meier曲线中重建个体患者数据,然后使用贝叶斯分层建模生成预设目标试验人群的预测生存分布。我们通过五个评估PD-1或PD-L1抑制剂与或无CTLA-4阻断的III期试验进行演示,这些试验针对一线非小细胞肺癌。基于基线特征的聚类识别出三个具有临床意义的人群,这些人群由组织学类型定义。对于在混合组织学人群中的前瞻性随机试验,比较单药与双药免疫检查点抑制,LEAD-ONC预测了中位总体生存期差异为2.8个月(95%可信区间-2.0至7.6),并估计至少有3个月益处的概率约为0.45。由于LEAD-ONC仍在积极开发中,这些结果旨在作为框架潜在支持证据驱动肿瘤试验设计的初步演示,而不是确定性的临床结论。

英文摘要:

Designing modern oncology trials requires synthesizing evidence from prior studies to inform hypothesis generation and sample size determination. Trial designs based on incomplete or imprecise summaries can lead to misspecified hypotheses and underpowered studies, resulting in false positive or negative conclusions. To address this challenge, we developed LEAD-ONC (Literature to Evidence for Analytics and Design in Oncology), an AI-assisted framework that transforms published clinical trial reports into quantitative, design-relevant evidence. Given expert-curated trial publications that meet prespecified eligibility criteria, LEAD-ONC uses large language models to extract baseline characteristics and reconstruct individual patient data from Kaplan-Meier curves, followed by Bayesian hierarchical modeling to generate predictive survival distributions for a prespecified target trial population. We demonstrate the framework using five phase III trials in first-line non-small-cell lung cancer evaluating PD-1 or PD-L1 inhibitors with or without CTLA-4 blockade. Clustering based on baseline characteristics identified three clinically interpretable populations defined by histology. For a prospective randomized trial in the mixed-histology population comparing mono versus dual immune checkpoint inhibition, LEAD-ONC projected a modest median overall survival difference of 2.8 months (95 percent credible interval -2.0 to 7.6) and an estimated probability of at least a 3-month benefit of approximately 0.45. As LEAD-ONC remains under active development, these results are intended as preliminary demonstrations of the frameworks potential to support evidence-driven oncology trial design rather than definitive clinical conclusions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑