arXiv 2412.019552024-12-04cs.CLcs.AI

利用大型语言模型改进癌症临床试验教育材料

The use of large language models to enhance cancer clinical trial educational materials

Massachusetts Institute of Technology（麻省理工学院）；Technical University of Munich（慕尼黑工业大学）；Mass General Brigham（麻省总医院布里格姆医疗系统）；Harvard Medical School（哈佛医学院）；Brigham and Women’s Hospital（布莱根妇女医院）；Dana-Farber Cancer Institute（丹娜-法伯癌症研究所）；Centaur Labs（半人马实验室）；Digidence；Loyola University Chicago（芝加哥洛约拉大学）

Mingye Gao, Aman Varshney, Shan Chen, Vikram Goddla, Jack Gallifant, Patrick Doyle, Claire Novack, Maeve Dillon-Martin, Teresia Perkins, Xinrong Correia, Erik D… 展开作者

Mingye Gao, Aman Varshney, Shan Chen, Vikram Goddla, Jack Gallifant, Patrick Doyle, Claire Novack, Maeve Dillon-Martin, Teresia Perkins, Xinrong Correia, Erik Duhaime, Howard Isenstein, Elad Sharon, Lisa Soleymani Lehmann, David Kozono, Brian Anthony, Dmitriy Dligach, Danielle S. Bitterman

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文评估 GPT4 基于临床试验知情同意书零样本生成摘要、单样本生成选择题的效果，证明其可辅助患者教育，但仍需人在回路审核以防范幻觉。

摘要：

癌症临床试验常因缺乏面向参与者的信息和教育资源而在招募与参与方面面临挑战。本研究考察了大型语言模型（LLM），特别是 GPT4，在根据临床试验知情同意书生成患者友好型教育内容方面的潜力。研究使用来自 ClinicalTrials.gov 的数据，采用 zero-shot learning（零样本学习）生成试验摘要，并采用 one-shot learning（单样本学习）开发多项选择题，随后通过患者调查和众包标注评估其有效性。结果显示，GPT4 生成的摘要兼具可读性和全面性，可能增进患者对临床试验的理解和兴趣。多项选择题表现出较高的准确性，并与众包标注者具有较高一致性。对于两类资源，研究均发现存在幻觉，因此需要持续的人工监督。研究结果表明，LLM“开箱即用”即可支持临床试验教育材料生成，只需极少的试验特定工程调整；但实际实施仍需采用 human-in-the-loop（人在回路）方式，以避免错误信息风险。

英文摘要：

Cancer clinical trials often face challenges in recruitment and engagement due to a lack of participant-facing informational and educational resources. This study investigated the potential of Large Language Models (LLMs), specifically GPT4, in generating patient-friendly educational content from clinical trial informed consent forms. Using data from ClinicalTrials.gov, we employed zero-shot learning for creating trial summaries and one-shot learning for developing multiple-choice questions, evaluating their effectiveness through patient surveys and crowdsourced annotation. Results showed that GPT4-generated summaries were both readable and comprehensive, and may improve patients' understanding and interest in clinical trials. The multiple-choice questions demonstrated high accuracy and agreement with crowdsourced annotators. For both resource types, hallucinations were identified that require ongoing human oversight. The findings demonstrate the potential of LLMs "out-of-the-box" to support the generation of clinical trial education materials with minimal trial-specific engineering, but implementation with a human-in-the-loop is still needed to avoid misinformation risks.

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。