ISPOR 发布生成式人工智能用于系统文献综述的良好实践报告
Generative Artificial Intelligence for Systematic Literature Reviews: A Good Practices Report of an ISPOR Special Task Force
作者：Rachael L. Fleurence、Riaz Qureshi、Rakesh Aggarwal、Jiang Bian、Dalia Dawoud、Diana Delnoij、Ruth R. Faden、Sven Klijn、Raphael Sonabend、Jagpreet Chhatwal、Turgay Ayer、Ran Balicer、Saskia Cheyne、Rebecca Trowman
单位：Center for Health Technology Assessment, Mass General Brigham, Harvard Medical School, Boston, MA, United States; Apodeixis Strategies LLC, Bethesda, MD, United States.；University of Colorado Anschutz Medical Campus, Aurora, CO, United States.；Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow, India.；Regenstrief Institute, Indianapolis, IN, United States; Indiana University School of Medicine, Indianapolis, IN, United States.；Cytel Inc, London, United Kingdom; Cairo University, Faculty of Pharmacy, Cairo, Egypt.；Zorginstituut Nederland (ZIN), Diemen, Netherlands; Erasmus School of Health Policy & Management, Erasmus University Rotterdam to Zorginstituut, Netherlands.；Johns Hopkins Berman Institute of Bioethics, Baltimore, MD, United States.；Bristol Myers Squibb, London, United Kingdom.
摘要
ISPOR 特别工作组于 2026 年 9 月 19 日在线发表《生成式人工智能用于系统文献综述：良好实践报告》，针对药物经济学与 outcomes 研究中文献综述流程引入生成式 AI 的技术应用提供规范性指导，涵盖方法学框架、质量控制及伦理考量等关键维度。
AI 主编 · 推荐理由推荐理由
系统文献综述是 HTA 和药物经济学评价的核心方法，本报告为行业提供了 AI 辅助综述的实操框架，建议在开展相关研究时参照其规范，尤其是合规审查与透明度披露部分。