AI 看似相似建模用于临床试验 site 选择，近半数 site 招募失败
Clinical Trial Site Selection and AI: Look-Alike Modeling Across Real-World Data and Care Delivery Signals
药企选临床试验机构近一半招不到人，这篇讲怎么用真实世界数据加 AI 建模来挑更靠谱的 site。
Tufts CSDD 对 151 项 II/III 期全球试验中近 16000 个研究 site 的分析显示，近一半选中的 site 未招募到患者或招募不足。Definitive Healthcare 的 Aaron Cohen 提出用 AI 看似相似建模，将真实世界数据与诊疗行为信号结合来改善 site 选择。该方法把 site 选择视为采样问题，用数据特征匹配更可能完成入组的机构。
Clinical Trial Site Selection and AI: Look-Alike Modeling Across Real-World Data and Care Delivery Signals
Site selection and enrollment failures are persistent challenges for life sciences organizations. A Tufts Center for the Study of Drug Development analysis of nearly 16,000 investigative sites across 151 Phase II and III global trials found that nearly half of all selected sites either failed to enroll a patient or under-enrolled.1 Site-selection decisions commonly draw ... Read More
