Population and Public Health Sciences, Keck School of Medicine, University of Southern California, Los Angeles, California, USA.
Population Health Sciences, University of Utah School of Medicine, Salt Lake City, Utah, USA.
Stat Med. 2023 Nov 20;42(26):4738-4762. doi: 10.1002/sim.9886. Epub 2023 Sep 3.
Rigorous evaluation of surrogate endpoints is performed in a trial-level analysis in which the strength of the association between treatment effects on the clinical and surrogate endpoints is quantified across a collection of previously conducted trials. To reduce bias in measures of the performance of the surrogate, the statistical model must account for the sampling error in each trial's estimated treatment effects and their potential correlation. Unfortunately, these within-study correlations can be difficult to obtain, especially for meta-analysis of published trial results where individual patient data is not available. As such, these terms are frequently partially or completely missing in the analysis. We show that improper handling of these missing terms can meaningfully alter the perceived quality of the surrogate and we introduce novel strategies to handle the missingness.
在试验层面的分析中，对替代终点进行严格评估，通过对一系列已开展试验的综合分析，量化治疗效果在临床终点和替代终点之间的关联强度。为了降低替代终点评估的偏倚，统计模型必须考虑到每个试验中估计的治疗效果的抽样误差及其潜在的相关性。不幸的是，这些研究内相关性很难获得，尤其是在分析已发表的试验结果的荟萃分析中，因为无法获得个体患者的数据。因此，在分析中这些术语经常部分或完全缺失。我们表明，对这些缺失术语的不当处理会显著改变对替代终点的质量的感知，我们引入了新的策略来处理缺失值。
