Henderson Robin, Diggle Peter, Dobson Angela
Medical Statistics Unit, Lancaster University, LA1 4YF, UK.
Biostatistics. 2002 Mar;3(1):33-50. doi: 10.1093/biostatistics/3.1.33.
Methods for the combined analysis of survival time and longitudinal biomarker data have been developed in recent years, with most emphasis on modelling and estimation. This paper focuses on the use of longitudinal marker trajectories as individual-level surrogates for survival. A score test for association which requires only standard methods for implementation is derived for the initial identification of candidate biomarkers. Methods for assessing efficacy of markers are discussed and a measure contrasting conditional and marginal distributions is proposed. An application using prothrombin index as biomarker for survival of liver cirrhosis patients is included.
近年来已开发出用于生存时间和纵向生物标志物数据联合分析的方法，其中大部分重点在于建模和估计。本文重点关注使用纵向标志物轨迹作为生存的个体水平替代指标。推导了一种关联得分检验，该检验仅需标准方法即可实施，用于初步识别候选生物标志物。讨论了评估标志物疗效的方法，并提出了一种对比条件分布和边际分布的度量。文中包含了一项将凝血酶原指数用作肝硬化患者生存生物标志物的应用。
