Bayesian meta-analytical methods to incorporate multiple surrogate endpoints in drug development process.
Bayesian meta-analytical methods to incorporate multiple surrogate endpoints in drug development process.
复制标题
DOI：
10.1002/sim.6776
复制
发表时间：
2016-03-30
影响因子：
2
通讯作者：
Abrams KR
中科院分区：
文献类型：
--
作者：
Bujkiewicz S;Thompson JR;Riley RD;Abrams KR
已经提出了许多旨在评估替代终点的元分析方法。双变量元分析方法可用于从替代终点测量的治疗效果估计预测最终结局的治疗效果，同时考虑到替代终点效果估计的不确定性。在本文中，开发了多变量模型的扩展，旨在包括多个代理端点，从而在进行预测时减少不确定性。在这个贝叶斯多元元分析框架中，研究之间的可变性是在正态单变量分布的乘积的公式中建模的。这个公式对于包含多个代理端点特别方便，并且对于结果建模特别灵活，这些结果可以是最终结果的代理端点，也可以是彼此之间的代理端点。提出了两种模型，第一种模型使用非结构化的研究间协方差矩阵，假设治疗对所有结果的影响是相关的；第二种模型使用结构化的研究间协方差矩阵，假设治疗对某些结果的影响是条件独立的。虽然这两个模型是为研究水平的汇总数据而开发的，但通过使用Prentice标准（从个体患者数据中获得）来考虑个体水平的关联，以告知模型中的研究内部相关性。以复发缓解型多发性硬化症为例研究了建模技术，其中残疾恶化是最终结果，而复发率和MRI病变是残疾进展的潜在替代指标。©2015作者。医学统计由约翰威利和儿子有限公司出版。
A number of meta‐analytical methods have been proposed that aim to evaluate surrogate endpoints. Bivariate meta‐analytical methods can be used to predict the treatment effect for the final outcome from the treatment effect estimate measured on the surrogate endpoint while taking into account the uncertainty around the effect estimate for the surrogate endpoint. In this paper, extensions to multivariate models are developed aiming to include multiple surrogate endpoints with the potential benefit of reducing the uncertainty when making predictions. In this Bayesian multivariate meta‐analytic framework, the between‐study variability is modelled in a formulation of a product of normal univariate distributions. This formulation is particularly convenient for including multiple surrogate endpoints and flexible for modelling the outcomes which can be surrogate endpoints to the final outcome and potentially to one another. Two models are proposed, first, using an unstructured between‐study covariance matrix by assuming the treatment effects on all outcomes are correlated and second, using a structured between‐study covariance matrix by assuming treatment effects on some of the outcomes are conditionally independent. While the two models are developed for the summary data on a study level, the individual‐level association is taken into account by the use of the Prentice's criteria (obtained from individual patient data) to inform the within study correlations in the models. The modelling techniques are investigated using an example in relapsing remitting multiple sclerosis where the disability worsening is the final outcome, while relapse rate and MRI lesions are potential surrogates to the disability progression. © 2015 The Authors. Statistics in Medicine Published by John Wiley & Sons Ltd.