Hong Hwanhee, Fu Haoda, Price Karen L, Carlin Bradley P
Department of Mental Health, Johns Hopkins Bloomberg School of Public Health, Baltimore, MD, 21205, U.S.A.
Eli Lilly and Company, Indianapolis, IN, U.S.A.
Stat Med. 2015 Sep 10;34(20):2794-819. doi: 10.1002/sim.6519. Epub 2015 Apr 30.
Availability of individual patient-level data (IPD) broadens the scope of network meta-analysis (NMA) and enables us to incorporate patient-level information. Although IPD is a potential gold mine in biomedical areas, methodological development has been slow owing to limited access to such data. In this paper, we propose a Bayesian IPD NMA modeling framework for multiple continuous outcomes under both contrast-based and arm-based parameterizations. We incorporate individual covariate-by-treatment interactions to facilitate personalized decision making. Furthermore, we can find subpopulations performing well with a certain drug in terms of predictive outcomes. We also impute missing individual covariates via an MCMC algorithm. We illustrate this approach using diabetes data that include continuous bivariate efficacy outcomes and three baseline covariates and show its practical implications. Finally, we close with a discussion of our results, a review of computational challenges, and a brief description of areas for future research.
个体患者层面数据（IPD）的可用性拓宽了网络荟萃分析（NMA）的范围，并使我们能够纳入患者层面的信息。尽管IPD在生物医学领域是一座潜在的金矿，但由于获取此类数据的机会有限，方法学的发展一直较为缓慢。在本文中，我们针对基于对比和基于组臂的参数化下的多个连续结局，提出了一种贝叶斯IPD NMA建模框架。我们纳入个体协变量与治疗的交互作用，以促进个性化决策。此外，我们可以找到在预测结局方面对某种药物反应良好的亚组人群。我们还通过MCMC算法对缺失的个体协变量进行插补。我们使用包含连续双变量疗效结局和三个基线协变量的糖尿病数据来说明这种方法，并展示其实际意义。最后，我们通过讨论结果、回顾计算挑战以及简要描述未来研究领域来结束本文。
