Lok Judith J, Hughes Michael D
Department of Biostatistics, Harvard T.H. Chan School of Public Health, Huntington Avenue, Boston, MA, 65502115, U.S.A.
Stat Med. 2016 Jun 15;35(13):2183-94. doi: 10.1002/sim.6852. Epub 2016 Jan 14.
We propose a prediction model for the cumulative incidence functions of competing risks, based on a logit link. Because of a concern about censoring potentially depending on time-varying covariates in our motivating human immunodeficiency virus (HIV) application, we describe an approach for estimating the parameters in the prediction models using inverse probability of censoring weighting under a missingness at random assumption. We then illustrate the application of this methodology to identify predictors of the competing outcomes of virologic failure, an efficacy outcome, and treatment limiting adverse event, a safety outcome, among human immunodeficiency virus-infected patients first starting antiretroviral treatment. Copyright © 2016 John Wiley & Sons, Ltd.
我们基于logit连接提出了一种用于竞争风险累积发病率函数的预测模型。由于在我们具有启发性的人类免疫缺陷病毒（HIV）应用中，担心删失可能取决于随时间变化的协变量，我们描述了一种在随机缺失假设下使用删失加权逆概率来估计预测模型中参数的方法。然后，我们举例说明了该方法在确定首次开始抗逆转录病毒治疗的人类免疫缺陷病毒感染患者中病毒学失败（一种疗效结果）和治疗限制性不良事件（一种安全性结果）这两种竞争结局的预测因素方面的应用。版权所有© 2016约翰·威利父子有限公司。
