Causal inference in survival analysis using longitudinal observational data: Sequential trials and marginal structural models.
Causal inference in survival analysis using longitudinal observational data: Sequential trials and marginal structural models.
复制标题
使用纵向观察数据进行生存分析的因果推断：序贯试验和边际结构模型。
DOI：
10.1002/sim.9718
复制
发表时间：
2023-06-15
影响因子：
2
通讯作者：
Vansteelandt S
中科院分区：
文献类型：
--
作者：
Keogh RH;Gran JM;Seaman SR;Davies G;Vansteelandt S
患者的纵向观察数据可用于研究随时间变化的治疗对至事件发生时间结局的因果影响。已经开发了几种方法，通过控制通常发生的时间依赖性混杂来估计这种影响。最常用的是边际结构模型的逆概率加权估计（MSM-IPTW）。另一种选择是序贯试验方法，它越来越受欢迎，涉及从新的时间起源创建一系列“试验”，并比较治疗启动者和非启动者。当个体在每次“试验”（启动者或非启动者）开始时偏离其治疗分配时，对其进行删失，这使用删失权重的逆概率进行解释。该分析使用跨试验合并的数据。我们表明，序贯试验方法可以估计一个特定的MSM的参数。我们关注的因果被估量是“始终治疗”与“从不治疗”的持续治疗策略之间的边际风险差异。我们比较了序贯试验方法和MSM-IPTW估计这个估计，讨论他们的假设，以及如何使用不同的数据。这两种方法的性能进行了比较，在模拟研究。序贯试验方法往往涉及比MSM-IPTW更少的极端权重，导致在大多数随访时间估计边际风险差异的效率更高，但在某些情况下，这可能在稍后的时间点逆转，并依赖于建模假设。我们将这些方法应用于英国囊性纤维化登记处的纵向观察数据，以评估α-链脱氧核糖核酸酶对生存率的影响。
Longitudinal observational data on patients can be used to investigate causal effects of time-varying treatments on time-to-event outcomes. Several methods have been developed for estimating such effects by controlling for the time-dependent confounding that typically occurs. The most commonly used is inverse probability weighted estimation of marginal structural models (MSM-IPTW). An alternative, the sequential trials approach, is increasingly popular, and involves creating a sequence of ‘trials’ from new time origins and comparing treatment initiators and non-initiators. Individuals are censored when they deviate from their treatment assignment at the start of each ‘trial’ (initiator or non-initiator), which is accounted for using inverse probability of censoring weights. The analysis uses data combined across trials. We show that the sequential trials approach can estimate the parameters of a particular MSM. The causal estimand that we focus on is the marginal risk difference between the sustained treatment strategies of ‘always treat’ versus ‘never treat’. We compare how the sequential trials approach and MSM-IPTW estimate this estimand, discuss their assumptions, and how data are used differently. The performance of the two approaches is compared in a simulation study. The sequential trials approach, which tends to involve less extreme weights than MSM-IPTW, results in greater efficiency for estimating the marginal risk difference at most follow-up times, but this can, in certain scenarios, be reversed at later time points and relies on modelling assumptions. We apply the methods to longitudinal observational data from the UK Cystic Fibrosis Registry to estimate the effect of dornase alfa on survival.
登录
查看更多内容
影响因子：
2.3
作者：
Danaei, Goodarz;Garcia Rodriguez, Luis A.;Hernan, Miguel A.
通讯作者：
Hernan, Miguel A.
影响因子：
13.6
作者：
Garcia-Albeniz, Xabier;Hsu, John;Hernan, Miguel A.
通讯作者：
Hernan, Miguel A.
影响因子：
5
作者：
Hernan, Miguel A.;Robins, James M.
通讯作者：
Robins, James M.
影响因子：
7.2
作者：
Hernan, Miguel A.;Sauer, Brian C.;Shrier, Ian
通讯作者：
Shrier, Ian
影响因子：
5.4
作者：
Hernan, Miguel A.;Alonso, Alvaro;Robins, James M.
通讯作者：
Robins, James M.