Random forests of interaction trees for estimating individualized treatment effects in randomized trials.

Random forests of interaction trees for estimating individualized treatment effects in randomized trials.
复制标题

DOI:
10.1002/sim.7660
复制
发表时间:
2018-07-30
影响因子:
2
通讯作者:
Levine RA
Levine RA
中科院分区:
医学3区
文献类型:
--
作者:
Su X;Peña AT;Liu L;Levine RA

文献摘要

参考文献

被引文献

相似文献

在推进精准医学方面,评估异质治疗效果越来越受到人们的关注。个体化治疗效果(ITE)在这一努力中发挥着关键作用。针对从随机试验中收集到的实验数据,我们提出了一种基于交互作用树的ITE估计方法,称为交互作用树的随机森林(RFIT)。为此,我们提出了一种平滑S型代理(SSS)方法,作为贪婪搜索的替代方法,以加快树的构建。在估计ITE方面,RFIT优于‘分离回归’方法。此外,还利用无穷小刀刀法得到了通过RFIT估计的ITE的标准误差。我们通过模拟和分析针灸头痛试验的数据来评估和说明RFIT的使用。
Assessing heterogeneous treatment effects is a growing interest in advancing precision medicine. Individualized treatment effects (ITE) play a critical role in such an endeavor. Concerning experimental data collected from randomized trials, we put forward a method, termed random forests of interaction trees (RFIT), for estimating ITE on the basis of interaction trees. To this end, we propose a smooth sigmoid surrogate (SSS) method, as an alternative to greedy search, to speed up tree construction. RFIT outperforms the ‘separate regression’ approach in estimating ITE. Furthermore, standard errors for the estimated ITE via RFIT are obtained with the infinitesimal jackknife method. We assess and illustrate the use of RFIT via both simulation and the analysis of data from an acupuncture headache trial.
DOI: 10.1002/sim.4322
发表时间: 2011-10-30
影响因子: 2
作者:
Foster, Jared C.;Taylor, Jeremy M. G.;Ruberg, Stephen J.
通讯作者: Ruberg, Stephen J.
DOI: 10.1080/01621459.2013.823775
发表时间: 2014-07-01
影响因子: 3.7
作者:
Efron B
通讯作者: Efron B
DOI: 10.1200/jco.2015.63.3651
发表时间: 2015-11-20
影响因子: 45.3
作者:
Ballman, Karla V.
通讯作者: Ballman, Karla V.
DOI: 10.1093/bioinformatics/btr597
发表时间: 2012-01-01
期刊: BIOINFORMATICS
影响因子: 5.8
作者:
Stekhoven, Daniel J.;Buehlmann, Peter
通讯作者: Buehlmann, Peter
DOI: 10.2307/2290325
发表时间: 1993-06-01
影响因子: 3.7
作者:
LEBLANC, M;CROWLEY, J
通讯作者: CROWLEY, J