Q-learning for estimating optimal dynamic treatment rules from observational data.

Q-learning for estimating optimal dynamic treatment rules from observational data.
复制标题

DOI:
10.1002/cjs.11162
复制
发表时间:
2012-12-01
影响因子:
0.6
通讯作者:
Kramer, Michael S.
Kramer, Michael S.
中科院分区:
数学4区
文献类型:
--
作者:
Moodie, Erica E. M.;Chakraborty, Bibhas;Kramer, Michael S.

文献摘要

参考文献

被引文献

相似文献

动态治疗方案(DTR)领域旨在对临床实践中的适应性、多阶段决策做出推断。DTR是一组决策规则,每个治疗间隔一个,其中每个决策是治疗和返回推荐治疗的协变量历史的函数。Q-学习是强化学习文献中的一种流行的方法,最近被应用于估计动态反馈。虽然原则上Q学习可以用于随机化和观察性数据,但到目前为止,文献中的重点仅限于随机治疗设置。使用直接调整和各种倾向评分方法,我们将该方法扩展到包括测量的混杂协变量。这些方法是在包括非常规情况在内的各种情况下进行检查的。我们以促进母乳喂养干预试验的数据为基础,说明了母乳喂养对词汇测试的影响的方法。
The area of dynamic treatment regimes (DTR) aims to make inference about adaptive, multistage decision-making in clinical practice. A DTR is a set of decision rules, one per interval of treatment, where each decision is a function of treatment and covariate history that returns a recommended treatment. Q-learning is a popular method from the reinforcement learning literature that has recently been applied to estimate DTRs. While, in principle, Q-learning can be used for both randomized and observational data, the focus in the literature thus far has been exclusively on the randomized treatment setting. We extend the method to incorporate measured confounding covariates, using direct adjustment and a variety of propensity score approaches. The methods are examined under various settings including non-regular scenarios. We illustrate the methods in examining the effect of breastfeeding on vocabulary testing, based on data from the Promotion of Breastfeeding Intervention Trial.
DOI: 10.1016/j.jpeds.2004.06.069
发表时间: 2004-11-01
影响因子: 5.1
作者:
Kramer, MS;Guo, T;Dewey, K
通讯作者: Dewey, K
DOI: 10.1111/j.1467-9469.2009.00661.x
发表时间: 2009-09-22
期刊: Scandinavian journal of statistics, theory and applications
影响因子: --
作者:
Moodie EE;Richardson TS
通讯作者: Richardson TS
DOI: 10.1093/ajcn/78.2.291
发表时间: 2003-08-01
影响因子: 7.1
作者:
Kramer, MS;Guo, T;Bogdanovich, N
通讯作者: Bogdanovich, N
DOI: 10.1001/jama.285.4.413
发表时间: 2001-01-24
影响因子: 120.7
作者:
Kramer, MS;Chalmers, B;Helsing, E
通讯作者: Helsing, E
DOI: 10.2202/1557-4679.1204
发表时间: 2010-01-01
影响因子: 1.2
作者:
Arjas, Elja;Saarela, Olli
通讯作者: Saarela, Olli