Risk controlled decision trees and random forests for precision Medicine.
Risk controlled decision trees and random forests for precision Medicine.
复制标题
DOI：
10.1002/sim.9253
复制
发表时间：
2022-02-20
影响因子：
2
通讯作者：
Fu H
中科院分区：
文献类型：
--
作者：
Doubleday K;Zhou J;Zhou H;Fu H
生成个体化治疗规则(ITR)的统计方法通常侧重于最大化预期收益，但这些规则可能会使患者面临额外的风险。例如，积极使用胰岛素疗法治疗2型糖尿病(T2D)可能会导致ITR，它可以控制血糖水平，但会增加低血糖的发生率，从而降低ITR的吸引力。这项工作提出了两种方法来识别风险受控的ITR(RcITR)，这是一类在将风险控制在预先指定的阈值下实现收益最大化的ITR。提出了一种新的惩罚递归划分算法，该算法优化了无约束的惩罚值函数。最后一条规则是易于解释的风险控制决策树(RcDT)。提出了RcDT模型的自然扩展--风险控制随机森林(RcRF)。仿真研究证明了RCRF模型的稳健性。为了进一步指导临床决策，本文提出了三个变量重要性度量。RcDT和rcRF程序都可以应用于来自随机对照试验或观察性研究的数据。一个广泛的模拟研究询问了所提出的方法的性能。此外，还提供了对两种疗法进行比较的耐久糖尿病试验的数据分析。R包实现所建议的方法(https://github.com/kdoub5ha/rcITR).
Statistical methods generating individualized treatment rules (ITRs) often focus on maximizing expected benefit, but these rules may expose patients to excess risk. For instance, aggressive treatment of type 2 diabetes (T2D) with insulin therapies may result in an ITR which controls blood glucose levels but increases rates of hypoglycemia, diminishing the appeal of the ITR. This work proposes two methods to identify risk-controlled ITRs (rcITR), a class of ITR which maximizes a benefit while controlling risk at a prespecified threshold. A novel penalized recursive partitioning algorithm is developed which optimizes an unconstrained, penalized value function. The final rule is a risk-controlled decision tree (rcDT) that is easily interpretable. A natural extension of the rcDT model, risk controlled random forests (rcRF), is also proposed. Simulation studies demonstrate the robustness of rcRF modeling. Three variable importance measures are proposed to further guide clinical decision-making. Both rcDT and rcRF procedures can be applied to data from randomized controlled trials or observational studies. An extensive simulation study interrogates the performance of the proposed methods. A data analysis of the DURABLE diabetes trial in which two therapeutics were compared is additionally presented. An R package implements the proposed methods (https://github.com/kdoub5ha/rcITR).
登录
查看更多内容
影响因子：
2
作者：
Foster, Jared C.;Taylor, Jeremy M. G.;Ruberg, Stephen J.
通讯作者：
Ruberg, Stephen J.
影响因子：
4.5
作者：
Qian M;Murphy SA
通讯作者：
Murphy SA
影响因子：
3.7
作者：
MORGAN, JN;SONQUIST, JA
通讯作者：
SONQUIST, JA
影响因子：
2.7
作者：
Zhao YQ;Zeng D;Laber EB;Song R;Yuan M;Kosorok MR
通讯作者：
Kosorok MR
DOI：
10.1080/01621459.2012.695674
发表时间：
2012-09-01
影响因子：
3.7
作者：
Zhao Y;Zeng D;Rush AJ;Kosorok MR
通讯作者：
Kosorok MR