面向精准医学的风险控制决策树与随机森林
提出风险控制个体化治疗规则(rcITR)方法,在最大化获益的同时将风险控制在预设阈值内。开发了风险控制决策树(rcDT)及其扩展风险控制随机森林(rcRF),并通过模拟研究和DURABLE糖尿病试验数据分析验证性能,同时提出三种变量重要性度量以辅助临床决策。
要点
- rcITR在最大化获益的同时将风险控制在预设阈值内。
- rcDT易于解释,rcRF为其自然扩展且建模稳健。
- 方法适用于随机对照试验或观察性研究数据。
核心结论
- 提出rcDT与rcRF两种方法识别风险控制个体化治疗规则,在最大化获益的同时将风险控制在预设阈值内。
研究设计与样本
- 开发惩罚递归划分算法优化无约束惩罚价值函数,最终规则为风险控制决策树(rcDT),并自然扩展为风险控制随机森林(rcRF)。
- 通过广泛模拟研究评估方法性能,并分析比较两种治疗方案的DURABLE糖尿病试验数据。
- 提供R包实现所提方法(https://github.com/kdoub5ha/rcITR)。
主要发现
- 模拟研究证明rcRF建模具有稳健性。
- 提出三种变量重要性度量以进一步指导临床决策。
- rcDT和rcRF均可应用于随机对照试验或观察性研究数据。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
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).
引用
- Doubleday K, Zhou J, Zhou H, et al. Risk controlled decision trees and random forests for precision Medicine. Stat Med. 2021. PMID: 34786731. doi:10.1002/sim.9253
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。