Abstract

Estimating treatment effects for survival outcomes in the high-dimensional setting is critical for many biomedical applications and any application with censored observations. This article establishes an “orthogonal” score for learning treatment effects, using observational data with a potentially large number of confounders. The estimator allows for root-n, asymptotically valid confidence intervals, despite the bias induced by the regularization. Moreover, we develop a novel hazard difference (HDi), estimator. We establish rate double robustness through the cross-fitting formulation. Numerical experiments illustrate the finite sample performance, where we observe that the cross-fitted HDi estimator has the best performance. We study the radical prostatectomy’s effect on conservative prostate cancer management through the SEER-Medicare linked data. Last, we provide an extension to machine learning both approaches and heterogeneous treatment effects. Supplementary materials for this article are available online.

摘要

在高维环境中估计治疗对生存结果的影响对于许多生物医学应用和任何具有删失观察的应用至关重要。本文使用具有潜在大量混杂因素的观察数据，为学习治疗效果建立了一个“正交”分数。估计器允许根n，渐近有效的置信区间，尽管由正则化引起的偏差。此外，我们开发了一种新的风险差异 (HDi) 估计器。我们通过交叉拟合公式建立速率双鲁棒性。数值实验说明了有限样本性能，我们观察到交叉拟合 HDi 估计器具有最佳性能。我们通过 SEER-Medicare 关联数据研究根治性前列腺切除术对保守性前列腺癌管理的影响。最后，我们提供了机器学习方法和异构处理效果的扩展。本文的补充材料可在线获取。