Efficient estimation of weighted cumulative treatment effects by double/debiased machine learning

TL;DR

This paper introduces a novel class of double/debiased machine learning estimators for weighted causal effects in time-to-event data, addressing issues of model misspecification and poor overlap in observational studies.

Contribution

It develops and proves the consistency and efficiency of these estimators, extending machine learning methods to weighted treatment effects with time-to-event outcomes.

Findings

Estimators perform well with nonparametric nuisance models.

They are robust to model misspecification.

Application to real-world data demonstrates practical utility.

Abstract

In empirical studies with time-to-event outcomes, investigators often leverage observational data to conduct causal inference on the effect of exposure when randomized controlled trial data is unavailable. Model misspecification and lack of overlap are common issues in observational studies, and they often lead to inconsistent and inefficient estimators of the average treatment effect. Estimators targeting overlap weighted effects have been proposed to address the challenge of poor overlap, and methods enabling flexible machine learning for nuisance models address model misspecification. However, the approaches that allow machine learning for nuisance models have not been extended to the setting of weighted average treatment effects for time-to-event outcomes when there is poor overlap. In this work, we propose a class of one-step cross-fitted double/debiased machine learning estimators for the weighted cumulative causal effect as a function of restriction time. We prove that the proposed estimators are consistent, asymptotically linear, and reach semiparametric efficiency bounds under regularity conditions. Our simulations show that the proposed estimators using nonparametric machine learning nuisance models perform as well as established methods that require correctly-specified parametric nuisance models, illustrating that our estimators mitigate the need for oracle parametric nuisance models. We apply the proposed methods to real-world observational data from a UK primary care database to compare the effects of anti-diabetic drugs on cancer clinical outcomes.