A pseudo-outcome-based framework to analyze treatment heterogeneity in survival data using electronic health records

TL;DR

This paper introduces a pseudo-outcome-based framework for analyzing heterogeneous treatment effects in survival data, addressing challenges in observational studies with right-censored data, and applies it to asthma treatment data to identify vulnerable subgroups benefiting from interventions.

Contribution

The paper proposes a novel pseudo-outcome-based framework with meta-learners, variable importance metrics, and subgroup selection methods for HTE analysis in survival data, validated through real-world EHR data.

Findings

Identified subgroups with poorer asthma outcomes but greater treatment benefits.

Demonstrated the framework's effectiveness across various observational study settings.

Provided insights for targeted healthcare strategies during public health crises.

Abstract

An important aspect of precision medicine focuses on characterizing diverse responses to treatment due to unique patient characteristics, also known as heterogeneous treatment effects (HTE), and identifying beneficial subgroups with enhanced treatment effects. Estimating HTE with right-censored data in observational studies remains challenging. In this paper, we propose a pseudo-outcome-based framework for analyzing HTE in survival data, which includes a list of meta-learners for estimating HTE, a variable importance metric for identifying predictive variables to HTE, and a data-adaptive procedure to select subgroups with enhanced treatment effects. We evaluate the finite sample performance of the framework under various settings of observational studies. Furthermore, we applied the proposed methods to analyze the treatment heterogeneity of a Written Asthma Action Plan (WAAP) on time-to-ED (Emergency Department) return due to asthma exacerbation using a large asthma electronic health records dataset with visit records expanded from pre- to post-COVID-19 pandemic. We identified vulnerable subgroups of patients with poorer asthma outcomes but enhanced benefits from WAAP and characterized patient profiles. Our research provides valuable insights for healthcare providers on the strategic distribution of WAAP, particularly during disruptive public health crises, ultimately improving the management and control of pediatric asthma.