Maximin Learning of Individualized Treatment Effect on Multi-Domain Outcomes

TL;DR

DRIFT is a novel maximin framework that estimates robust individualized treatment effects from high-dimensional, multi-domain data, enhancing generalizability and handling unmeasured clinical domains.

Contribution

It introduces a maximin approach leveraging latent factor analysis and adversarial learning to improve robustness and generalizability of treatment effect estimates.

Findings

DRIFT outperforms existing methods in a depression treatment trial.

It demonstrates robustness to unmeasured domains and symptom selection.

The method has theoretical guarantees for identification and convergence.

Abstract

Precision mental health requires treatment decisions that account for heterogeneous symptoms reflecting multiple clinical domains. However, existing methods for estimating individualized treatment effects (ITE) rely on a single summary outcome or a specific set of observed symptoms or measures, which are sensitive to symptom selection and limit generalizability to unmeasured yet clinically relevant domains. We propose DRIFT, a new maximin framework for estimating robust ITEs from high-dimensional item-level data by leveraging latent factor representations and adversarial learning. DRIFT learns latent constructs via generalized factor analysis, then constructs an anchored on-target uncertainty set that extrapolates beyond the observed measures to approximate the broader hyper-population of potential outcomes. By optimizing worst-case performance over this uncertainty set, DRIFT yields ITEs that are robust to underrepresented or unmeasured domains. We further show that DRIFT is invariant to admissible reparameterizations of the latent factors and admits a closed-form maximin solution, with theoretical guarantees for identification and convergence. In analyses of a randomized controlled trial for major depressive disorder (EMBARC), DRIFT demonstrates superior performance and improved generalizability to external multi-domain outcomes, including side effects and self-reported symptoms not used during training.