Safe Individualized Treatment Rules with Controllable Harm Rates

TL;DR

This paper develops methods to estimate individualized treatment rules that maximize reward while controlling the harm rate below a specified threshold, addressing the limitations of traditional approaches that overlook individual-level harm.

Contribution

It introduces two strategies for estimating harm-constrained ITRs under partial identification and analyzes their large-sample properties, advancing personalized treatment decision-making.

Findings

Proposed methods effectively control harm rates in simulations.

Methods outperform traditional ITRs in reducing harm in real data applications.

Theoretical guarantees established for the estimators' large-sample behavior.

Abstract

Estimating individualized treatment rules (ITRs) is crucial for tailoring interventions in precision medicine. Typical ITR estimation methods rely on conditional average treatment effects (CATEs) to guide treatment assignments. However, such methods overlook individual-level harm within covariate-specific subpopulations, potentially leading many individuals to experience worse outcomes under CATE-based ITRs. In this article, we aim to estimate ITRs that maximize the reward while ensuring that the harm rate induced by the ITR remains below a pre-specified threshold. We first derive the explicit form of the oracle ITR. However, the oracle ITR is not achievable without strong assumptions, as the harm rate is generally unidentifiable due to its dependence on the joint distribution of potential outcomes. To address this, we propose two strategies for estimating ITRs with a harm rate constraint under partial identification and establish their large-sample properties. By accounting for both reward and harm, our method provides a reliable solution for developing ITRs in high-stakes domains where harm is a critical consideration. Extensive simulations demonstrate the effectiveness of the proposed methods in controlling harm rates. We apply the proposed method to analyze two real-world datasets from a new perspective, assessing the potential reduction in harm rate compared with historical interventions.