Evaluating the Use of Generalized Dynamic Weighted Ordinary Least Squares for Individualized HIV Treatment Strategies

TL;DR

This paper introduces an extension of the G-dWOLS method for estimating individualized treatment rules in longitudinal data, demonstrating its application to optimize HIV treatment strategies with promising simulation and real-world results.

Contribution

It extends G-dWOLS to categorical treatments and applies it to HIV data to develop an optimal treatment rule for IL-7 administration.

Findings

G-dWOLS effectively estimates ITRs in simulated data.

The HIV application shows potential for personalized treatment optimization.

Method demonstrates double robustness in longitudinal settings.

Abstract

Dynamic treatment regimes (DTR) are a statistical paradigm in precision medicine which aim to optimize patient outcomes by individualizing treatments. At its simplest, a DTR may require only a single decision to be made; this special case is called an individualized treatment rule (ITR) and is often used to maximize short-term rewards. Generalized dynamic weighted ordinary least squares (G-dWOLS), a DTR estimation method that offers theoretical advantages such as double robustness of parameter estimators in the decision rules, has been recently extended to now accommodate categorical treatments. In this work, G-dWOLS is applied to longitudinal data to estimate an optimal ITR, which is demonstrated in simulations. This novel method is then applied to a population affected by HIV whereby an ITR for the administration of Interleukin 7 (IL-7) is devised to maximize the duration where the CD4 load is above a healthy threshold (500 cells/$\mu$L) while preventing the administration of unnecessary injections.