Deep Optimal Individualized Treatment Rules for Bivariate Survival Outcomes via Adaptive Prediction-Powered Learning

2026-05-28

AI Summary

This study addresses the optimization of individualized treatment strategies in multi-arm randomized trials with bivariate right-censored survival outcomes, aiming to maximize the joint probability of patient survival beyond a fixed time point \((t_1, t_2)\). To this end, the authors propose a novel approach that integrates deep neural networks with marginal accelerated failure time models, formulating individualized rules through stochastic policies and incorporating an adaptive prediction-augmentation mechanism to enhance robustness. This work represents the first integration of deep learning with a prediction-augmentation framework for bivariate censored survival data, enabling efficient estimation of individualized treatment rules while significantly improving the optimization of joint survival probabilities without compromising robustness.

Abstract

In randomized trials involving multiple treatments, bivariate survival outcomes present significant analytical challenges for making decisions. This paper addresses the problem of deriving optimal individualized treatment rules to maximize the joint survival probability beyond fixed time points $(t_1, t_2)$ through deep neural networks, while accounting for right censoring. We propose a novel approach that models treatment rules via stochastic policies, coupling marginal accelerated failure time models via link function to capture bivariate dependence. To enhance robustness and effectiveness of decision making, we introduce an adaptive prediction-powered method that leverages auxiliary predictions from machine learning models.

Problem

• individualized treatment rules
• bivariate survival outcomes
• right censoring
• joint survival probability
• randomized trials

Innovation

• individualized treatment rules
• bivariate survival
• deep neural networks
• adaptive prediction-powered learning
• accelerated failure time model