Multi-stage optimal dynamic treatment regimes for survival outcomes with dependent censoring

DOI10.1093/BIOMET/ASAC047MaRDI QIDQ6045149zbMATH OpenOpenAlexFDO

Authors Hunyong Cho, Shannon T. Holloway, David Couper, Michael R. Kosorok

Publication date 26 May 2023

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2012.03294

zbMATH Keywords

conditionally independent censoringdynamic treatment regimeempirical processprecision medicinerandom forestreinforcement learningsurvival analysis

Mathematics Subject Classification ID

Statistics (62-XX)

Abstract: We propose a reinforcement learning method for estimating an optimal dynamic treatment regime for survival outcomes with dependent censoring. The estimator allows the failure time to be conditionally independent of censoring and dependent on the treatment decision times, supports a flexible number of treatment arms and treatment stages, and can maximize either the mean survival time or the survival probability at a certain time point. The estimator is constructed using generalized random survival forests and can have polynomial rates of convergence. Simulations and data analysis results suggest that the new estimator brings higher expected outcomes than existing methods in various settings. An R package dtrSurv is available on CRAN.

Cited in

(9)

• dtrSurv
• Optimal dynamic treatment regimes with survival endpoints: introducing DWSurv in the R package DTRreg
• A multi-treatment two stage adaptive allocation for survival outcomes
• Multicategory Angle-Based Learning for Estimating Optimal Dynamic Treatment Regimes With Censored Data
• Censored C-learning for dynamic treatment regime in colorectal cancer study
• Efficient and robust transfer learning of optimal individualized treatment regimes with right-censored survival data
• Estimation of the optimal treatment regimes with multiple treatments under proportional hazards model
• Counterfactual Q-learning via the linear Buckley-James method for longitudinal survival data
• Variable selection based on A-learning for optimal treatment regimes with survival data under semiparametric model

This page was built for publication: Multi-stage optimal dynamic treatment regimes for survival outcomes with dependent censoring

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6045149)