Transformation-Invariant Learning of Optimal Individualized Decision Rules with Time-to-Event Outcomes
From MaRDI portal
Abstract: In many important applications of precision medicine, the outcome of interest is time to an event (e.g., death, relapse of disease) and the primary goal is to identify the optimal individualized decision rule (IDR) to prolong survival time. Existing work in this area have been mostly focused on estimating the optimal IDR to maximize the We propose a new robust framework for estimating an optimal static or dynamic IDR with time-to-event outcomes based on an easy-to-interpret quantile criterion. The new method does not need to specify an outcome regression model and is robust for heavy-tailed distribution. The estimation problem corresponds to a nonregular M-estimation problem with both finite and infinite-dimensional nuisance parameters. Employing advanced empirical process techniques, we establish the statistical theory of the estimated parameter indexing the optimal IDR. Furthermore, we prove a novel result that the proposed approach can consistently estimate the optimal value function under mild conditions even when the optimal IDR is non-unique, which happens in the challenging setting of exceptional laws. We also propose a smoothed resampling procedure for inference. The proposed methods are implemented in the R-package QTOCen. We demonstrate the performance of the proposed new methods via extensive Monte Carlo studies and a real data application.restricted mean survival time in the population.
Cites work
- \({\mathcal Q}\)-learning
- A consistent bootstrap procedure for the maximum score estimator
- A generalization error for Q-learning
- A massive data framework for M-estimators with cubic-rate
- A robust method for estimating optimal treatment regimes
- A Sequential Significance Test for Treatment by Covariate Interactions
- A simple censored median regression estimator
- Adaptive Treatment Strategies in Practice
- Asymptotic properties of a generalized kaplan-meier estimator with some applications
- Bayesian inference for causal effects: The role of randomization
- Confidence sets for split points in decision trees
- Cube root asymptotics
- Discussion of ``Dynamic treatment regimes: technical challenges and applications
- Divide and conquer in nonstandard problems and the super-efficiency phenomenon
- Doubly robust estimation of optimal treatment regimes for survival data -- with application to an HIV/AIDS study
- Doubly robust learning for estimating individualized treatment with censored data
- Estimating individualized treatment rules using outcome weighted learning
- Estimating optimal dynamic regimes correcting bias under the null
- Estimating optimal dynamic treatment regimes with survival outcomes
- Estimation of survival quantiles in two-stage randomization designs
- Evaluating marker-guided treatment selection strategies
- Greedy outcome weighted tree learning of optimal personalized treatment rules
- scientific article; zbMATH DE number 1131224 (Why is no real title available?)
- Inconsistency of bootstrap: the Grenander estimator
- Inference for non-regular parameters in optimal dynamic treatment regimes
- Inference for optimal dynamic treatment regimes using an adaptive m-out-of-n bootstrap scheme
- Interpretable dynamic treatment regimes
- Introduction to empirical processes and semiparametric inference
- New statistical learning methods for estimating optimal dynamic treatment regimes
- On estimation of optimal treatment regimes for maximizing t-year survival probability
- On the bootstrap in cube root asymptotics
- On the Bootstrap of the Maximum Score Estimator
- On the choice of m in the m out of n bootstrap and confidence bounds for extrema
- Optimal Dynamic Treatment Regimes
- Optimal treatment regimes for survival endpoints using a locally-efficient doubly-robust estimator from a classification perspective
- Penalized Q-learning for dynamic treatment regimens
- Performance guarantees for individualized treatment rules
- Q-learning with censored data
- Quantile regression.
- Quantile-optimal treatment regimes
- Resampling Fewer Than n Observations: Gains, Losses, and Remedies for Losses
- Resampling‐based confidence intervals for model‐free robust inference on optimal treatment regimes
- Semiparametric \(M\)-estimation with non-smooth criterion functions
- Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy
- Statistical methods for dynamic treatment regimes. Reinforcement learning, causal inference, and personalized medicine
- Subsampling inference in cube root asymptotics with an application to Manski's maximum score estimator.
- Targeted learning ensembles for optimal individualized treatment rules with time-to-event outcomes
- The central role of the propensity score in observational studies for causal effects
- Tree based weighted learning for estimating individualized treatment rules with censored data
- Tree-based methods for individualized treatment regimes
- Weak convergence and empirical processes. With applications to statistics
Cited in
(5)- Doubly robust estimation of optimal treatment regimes for survival data using an instrumental variable
- Estimation in optimal treatment regimes based on mean residual lifetimes with right-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
- Treatment choice with nonlinear regret
This page was built for publication: Transformation-Invariant Learning of Optimal Individualized Decision Rules with Time-to-Event Outcomes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6144778)
