mlsanityData to 7 Oct 2026

Efficient and robust transfer learning of optimal individualized treatment regimes with right-censored survival data

arXiv 2301.05491 ↗First posted 13 Jan 2023stat.ME stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

An individualized treatment regime (ITR) is a decision rule that assigns treatments based on patients' characteristics. The value function of an ITR is the expected outcome in a counterfactual world had this ITR been implemented. Recently, there has been increasing interest in combining heterogeneous data sources, such as leveraging the complementary features of randomized controlled trial (RCT) data and a large observational study (OS). Usually, a covariate shift exists between the source and target population, rendering the source-optimal ITR unnecessarily optimal for the target population. We present an efficient and robust transfer learning framework for estimating the optimal ITR with right-censored survival data that generalizes well to the target population. The value function accommodates a broad class of functionals of survival distributions, including survival probabilities and restrictive mean survival times (RMSTs). We propose a doubly robust estimator of the value function, and the optimal ITR is learned by maximizing the value function within a pre-specified class of ITRs. We establish the N-1/3 rate of convergence for the estimated parameter indexing the optimal ITR, and show that the proposed optimal value estimator is consistent and asymptotically normal even with flexible machine learning methods for nuisance parameter estimation. We evaluate the empirical performance of the proposed method by simulation studies and a real data application of sodium bicarbonate therapy for patients with severe metabolic acidaemia in the intensive care unit (ICU), combining a RCT and an observational study with heterogeneity.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 35 of its 111 references that are in the map. First posted on arXiv 13 Jan 2023.

Builds on

35 of 111 references.

References · 35

  1. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 475
  2. 2016Generalized Random Forestscited by 309
  3. 2022Semiparametric doubly robust targeted double machine learning: a reviewcited by 129
  4. 2020Causal inference methods for combining randomized trials and observational studies: a reviewcited by 50
  5. 2021A Review of Generalizability and Transportabilitycited by 36
  6. 2022Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effectscited by 32
  7. 2022Policy learning "without" overlap: Pessimism and generalized empirical Bernstein's inequalitycited by 32
  8. 2013Program Evaluation and Causal Inference with High-Dimensional Datacited by 29
  9. 2020Estimating heterogeneous treatment effects with right-censored data via causal survival forestscited by 29
  10. 2020Learning Optimal Distributionally Robust Individualized Treatment Rulescited by 28
  11. 2019Semi-Parametric Efficient Policy Learning with Continuous Actionscited by 26
  12. 2021Fast Rates for the Regret of Offline Reinforcement Learningcited by 26
23 more
  1. 2017Generalizing causal inferences from individuals in randomized trials to all trial-eligible individualscited by 24
  2. 2019More Efficient Policy Learning via Optimal Retargetingcited by 23
  3. 2018Sharp instruments for classifying compliers and generalizing causal effectscited by 22
  4. 2019A semiparametric instrumental variable approach to optimal treatment regimes under endogeneitycited by 22
  5. 2022Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelinescited by 22
  6. 2021Proximal Learning for Individualized Treatment Regimes Under Unmeasured Confoundingcited by 21
  7. 2016Interpretable Dynamic Treatment Regimescited by 17
  8. 2020Elastic Integrative Analysis of Randomized Trial and Real-World Data for Treatment Heterogeneity Estimationcited by 17
  9. 2021Multi-Source Causal Inference Using Control Variatescited by 13
  10. 2022Learning from a Biased Samplecited by 12
  11. 2015Using Decision Lists to Construct Interpretable and Parsimonious Treatment Regimescited by 11
  12. 2022Falsification before Extrapolation in Causal Effect Estimationcited by 10
  13. 2014On Estimation of Optimal Treatment Regimes For Maximizing t-Year Survival Probabilitycited by 9
  14. 2020Improving trial generalizability using observational studiescited by 7
  15. 2022Doubly robust estimators for generalizing treatment effects on survival outcomes from randomized controlled trials to a target populationcited by 7
  16. 2017Tree based weighted learning for estimating individualized treatment rules with censored datacited by 5
  17. 2020Multi-stage optimal dynamic treatment regimes for survival outcomes with dependent censoringcited by 5
  18. 2017Targeted Learning Ensembles for Optimal Individualized Treatment Rules with Time-to-Event Outcomescited by 4
  19. 2021Transfer learning of individualized treatment rules from experimental to real-world datacited by 4
  20. 2019Study designs for extending causal inferences from a randomized trial to a target populationcited by 3
  21. 2022Targeted Optimal Treatment Regime Learning Using Summary Statisticscited by 2
  22. 2020SMIM: a unified framework of Survival sensitivity analysis using Multiple Imputation and Martingalecited by 1
  23. 2022Transformation-Invariant Learning of Optimal Individualized Decision Rules with Time-to-Event Outcomescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 1; 2026: 1.

5 papers.

  1. 2023Positivity-free Policy Learning with Observational Datacited by 6
  2. 2024Learning Robust Treatment Rules for Censored Datacited by 1
  3. 2023A Semiparametric Instrumented Difference-in-Differences Approach to Policy Learningcited by 0
  4. 2025Learning Survival Models with Right-Censored Reporting Delayscited by 0
  5. 2026Efficient Neural Network Model Selection for Few-Class Application Datasetscited by 0