Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges

DOI10.1214/14-STS504zbMath1332.62267arXiv1507.08025WikidataQ38829437 ScholiaQ38829437MaRDI QIDQ254442

Jack Bowden, Sofía S. Villar, James M. S. Wason

Publication date: 8 March 2016

Published in: Statistical Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1507.08025

zbMATH Keywords

Gittins index; multi-armed bandit; patient allocation; response adaptive procedures; Whittle index

Mathematics Subject Classification ID

62P10: Applications of statistics to biology and medical sciences; meta analysis

62K05: Optimal statistical designs

92C50: Medical applications (general)

Related Items

BANDIT STRATEGIES EVALUATED IN THE CONTEXT OF CLINICAL TRIALS IN RARE LIFE-THREATENING DISEASES, Unnamed Item, On the Bias, Risk, and Consistency of Sample Means in Multi-armed Bandits, Bayesian adaptive bandit-based designs using the Gittins index for multi-armed trials with normally distributed endpoints, Bandit Theory: Applications to Learning Healthcare Systems and Clinical Trials, Dynamic Programming for Response-Adaptive Dose-Finding Clinical Trials, Simple Bayesian Algorithms for Best-Arm Identification, An Approximation Approach for Response-Adaptive Clinical Trial Design, Optimal activation of halting multi‐armed bandit models, A novel statistical test for treatment differences in clinical trials using a response‐adaptive forward‐looking Gittins Index Rule, Index policy for multiarmed bandit problem with dynamic risk measures, Testing indexability and computing Whittle and Gittins index in subcubic time, Rejoinder: response-adaptive randomization in clinical trials, Online Debiasing for Adaptively Collected High-Dimensional Data With Applications to Time Series Analysis, Response-adaptive randomization in clinical trials: from myths to practical considerations, Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems, Mathematical models for immunology: current state of the art and future research directions, Response adaptive designs for phase II trials with binary endpoint based on context-dependent information measures, A Bayesian adaptive design for clinical trials in rare diseases, A revised approach for risk-averse multi-armed bandits under CVaR criterion, A Markov decision process for response-adaptive randomization in clinical trials, Whittle index based Q-learning for restless bandits with average reward, A simple solution to the inadequacy of asymptotic likelihood-based inference for response-adaptive clinical trials: likelihood-based inference for RAR trials, Generalisations of a Bayesian decision-theoretic randomisation procedure and the impact of delayed responses, Ballooning multi-armed bandits, Covariate-adjusted response-adaptive randomization for multi-arm clinical trials using a modified forward looking Gittins index rule

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Asymptotically efficient adaptive allocation rules
• Arm-acquiring bandits
• Algorithms for evaluating the dynamic allocation index
• On the Gittins index for multiarmed bandits
• The learning component of dynamic allocation indices
• Celebrating 70: an interview with Don Berry
• Restless bandits, partial conservation laws and indexability
• A generalized Dunnett test for multi-arm multi-stage clinical studies with treatment selection
• A (2/3)n³ Fast-Pivoting Algorithm for the Gittins Index and Optimal Stopping of a Markov Chain
• Computing a Classic Index for Finite-Horizon Bandits
• Multi‐Armed Bandit Allocation Indices
• INDEXABILITY OF BANDIT PROBLEMS WITH RESPONSE DELAYS
• Extensions of the multiarmed bandit problem: The discounted case
• The Search for Optimality in Clinical Trials
• Linear Programming for Finite State Multi-Armed Bandit Problems
• On an index policy for restless bandits
• On the optimal allocation of two or more treatments in a controlled clinical trial
• Conservation Laws, Extended Polymatroids and Multiarmed Bandit Problems; A Polyhedral Approach to Indexable Systems
• Ethics, data-dependent designs, and the strategy of clinical trials: time to start learning-as-we-go?
• On the Theory of Dynamic Programming
• Some aspects of the sequential design of experiments
• Finite-time analysis of the multiarmed bandit problem