Response-adaptive designs for clinical trials: Simultaneous learning from multiple patients

Ahuja, Vishal; Birge, John R.

doi:10.1016/j.ejor.2015.06.077

Cited by 35 publications

(11 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, scientific disciplines, such as computer science (Audibert, Munos, & Szepesvári, 2009; Scott, 2010, 2015), marketing (Kaptein, McFarland, & Parvinen, 2018; Schwartz, Bradlow, & Fader, 2017), and medical research (cf. Ahuja & Birge, 2016; Berry, 2004; Berry & Eick, 1995; Press, 2009; Villar, Bowden, & Wason, 2015; Villar, Wason, & Bowden, 2015; Wason & Trippa, 2014; Williamson, Jacko, Villar, & Jaki, 2017), began to introduce response-adaptive randomization approaches in experiments that can be conducted sequentially.…”

Section: Utilizing Machine Learning Algorithms and Technological Advamentioning

confidence: 99%

Rethinking the Gold Standard With Multi-armed Bandits: Machine Learning Allocation Algorithms for Experiments

Kaibel

Biemann

2019

Organizational Research Methods

View full text Add to dashboard Cite

In experiments, researchers commonly allocate subjects randomly and equally to the different treatment conditions before the experiment starts. While this approach is intuitive, it means that new information gathered during the experiment is not utilized until after the experiment has ended. Based on methodological approaches from other scientific disciplines such as computer science and medicine, we suggest machine learning algorithms for subject allocation in experiments. Specifically, we discuss a Bayesian multi-armed bandit algorithm for randomized controlled trials and use Monte Carlo simulations to compare its efficiency with randomized controlled trials that have a fixed and balanced subject allocation. Our findings indicate that a randomized allocation based on Bayesian multi-armed bandits is more efficient and ethical in most settings. We develop recommendations for researchers and discuss the limitations of our approach.

show abstract

Section: Utilizing Machine Learning Algorithms and Technological Advamentioning

confidence: 99%

Rethinking the Gold Standard With Multi-armed Bandits: Machine Learning Allocation Algorithms for Experiments

Kaibel

Biemann

2019

Organizational Research Methods

View full text Add to dashboard Cite

show abstract

“…A large body of research focuses on optimal trial design so as to shorten trial duration or minimize the number of volunteers exposed to a potentially unsafe drug. Ahuja and Birge (2016) dynamically adjust randomization probabilities of patients to treatments so that patients are treated as effectively as possible without compromising the ability to learn about treatment efficacy. Bertsimas et al (2015) employ discrete linear optimization methods to construct treatment groups for small samples to allow for more powerful statistical inference.…”

Section: Randomized Controlled Trials (Rcts) a Major Bottleneck In Tmentioning

confidence: 99%

Flexible FDA Approval Policies

2017

View full text Add to dashboard Cite

“…Here, the adoption of multiple stages of sampling allows the designer to modify the sample size of the trial, to adapt the allocation of patients among arms, and/or to drop inferior arms based on the outcomes observed so far, with the goal of improving a trial's cost, duration, or information gain. The advantages of adaptive trials are discussed widely (Berry 2012, Chow 2014, Ahuja and Birge 2016, Ellenberg and Ellenberg 2017, Pallmann et al 2018.…”

Section: Introductionmentioning

confidence: 99%

Bayesian Sequential Learning for Clinical Trials of Multiple Correlated Medical Interventions

2022

View full text Add to dashboard Cite

We propose and analyze the first model for clinical trial design that integrates each of three important trends intending to improve the effectiveness of clinical trials that inform health-technology adoption decisions: adaptive design, which dynamically adjusts the sample size and allocation of interventions to different patients; multiarm trial design, which compares multiple interventions simultaneously; and value-based design, which focuses on cost-benefit improvements of health interventions over a current standard of care. Example applications are to seamless phase II/III dose-finding trials and to trials that test multiple combinations of therapies. Our objective is to maximize the expected population health-economic benefit of health-technology adoption decisions less clinical trial costs. We show that unifying the adaptive, multiarm, and value-based approaches to trial design can reduce the cost and duration of multiarm trials with efficient adaptive look ahead policies that focus on value to patients and account for correlated rewards across arms. Features that differentiate our approach from much other work on stochastic optimization include stopping times that balance sampling costs and the expected value of information of those samples, performance guarantees offered by new asymptotic convergence proofs, and the modeling of arms’ potentially different sampling costs. Our proposed solution can be computed feasibly and can randomize patients. The class of trials for the base model assumes that health-economic data are collected and observed quickly. Related work from Bayesian optimization can enable the further inclusion of trials with intermediate duration delays between the time of treatment initiation and observation of outcomes. This paper was accepted by Stefan Scholtes, healthcare management.

show abstract

Response-adaptive designs for clinical trials: Simultaneous learning from multiple patients

Cited by 35 publications

References 41 publications

Rethinking the Gold Standard With Multi-armed Bandits: Machine Learning Allocation Algorithms for Experiments

Rethinking the Gold Standard With Multi-armed Bandits: Machine Learning Allocation Algorithms for Experiments

Flexible FDA Approval Policies

Bayesian Sequential Learning for Clinical Trials of Multiple Correlated Medical Interventions

Contact Info

Product

Resources

About