Skip to content

Advertisement

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact us so we can address the problem.

Patient drift and response-adaptive randomisation: impact and solutions

  • 1,
  • 1 and
  • 1
Trials201516 (Suppl 2) :P232

https://doi.org/10.1186/1745-6215-16-S2-P232

  • Published:

Keywords

  • Error Rate
  • Control Treatment
  • Trial Design
  • Patient Response
  • Major Criticism

There is a considerable interest in using response-adaptive randomisation in clinical trials. Several reasons motivate this. First, they improve individual patient response in clinical trials by increasing the allocation to a best performing treatment (if it exists). Skewing its allocation probability as data accumulates. Second, in multi-armed trials, by protecting the allocation to the control treatment, one can identify trial designs that score highly in both statistical power and patient benefit. Moreover, in this context, by testing many promising treatments simultaneously, multi-arm trials increase the probability of finding a successful new treatment, speeding up the process of doing so. Despite this, response-adaptive designs have seldom been used in practice. One of the major criticisms of response-adaptive randomisation is the potential for type-one error inflation due to “patient drift”. Patient drift can include changes in patients characteristics or the effectiveness of treatments over time. There have been few papers quantifying the extent to which this phenomena actually affects the operating characteristics and how to best correct for it.

In this talk we present work addressing both questions for novel adaptive randomisation methods. We consider several scenarios and allocation rules to assess how the type and magnitude of the drift affects the type-one error rate for these designs. We further suggest and assess statitiscal procedures that preserve type one error in the presence of unknown patient drift in both a two-arm and a multi-arm trial setting.

Authors’ Affiliations

(1)
MRC Biostatistics Unit, Cambridge, UK

Copyright

© Villar et al. 2015

This article is published under license to BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.

Comments

By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate. Please note that comments may be removed without notice if they are flagged by another user or do not comply with our community guidelines.

Advertisement