Advertisement

An overview of methodological considerations regarding adaptive stopping, arm dropping and randomisation in clinical trials

Open AccessPublished:November 15, 2022DOI:https://doi.org/10.1016/j.jclinepi.2022.11.002
      This paper is only available as a PDF. To read, Please Download here.

      Highlights

      • -
        Adaptive clinical trials are flexible and adaptive features may increase trial efficiency and individual participants’ chances of being allocated to superior interventions.
      • -
        Adaptive trials come with increased complexity and not all adaptive features may always be beneficial.
      • -
        We provide an overview of and guidance on key methodological considerations for clinical trials employing adaptive stopping, adaptive arm dropping, or response-adaptive randomisation.
      • -
        Further, we provide, a simulation engine and example on how to compare adaptive trial designs using simulation is provided.
      • -
        This guidance paper may help trialists designing and planning adaptive clinical trials.

      Abstract

      Objective

      Adaptive features may increase flexibility and efficiency of clinical trials, and improve participants’ chances of being allocated to better interventions. Our objective is to provide thorough guidance on key methodological considerations for adaptive clinical trials.

      Study Design and Setting

      We provide an overview of key methodological considerations for clinical trials employing adaptive stopping, adaptive arm dropping, and response-adaptive randomisation. We cover pros and cons of different decisions and provide guidance on using simulation to compare different adaptive trial designs. We focus on Bayesian multi-arm adaptive trials, although the same general considerations apply to frequentist adaptive trials.

      Results

      We provide guidance on: 1) interventions and possible common control, 2) outcome selection, follow-up duration and model choice, 3) timing of adaptive analyses, 4) decision rules for adaptive stopping and arm dropping, 5) randomisation strategies, 6) performance metrics, their prioritisation, and arm selection strategies, and 7) simulations, assessment of performance under different scenarios, and reporting. Finally, we provide an example using a newly developed R simulation engine that may be used to evaluate and compare different adaptive trial designs.

      Conclusion

      This overview may help trialists design better and more transparent adaptive clinical trials and to adequately compare them before initiation.

      Keywords