Adaptive Group Sequential Design

Classic group sequential design is a study design that has the option to

  • (1) review accumulating data (either safety or efficacy or both) at interim,
  • (2) stop the trial early due to safety, futility, or efficacy after review of the interim data, and (3) perform SSRE at interim to determine whether the study will achieve its objective if the observed treatment effect is preserved until the end of the study. Classic group sequential design with the above-described options is considered a well-understood design by the FDA (FDA 2010a) because the corresponding statistical methods and various stopping boundaries based on different boundary functions for controlling an overall type I error rate are well established and available in the literature (see e.g., Chow and Chang 2011).

Adaptive group sequential design, in contrast, is a classical group sequential design with prespecified options for additional adaptations (e.g., modifica- tion/deletion/addition of treatment arms, change of study endpoints, modification of dose and/or treatment duration, modification of randomization schedules, etc.) after interim analysis. With additional adaptations, adaptive group sequential design has become a less well-understood design. In this case, standard methods for the classical group sequential design may not be appropriate. For example, they may not be able to control the overall type I error rate at the desired level of 5%, owing to potential issues pertaining to adaptations of a given study design. Appropriate statistical procedures are necessary to avoid the potential increase in the study-wide type I error rate (FDA 2010a).

< Prev   CONTENTS   Source   Next >