Flexible design clinical trial methodology in regulatory applications

Adaptive designs or flexible designs in a broader sense have increasingly been considered in planning pivotal registration clinical trials. Sample size reassessment design and adaptive selection design are two of such designs that appear in regulatory applications. At the design stage, consideration of sample size reassessment at an interim time of the trial should lead to extensive discussion about how to appropriately size the trial. Additionally, careful attention needs to be paid to the issue of how the size of the trial is impacted by the requirement that the final p-value of the trial meets the specific threshold of a clinically meaningful effect. These issues are not straightforward and will be discussed in this work. In a trial design that allows selection between a pre-specified patient subgroup and the initially planned overall patient population based on the accumulating data, there is an issue of what the 'overall' population means. In addition, it is critically important to know how such selection influences the validity of statistical inferences on the potentially modified overall population. This work presents the biases that may incur under adaptive patient selection designs.