ABSTRACT
In this chapter, the author aims to assume that the biomarker threshold is known and the subjects can be accurately separated into two groups with one group likely to respond more than the biomarker-negative subgroup. A Two-Stage Design is sometimes also called adaptive enrichment designs. In this specific case, it is a two-stage design, where in a first stage patients are recruited from the full population. Then, in an interim analysis, based on interim data at the end of the first stage, the trial design of the second stage may be adapted to patients in the BM+ subgroup. The stage I patients remain in the trial and continue to be monitored for survival events for a prespecified follow-up time. Meanwhile, more subjects are newly recruited to stage II. None of the information gained in stage I is lost in the final analysis; hence, the design is inferentially seamless, as well as operationally seamless.
