ABSTRACT
In recent years, the use of adaptive design methods in clinical research and development based on accrued data and/or external information has become very popular due to its ¨exibility and efŒciency (Liu and Chi, 2001; Chow and Chang, 2005, 2006; Krams et al. 2006; EMEA, 2007; FDA, 2010b). An adaptive design is deŒned as a clinical trial design that allows adaptations (modiŒcations or changes) to trial and/or statistical procedure of the trial after its initiation without undermining the validity and integrity of the trial. In their recent publication, with the emphasis of the feature of design adaptations only (rather than ad hoc adaptations), the Pharmaceutical Research Manufacturer Association (PhRMA) Working Group on Adaptive Design deŒnes an adaptive design as a study design that uses accumulating data to decide on how to modify aspects of the study as it continues, without undermining the validity and integrity of the trial. On the other hand, the FDA deŒnes an adaptive design as a study that includes a prospectively planned opportunity for modiŒcation of one or more speciŒed aspects of the study design and hypotheses based on analysis of data (usually interim data) from subjects in the study (FDA, 2010b). Based on the adaptations applied, adaptive designs can be classiŒed into three categories: prospective, concurrent, and retrospective adaptive designs. Chow and Chang (2006) indicate that commonly considered adaptive designs in these categories include, but are not limited to, (1) an adaptive randomization design, (2) a group sequential design (Jennison and Turnball, 2000; Kelly, 2005a, 2005b), (3) a ¨exible sample size reestimation design, (4) a drop-the-loser (or pick-the-winner) design (Sampson and Sill, 2005), (5) an adaptive dose-Œnding design (Chang and Chow, 2005), (6) a biomarker-adaptive design (Chang, 2005a, 2005b), (7) an adaptive treatment-switching design (Branson and Whitehead, 2002; Shao et al., 2005), (8) a hypothesis-adaptive design, (9) a seamless adaptive trial design (Maca et al., 2006), and (10) a multiple adaptive design, which is any combinations of the above-mentioned adaptive designs. Among these, group sequential design, adaptive dose-Œnding design, and (two-stage) seamless adaptive design are probably the most
commonly employed adaptive designs in clinical trials. In this chapter, however, we will only focus on the two-stage seamless adaptive trial design.
