Group Sequential Designs

Clinical trials, with almost no exception, are longitudinal (Chow and Liu, 2004). This means that data are accumulated sequentially over time. From the perspective outlined so far in the book, the statistical analysis takes place once the number of subjects stated in the study protocol have been enrolled, randomized, and completed their participation in the trial. This approach can be called the Fixed design or fixed sample design approach. Another design of interest in clinical trials is the group sequential design, in which interim analysis plays a crucial role. 

Several interim analyses may be performed during an ongoing clinical trial at various preidentified points. Each interim analysis conducted utilizes all of the data that have been collected to date. The rationale for this approach is that this strategy may reveal compelling evidence that the clinical trial should be stopped at the time of a particular interim analysis because there is already compelling evidence that the drug is effective or that it is toxic. This particular interim analysis could be conducted some considerable time before the trial would have otherwise been completed. 

The purpose of interim analyses in group sequential trials is to determine if the clinical trial should be terminated at that point. The rationale for interim analyses of data that are accumulating over time in a clinical trial was established almost 40 years ago, and considerable attention has subsequently focused on the development of statistical approaches and decision-making processes that facilitate the implementation of data monitoring and interim analyses for the early termination of a clinical trial (Chow and Liu, 2004). 

The composition of DMCs is typically multidisciplinary, and the participation of both clinicians and statisticians is critical. The DMC for a particular trial can be appointed by the trial sponsor or by a steering committee. Its duties can include reviewing the initial protocol, monitoring the conduct of the study by assessing accrual, eligibility, protocol compliance, losses to follow-up, and other issues concerned with safeguarding the subjects and the integrity of the trial. 

Before a trial starts, a charter needs to be written and agreed upon by the trial sponsor and the committee. This charter describes the structure and operation of the committee and specifies its activities and responsibilities. The DMC should have access to fully unblinded data, with actual treatments and not just codes available for its review. Except in certain limited circumstances, trial integrity is best protected when interim data comparing treatment groups are seen only by the DMC members and statisticians preparing the interim report (Ellenberg et al., 2003, see also O Neill, 2006). 

As of writing this text, the guidance document is still in the development 

Group sequential designs facilitate interim analyses being performed during the conduct of a clinical trial. Each interim analysis that is performed utilizes all of the data that have been collected to the point when a given analysis is conducted. 

---

By its nature, therefore, the group sequential design involves the possibility of multiple testing. In this example it is possible that five analyses could be conducted on data collected in this clinical trial. As discussed in Section 7.10, there is an inherent problem with multiple testing. As more tests are performed, it becomes increasingly likely that a Type I error will occur, i.e., that a result will erroneously be declared as statistically significant. As also noted at that point, however, the problem can be addressed completely satisfactorily by taking appropriate statistical care. 

One type of flexible design is the group sequential design (23). Such a design typically includes one or more preplanned interim analyses. Based on the results of the interim analysis, a preplanned action is taken. Most commonly these actions include ... 

Group sequential designs, particularly in noninferiority safety studies where many events may occur after accrual during the follow-up phase, are unlikely to stop early. The design described here, instead, uses accruing information to predict how many events the current cohort is likely to provide with addition follow-up. Therefore, rather than having many patients with short exposure times, it relies on a smaller number of patients with greater exposure times—with that optimal number chosen adaptively and based upon internal trial data. 

The original methodology for group sequential designs, and hence interim analyses, required that the number and timing of interim analyses be specified in advance. However, in cases where potentially unfavorable safety data may be emerging, a... 

---