Superiority of combining two independent trials in interim futility analysis

Abstract

Traditionally, statistical methods for futility analysis are developed based on a single study. To establish a drug's effectiveness, usually at least two adequate and well-controlled studies need to demonstrate convincing evidence on its own. Therefore, in a standard clinical development program in chronic diseases, two independent studies are generally conducted for drug registration. This paper proposes a statistical method to combine interim data from two independent and similar studies for interim futility analysis and shows that the conditional power approach based on combined interim data has better operating characteristics compared to the approach based on single-trial interim data, even with small to moderate heterogeneity on the treatment effects between the two studies.