Variable Duration Trial as an Alternative Design for Continuous Endpoints.

Abstract

Clinical trials with continuous primary endpoints typically measure outcomes at baseline, at a fixed timepoint (denoted T_min), and at intermediate timepoints. The analysis is commonly performed using the mixed model repeated measures method. It is sometimes expected that the effect size will be larger with follow-up longer than T_min. But extending the follow-up for all patients delays trial completion. We propose an alternative trial design and analysis method that potentially increases statistical power without extending the trial duration or increasing the sample size. We propose following the last enrolled patient until T_min, with earlier enrollees having variable follow-up durations up to a maximum of T_max. The sample size at T_max will be smaller than at T_min, and due to staggered enrollment, data missing at T_max will be missing completely at random. For analysis, we propose an alpha-adjusted procedure based on the smaller of the p values at T_min and T_max, termed $\text{minP}$ . This approach can provide the highest power when the powers at T_min and T_max are similar. If the power at T_min and T_max differ significantly, the power of $\text{minP}$ is modestly reduced compared with the larger of the two powers. Rare disease trials, due to the limited size of the patient population, may benefit the most with this design.