Trial designs for assessing induction, maintenance and other treatment effects on a continuous endpoint.

A pivotal clinical trial designed to demonstrate the benefit of a new treatment for treating a chronic disease usually has multiple objectives of affirming that the treatment is an appropriate induction, maintenance and long-term therapy. To fulfill some of these and other objectives for the trial, various designs have been applied. They include the active treatment lead-in followed by randomized maintenance design, the randomized induction followed by re-randomized withdrawal maintenance design, and the treat-through design. A sequential parallel comparison design (SPCD) has also been proposed for a trial with a binary endpoint. This SPCD can be treated as a hybrid of the above three designs and has some additional advantages. As the model and method for data analysis heavily depend on the type of endpoint, in this paper, we extend the application of the SPCD to a trial with a continuous endpoint. To fully utilize all available data of the induction and maintenance phases for an overall treatment effect evaluation, we consider a weighted combination test for an overall treatment effect assessment which incorporates the correlations of the components. Further, approaches for handling missing data are discussed. Simulations are conducted to evaluate the performances of the methods, and an example is used to illustrate the application of the methods.