Design and analysis of phase II clinical trials

Abstract

A clinical trial may be defined as a carefully designed, prospective medical study which attempts to answer a precisely defined set of questions with respect to the effects of a particular treatment or treatments. Major types of clinical trials include phase I, II, III, and IV studies, although a more strict definition may limit to phase III studies only. A phase II study is to characterize, but not to compare, the therapeutic efficacy, toxicity, or quality of life of one or more therapeutic strategies for a given disease or condition, and then decide whether the regimen(s) merit further study in subsequent phase III trials. In designing of a phase II study, we decide the number of patients for a multi-stage design through an optimal strategy. In completion of a phase II study, one of major statistical analyses is to obtain the exact confidence interval of response (or toxicity) rate. This article reviews the existing statistical methodologies used in designing and analyzing phase II clinical trials or anti-cancer therapeutics.