A BAYESIAN-APPROACH TO ESTABLISHING SAMPLE-SIZE AND MONITORING CRITERIA FOR PHASE-II CLINICAL-TRIALS

Thall and Simon [1] propose a Bayesian approach to phase II clinical t rials with binary outcomes and continuous monitoring. The efficacy the ta(E) of an experimental treatment E is evaluated relative to that of a standard treatment S based on data from an uncontrolled trial of E, an informative Frier for theta(S), and a noninformative prior for thet a(E). The trial continues until E is shown with high posterior probabi lity to be either promising or not promising, or until a predetermined maximum sample size is reached. Operating characteristics are evaluat ed under fixed values of the success probability of E. In this paper, we propose two extensions of this decision structure, describe sample size and monitoring criteria, and provide numerical guidelines for imp lementation. The first extension gives criteria from early termination of trials unlikely to yield conclusive results, based on the marginal (predictive) distribution of the observed success rate. The second ex tension allows early termination only if E is found to be not promisin g compared to S. Operating characteristics of each of these designs ar e evaluated numerically over a range of design parameterizations. We a lso examine the effects of intermittent monitoring on the design's pro perties. An application of this approach to a leukemia biochemotherapy trial is described.