We propose a design strategy for single--arm clinical trials with goals (1) to find a dose of an experimental treatment satisfying both safety and efficacy requirements, (2) treat a sufficient number of patients to estimate the rates of these events at the selected dose with a given reliability, and (3) stop the trial early if it is likely that no dose is both safe and efficacious. Patient outcome is characterized by a trinary ordinal variable accounting for both efficacy and toxicity. We use Bayesian criteria to generate decision rules while relying on frequentist criteria obtained via simulation to determine a design parameterization with good operating characteristics. The strategy is illustrated by application to a bone marrow transplantation trial and a biologic agent trial.

This is joint work with Kathy E. Russell.

Back to Workshop Schedule