Abstract:
|
With the rapid growth of targeted and immune-oncology therapies, novel statistical design are needed to increase the flexibility and efficiency of early phase oncology trials.Typically, the different indications are analyzed using parallel Simon's two-stage designs. This ignores the potential biological similarities among the indications. Our research provides a statistical methodology to further enhance such basket trials by assessing the homogeneity of the response rates of each indication arm at an interim analysis, and applying a Bayesian hierarchical mixture modeling approach in the second stage if the efficacy is deemed reasonably homogeneous across indications. This would increase the power of the study by allowing indications with similar response rates to borrow information from each other. Via simulations, we compare the efficiency of our approach and the classical design. Nevertheless, if the drug behaves similarly in most or all tumor types, a substantial increase in efficiency can be obtained, by requiring less patients and gaining more power.
|