Efficient Designs for Dose-Response Studies Under Model Uncertainty

• Activity Number: 497
• Type: Contributed
• Date/Time: Wednesday, August 7, 2013 : 8:30 AM to 10:20 AM
• Sponsor: Biopharmaceutical Section
• Author(s): Tobias Mielke*+
• Companies: Aptiv Solutions
• Keywords: dose-response studies ; MCP-Mod ; multiple contrast tests ; nonlinear modeling ; optimal design

Abstract

Dose-response studies have typically two main objectives. The first objective is to prove the existence of a dose-response effect. Multiple contrast tests are usually applied for addressing this proof-of-concept. After successfully establishing the dose-response effect, the second objective is the selection of a set of doses for confirmatory Phase III studies. The MCP-Mod approach provides robust methods for selecting doses by combining model based contrast tests and nonlinear modeling procedures. In the first step of the MCP-Mod approach the contrasts are optimized with respect to certain reasonable dose-response shapes for improving the power of the proof-of-concept. One or more dose response shapes with significant contrasts are then used in a second step for selecting doses for the confirmatory Phase III studies. Different approaches for deriving optimal allocations to the dose groups and for calculating the needed sample size for establishing the dose response effect will be discussed in this presentation. Simulation studies provide insight in the efficiency of the presented designs in comparison to standard modeling and design approaches.