|
Activity Number:
|
479
- Complex Innovative Designs in Practice of Early Phase Drug Development
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, July 31, 2019 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biopharmaceutical Section
|
|
Abstract #300268
|
Presentation
|
|
Title:
|
Adaptive Designs for Drug Combination Informed by Longitudinal Model for the Response
|
|
Author(s):
|
Tobias Mielke*
|
|
Companies:
|
Janssen
|
|
Keywords:
|
Adaptive Designs;
Dose Combination;
Delayed Response;
Optimal Designs of Experiments
|
|
Abstract:
|
We are focusing on adaptive design of drug combination studies in the Phase II of drug development. The safety-tolerated two-dimensional dose space of the two drugs has been established in previous phases. The objective is to estimate the efficacy response surface in this region and select the most efficient dose-combination for the final Phase III clinical trial. In contrast with the dose escalation designs for Phase I trials, in Phase II studies subjects can be allocated upfront to all dose-combinations in the acceptable dose-combination region. The problem is then to find the optimal design that allocates subjects to these dose-combinations in order to maximize the efficacy information obtained in the trial. We are using a binary endpoint as a measure of efficacy but consider the practical situation when the timing of the endpoint assessment period on the subject level is considerably longer relative to the inter-arrival time of subjects. This poses some implementation challenges and we propose a solution by using time-to-event as a particular type of longitudinal response models that helps to draw information from partial follow-up on subjects at the interim analysis.
|
Authors who are presenting talks have a * after their name.
