|
Activity Number:
|
162
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, August 3, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #305592 |
|
Title:
|
Optimum Duration Designs for Phase II Oncology Trials
|
|
Author(s):
|
Ying Lu*+ and Shenghua K. Fan
|
|
Companies:
|
University of California, San Francisco and California State University, East Bay
|
|
Address:
|
Department of Radiology and Biomedical Imaging, San Francisco, CA, 94143-0946,
|
|
Keywords:
|
Phase II Cancer Trials ; Two-stage Design ; Trial Duration ; Optimal Duration ; Endpoint Selection
|
|
Abstract:
|
Phase II cancer trials evaluate total response (TR) rate using a single-arm open-label design. Simon's two-stage design minimizes either the expected or the maximum number of patients. We haven't yet seen a formula to calculate duration of such a trial. In this paper, we derive a formula for distribution of trial duration, which considers the accrual rate, time to TR, futility rule, and efficacy rule. Our formulas work for both one and two stage designs. We further develop two applications of this formula: (1) an optimal time design that minimizes the expected trial duration; and (2) a method for selecting trial endpoints according to the expected durations. In many cases, the optimal time design is only slightly different from the Simon's optimal design. In conclusion, an explicit formula for trial duration provides an additional dimension of phase II cancer trial designs.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
