Response and Survival
Description
Software for conducting the simulations in "Using short-term response information to facilitate adaptive
randomization for survival clinical trials" by Xuelin Huang, Jing Ning, Yisheng Li, Elihu Estey, Jean-Pierre Issa
and Donald A. Berry in Statistics in Medicine 28(12): 1680-1689, 2009. The paper is available
here.
Please read the paper carefully before using the computer program. To use the program,
after you download it and source it in R, simply type AR_survival()
at the prompt.
The you will be asked to specify the parameters for the simulations.
The following gives is a short description of the background and method. Although achieving complete remission (CR)
is necessary for prolonging survival, it is not sufficient because patients may relapse shortly after
achieving CR. Many chemotherapies have improved CR rates. However, because of their short CR durations,
the improvements on CR rate do not translate into significant benefit on survival.
While most phase II trials use CR as the primary end point, phase III trials are usually required to
evaluate benefit to survival. This discrepancy is one of the major reasons for the high failure rates
of phase III trials. We propose a new design that utilizes information on both short-term response and
long-term survival. Progression-free survival is used as the primary outcome, and short-term
response data is used to shorten the long waiting time for reaching a decision in survival trials.
This is done by establishing a connection between the short-term response and long-term survival through
a Bayesian model. This model is first constructed by using prior clinical information, and then updated
continuously by the information accumulated in the ongoing trial. Compared to a trial using only
information on progression free survival, the new design uses fewer patients, takes less time,
and can more effectively assign patients to the better treatment arms. Compared
to a trial using only
the short term response information, the conclusion by the new design is more reliable and the trial
duration is only slightly longer.
The computer program was written by Jing Ning (Jing.Ning@uth.tmc.edu).
If you have questions, please contact Jing Ning or Xuelin Huang (xlhuang@mdanderson.org).