Estimation of Progression-Free Survival for All Treated Patients in the Randomized Discontinuation Trial Design
The randomized discontinuation trial (RDT) design is an enrichment-type design that has been used in a variety of diseases to evaluate the efficacy of new treatments. The RDT design seeks to select a more homogeneous group of patients, consisting of those who are more likely to show a treatment benefit if one exists. In oncology, the RDT design has been applied to evaluate the effects of cytostatic agents, that is, drugs that act primarily by slowing tumor growth rather than shrinking tumors. In the RDT design, all patients receive treatment during an initial, open-label run-in period of duration <italic>T.</italic> Patients with objective response (substantial tumor shrinkage) remain on therapy while those with early progressive disease are removed from the trial. Patients with stable disease (SD) are then randomized to either continue active treatment or switched to placebo. The main analysis compares outcomes, for example, progression-free survival (PFS), between the two randomized arms. As a secondary objective, investigators may seek to estimate PFS for all treated patients, measured from the time of entry into the study, by combining information from the run-in and post run-in periods. For <italic>t</italic> ⩽ <italic>T</italic>, PFS is estimated by the observed proportion of patients who are progression-free among all patients enrolled. For <italic>t</italic> > <italic>T</italic>, the estimate can be expressed as <inline-graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="utas_a_720900_o_ilm0001.gif"/>, where <inline-graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="utas_a_720900_o_ilm0002.gif"/> is the estimated probability of response during the run-in period, <inline-graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="utas_a_720900_o_ilm0003.gif"/> is the estimated probability of SD, and <inline-graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="utas_a_720900_o_ilm0004.gif"/> and <inline-graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="utas_a_720900_o_ilm0005.gif"/> are the Kaplan--Meier estimates of subsequent PFS in the responders and patients with SD randomized to continue treatment, respectively. In this article, we derive the variance of <inline-graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="utas_a_720900_o_ilm0006.gif"/>, enabling the construction of confidence intervals for both <italic>S</italic>(<italic>t</italic>) and the median survival time. Simulation results indicate that the method provides accurate coverage rates. An interesting aspect of the design is that outcomes during the run-in phase have a negative multinomial distribution, something not frequently encountered in practice.
Year of publication: |
2012
|
---|---|
Authors: | Karrison, Theodore G. ; Ratain, Mark J. ; Stadler, Walter M. ; Rosner, Gary L. |
Published in: |
The American Statistician. - Taylor & Francis Journals, ISSN 0003-1305. - Vol. 66.2012, 3, p. 155-162
|
Publisher: |
Taylor & Francis Journals |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Cruz-Marcelo, Alejandro, (2011)
-
An ANOVA model for dependent random measures
De Iorio, Maria, (2004)
-
Bayesian Inference for the Lead Time in Periodic Cancer Screening
Wu, Dongfeng, (2007)
- More ...