Abstract:
|
The patient population in oncology is highly heterogeneous and the patient exposure to cancer treatments varies. Cancer treatments have evolved from a single mechanism of action to multiple mechanisms of actions. With the advancement of oncology therapy, a proportion of patients are expected to be cured or to have long-term survivals in certain diseases. Data generated from this kind of studies post strong challenges in using traditional single distribution model. The median survival time is a key parameter in the planning and interpretation of result for an oncology study. Thus, accurately estimating the median survival time is very important. In this talk, we explore the mixture model, which includes the cure model as its special case, in modeling the time-to-event data in oncology studies. Simulation and real data are used to demonstrate the benefit of using mixture model.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.