Abstract Details
Activity Number:
|
545
|
Type:
|
Topic Contributed
|
Date/Time:
|
Wednesday, August 6, 2014 : 2:00 PM to 3:50 PM
|
Sponsor:
|
Biometrics Section
|
Abstract #313409
|
|
Title:
|
On Risk Prediction with Longitudinal Markers
|
Author(s):
|
Yingye Zheng*+
|
Companies:
|
Fred Hutchinson Cancer Research Center
|
Keywords:
|
|
Abstract:
|
in order to monitor disease progression among patients diagnosed with cancer who chose to be on active surveillance, frequently repeated measurements are obtained. The primary inferential objectives are to identify predictive algorithms for time to event occurrence based on relevant longitudinal processes, and to assess the utility of such an algorithm when used for aiding medical decision regarding disease monitoring plan and treatment choices. A key issue is how to assess the risk of progression as a function of marker history. Joint modeling the longitudinal marker process via a random effect model and failure time process via a time-varying covariate hazard model is often considered. But such a survival model does not directly facilitate the estimation of hazard at s given marker history up to the time a clinical decision is make. As an alternative we consider longitudinal models for t-year survival that is computationally simple yet sufficiently flexible to capture how the underlying distribution of the residual life conditional on the updated marker information change dynamically over time. Simulation studies are used to evaluate the predictive performanc
|
Authors who are presenting talks have a * after their name.
Back to the full JSM 2014 program
|
2014 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Professional Development program, please contact the Education Department.
The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Copyright © American Statistical Association.