|
Activity Number:
|
361
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #304211 |
|
Title:
|
How Much Information Can a Genomic Classifier Based on Gene Expression Add to Models Based on Clinical Covariates Alone?
|
|
Author(s):
|
Samir Lababidi*+
|
|
Companies:
|
FDA
|
|
Address:
|
1350 Piccard Drive, Rockville, MD, 20850,
|
|
Keywords:
|
microarrays ; gene expression ; prognostic ; added clinical effect ; genomic classifier ; MAQC
|
|
Abstract:
|
The early papers in microarray gene expression promised better prediction in cancer outcome classification than what have been done before for prognostic and diagnostic medicine. However, it became clear later that the actual gain in predictive ability due to the use of gene expression classifiers practices may have been sometimes exaggerated and in need of careful evaluation. Here in this talk, we will present statistical analysis methods for evaluating models based on genomic classifiers and compare their performance with models based on clinical covariates alone under different scenarios. Models are provided by over 30 different analysis teams for three clinical studies from the MicroArray Quality Control Phase II (MAQC-II) Project in a collaborative effort by FDA, Industry, and Academia to come up with "best practices" on microarray data analysis.
|
- 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 |
