|
Activity Number:
|
23
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, July 29, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #309892 |
|
Title:
|
Robustness of Cancer Risk Prediction Using Microarrays
|
|
Author(s):
|
Chiang-Ching Huang*+ and Irene Helenowski
|
|
Companies:
|
Northwestern University and Northwestern University
|
|
Address:
|
680 N. Lake Shore Dr., Suite 1102, Chicago, IL, 60611,
|
|
Keywords:
|
cross validation ; cancer ; risk stratification ; sample size ; microarray
|
|
Abstract:
|
Microarrays have demonstrated its utility in cancer research for better risk stratification. However, classifiers constructed from several cancer studies cannot be confirmed in subsequent studies, raising the concern regarding the robustness of cancer classification using microarrays. This hurdle is largely due to the limited number of tumors under study and cancer heterogeneity evidenced by the gene expression profiles. We propose to use a sequential cross validation approach to investigate the sample size required to achieve statistical robustness of a molecular classifier. This approach also serves to identify tumors that can not be correctly classified by the gene expression profiles of tumor tissues alone. Our result suggests current sample size calculation for microarray studies, especially in the prognosis problem, could be underestimated.
|
- 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 2007 program |
