|
Activity Number:
|
537
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Thursday, August 2, 2007 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #309653 |
|
Title:
|
Ensemble Methods for Classification of Patients for Personalized Medicine Using High-Dimensional Biomarkers
|
|
Author(s):
|
Hojin Moon*+ and Hongshik Ahn and Ralph L. Kodell and Songjoon Baek and Chien-Ju Lin and James J. Chen
|
|
Companies:
|
Food and Drug Administration and Stony Brook University and University of Arkansas for Medical Sciences and Food and Drug Administration and National Center for Toxicological Research and Food and Drug Administration
|
|
Address:
|
3900 NCTR RD, Jefferson, AR, 72079,
|
|
Keywords:
|
Classification tree ; Cross-validation ; Ensemble classifiers ; Majority voting ; Random partitions ; Resampling
|
|
Abstract:
|
Personalized medicine is defined by the use of genomic signatures of patients in a target population for assignment of more effective therapies as well as better diagnosis and earlier interventions that might prevent or delay disease. Classification algorithms can be used for prediction of response to therapy to help individualize clinical assignment of treatment. An ensemble classifier built from the optimal number of random partitions of the feature space will be presented. This classification algorithm can overcome the problem of having fewer samples than predictors. The algorithm is applied to several published genomic data sets to classify patients into risk/benefit categories. Based on cross-validated results for several high-dimensional data sets, our algorithm is consistently one of the best classification algorithms.
|
