|
Activity Number:
|
341
|
|
Type:
|
Invited
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
International Chinese Statistical Association
|
| Abstract - #302974 |
|
Title:
|
Analysis of Complex and High-Dimensional Data
|
|
Author(s):
|
DuBois Bowman*+
|
|
Companies:
|
Emory University
|
|
Address:
|
Department of Biostatistics and Bioinformatics, Atlanta, GA, 30322,
|
|
Keywords:
|
brain imaging ; fMRI ; classification ; prediction ; depression
|
|
Abstract:
|
Functional magnetic resonance imaging (fMRI) has played a critical role in elucidating the pathophysiology of major psychiatric disorders. fMRI also has the potential to improve our understanding of the neural processing changes associated with treatment for these disorders. In this talk, we present pattern discovery methods for high-dimensional fMRI data from individuals with major depression. Specifically, we seek to identify dissociable patterns of resting state brain activity associated with either a pharmacologic treatment for major depression or cognitive behavioral therapy. Our approach leverages the discriminatory power of post-treatment changes in brain activity revealed from fMRI scans while also incorporating individualized patient history. We utilize cross-validation to train and test our classification procedures.
|
