About this item:

16 Views | 5 Downloads

Author Notes:

Corresponding Author 101 Woodruff Circle NE, Suite 4000 Atlanta, GA 30322 Tel: 404-727-5528, Fax: 404-727-3233. rcraddo@emory.edu, xhu@bme.emory.edu.

We would like to thank Andy James and Stephen LaConte for their countless suggestions, Rebecca de Mayo for study coordination, Robert Smith for MRI operation, Julie Kozarsky for editorial help, and Boadie Dunlop, Ed Craighead, and Ebrahim Haroon for patient recruitment and treatment.

Subjects:

Research Funding:

This research was supported by NIMH P50 MH077083, 1R01MH073719 and Emory URC2004113.

Keywords:

  • Science & Technology
  • Life Sciences & Biomedicine
  • Radiology, Nuclear Medicine & Medical Imaging
  • functional connectivity
  • multivariate pattern analysis (MVPA)
  • support vector classification (SVC)
  • feature selection
  • disease state prediction
  • biomarker
  • major depressive disorder (MDD)
  • SUPPORT VECTOR MACHINES
  • HUMAN BRAIN
  • FMRI DATA
  • COMPONENT ANALYSIS
  • CINGULATE CORTEX
  • PATTERN-ANALYSIS
  • SINGLE-SUBJECT
  • CLASSIFICATION
  • MRI
  • DEPRESSION

Disease State Prediction From Resting State Functional Connectivity

Tools:

Journal Title:

Magnetic Resonance in Medicine

Volume:

Volume 62, Number 6

Publisher:

, Pages 1619-1628

Type of Work:

Article | Post-print: After Peer Review

Abstract:

The application of multivoxel pattern analysis methods has attracted increasing attention, particularly for brain state prediction and real-time functional MRI applications. Support vector classification is the most popular of these techniques, owing to reports that it has better prediction accuracy and is less sensitive to noise. Support vector classification was applied to learn functional connectivity patterns that distinguish patients with depression from healthy volunteers. In addition, two feature selection algorithms were implemented (one filter method, one wrapper method) that incorporate reliability information into the feature selection process. These reliability feature selections methods were compared to two previously proposed feature selection methods. A support vector classifier was trained that reliably distinguishes healthy volunteers from clinically depressed patients. The reliability feature selection methods outperformed previously utilized methods. The proposed framework for applying support vector classification to functional connectivity data is applicable to other disease states beyond major depression.

Copyright information:

© 2009 Wiley-Liss, Inc.

Export to EndNote