Support vector machine classification of major depressive disorder using diffusion-weighted neuroimaging and graph theory

Matthew D Sacchet; Gautam Prasad; Lara C Foland-Ross; Paul M Thompson; Ian H Gotlib

doi:10.3389/fpsyt.2015.00021

Support vector machine classification of major depressive disorder using diffusion-weighted neuroimaging and graph theory

Front Psychiatry. 2015 Feb 18:6:21. doi: 10.3389/fpsyt.2015.00021. eCollection 2015.

Authors

Matthew D Sacchet¹, Gautam Prasad², Lara C Foland-Ross³, Paul M Thompson⁴, Ian H Gotlib¹

Affiliations

¹ Neurosciences Program, Stanford University , Stanford, CA , USA ; Department of Psychology, Stanford University , Stanford, CA , USA.
² Department of Psychology, Stanford University , Stanford, CA , USA ; Imaging Genetics Center, Institute for Neuroimaging and Informatics, Keck School of Medicine of the University of Southern California , Los Angeles, CA , USA.
³ Department of Psychology, Stanford University , Stanford, CA , USA.
⁴ Imaging Genetics Center, Institute for Neuroimaging and Informatics, Keck School of Medicine of the University of Southern California , Los Angeles, CA , USA.

Abstract

Recently, there has been considerable interest in understanding brain networks in major depressive disorder (MDD). Neural pathways can be tracked in the living brain using diffusion-weighted imaging (DWI); graph theory can then be used to study properties of the resulting fiber networks. To date, global abnormalities have not been reported in tractography-based graph metrics in MDD, so we used a machine learning approach based on "support vector machines" to differentiate depressed from healthy individuals based on multiple brain network properties. We also assessed how important specific graph metrics were for this differentiation. Finally, we conducted a local graph analysis to identify abnormal connectivity at specific nodes of the network. We were able to classify depression using whole-brain graph metrics. Small-worldness was the most useful graph metric for classification. The right pars orbitalis, right inferior parietal cortex, and left rostral anterior cingulate all showed abnormal network connectivity in MDD. This is the first use of structural global graph metrics to classify depressed individuals. These findings highlight the importance of future research to understand network properties in depression across imaging modalities, improve classification results, and relate network alterations to psychiatric symptoms, medication, and comorbidities.

Keywords: diffusion-weighted imaging; graph theory; major depressive disorder; small world network; subgenual anterior cingulate cortex; support vector machine.

Abstract

Grants and funding