Classifying heterogeneous presentations of PTSD via the default mode, central executive, and salience networks with machine learning

Andrew A. Nicholson; Sherain Harricharan; Maria Densmore; Richard W.J. Neufeld; Tomas Ros; Margaret C. McKinnon; Paul A. Frewen; Jean Théberge; Rakesh Jetly; David Pedlar; Ruth A. Lanius

NeuroImage: Clinical (Jan 2020)

Classifying heterogeneous presentations of PTSD via the default mode, central executive, and salience networks with machine learning

Andrew A. Nicholson,
Sherain Harricharan,
Maria Densmore,
Richard W.J. Neufeld,
Tomas Ros,
Margaret C. McKinnon,
Paul A. Frewen,
Jean Théberge,
Rakesh Jetly,
David Pedlar,
Ruth A. Lanius

Affiliations

Andrew A. Nicholson: Department of Cognition, Emotion and Methods in Psychology, University of Vienna, Austria; Department of Psychiatry and Behavioural Neurosciences, McMaster University, Hamilton, ON, Canada; Corresponding author.
Sherain Harricharan: Department of Psychiatry and Behavioural Neurosciences, McMaster University, Hamilton, ON, Canada
Maria Densmore: Department of Psychiatry, Western University, London, ON, Canada; Imaging Division, Lawson Health Research Institute, London, ON, Canada
Richard W.J. Neufeld: Department of Psychiatry, Western University, London, ON, Canada; Department of Psychology, Western University, London, ON, Canada; Department of Medical Imaging, Western University, London, ON, Canada
Tomas Ros: Department of Neuroscience, University of Geneva, Switzerland
Margaret C. McKinnon: Department of Psychiatry and Behavioural Neurosciences, McMaster University, Hamilton, ON, Canada; Mood Disorders Program, St. Joseph's Healthcare, Hamilton, ON, Canada; Homewood Research Institute, Guelph, ON, Canada
Paul A. Frewen: Department of Psychiatry, Western University, London, ON, Canada; Department of Neuroscience, Western University, London, ON, Canada
Jean Théberge: Department of Psychiatry, Western University, London, ON, Canada; Department of Medical Imaging, Western University, London, ON, Canada; Imaging Division, Lawson Health Research Institute, London, ON, Canada; Department of Diagnostic Imaging, St. Joseph's Health Care, London, ON, Canada
Rakesh Jetly: Canadian Forces, Health Services, Ottawa, Ontario, Canada
David Pedlar: Canadian Institute for Military and Veteran Health Research (CIMVHR), Canada
Ruth A. Lanius: Department of Psychiatry, Western University, London, ON, Canada; Department of Neuroscience, Western University, London, ON, Canada; Imaging Division, Lawson Health Research Institute, London, ON, Canada

Journal volume & issue: Vol. 27
p. 102262

Abstract

Read online

Intrinsic connectivity networks (ICNs), including the default mode network (DMN), the central executive network (CEN), and the salience network (SN) have been shown to be aberrant in patients with posttraumatic stress disorder (PTSD). The purpose of the current study was to a) compare ICN functional connectivity between PTSD, dissociative subtype PTSD (PTSD+DS) and healthy individuals; and b) to examine the use of multivariate machine learning algorithms in classifying PTSD, PTSD+DS, and healthy individuals based on ICN functional activation. Our neuroimaging dataset consisted of resting-state fMRI scans from 186 participants [PTSD (n = 81); PTSD + DS (n = 49); and healthy controls (n = 56)]. We performed group-level independent component analyses to evaluate functional connectivity differences within each ICN. Multiclass Gaussian Process Classification algorithms within PRoNTo software were then used to predict the diagnosis of PTSD, PTSD+DS, and healthy individuals based on ICN functional activation. When comparing the functional connectivity of ICNs between PTSD, PTSD+DS and healthy controls, we found differential patterns of connectivity to brain regions involved in emotion regulation, in addition to limbic structures and areas involved in self-referential processing, interoception, bodily self-consciousness, and depersonalization/derealization. Machine learning algorithms were able to predict with high accuracy the classification of PTSD, PTSD+DS, and healthy individuals based on ICN functional activation. Our results suggest that alterations within intrinsic connectivity networks may underlie unique psychopathology and symptom presentation among PTSD subtypes. Furthermore, the current findings substantiate the use of machine learning algorithms for classifying subtypes of PTSD illness based on ICNs.

Published in NeuroImage: Clinical

ISSN: 2213-1582 (Online)
Publisher: Elsevier
Country of publisher: Netherlands
LCC subjects: Medicine: Medicine (General): Computer applications to medicine. Medical informatics; Medicine: Internal medicine: Neurosciences. Biological psychiatry. Neuropsychiatry: Neurology. Diseases of the nervous system
Website: http://www.journals.elsevier.com/neuroimage-clinical/

About the journal