Home
Scholarly Works
EEG Microstates In PTSD: Using Machine Learning To...
Preprint

EEG Microstates In PTSD: Using Machine Learning To Identify Neuromarkers

Abstract

Microstates offer a promising framework to study whole-brain dynamics in the resting-state electroencephalogram (EEG). However, microstate dynamics have yet to be investigated in post-traumatic stress disorder (PTSD), despite research demonstrating resting-state alterations in PTSD. We performed microstate-based segmentation of resting-state EEG in a clinical population of participants with PTSD (N = 61) and a neurotypical control group (N = 61). Microstate-based measures (i.e., occurrence, mean duration, time coverage) were compared group-wise using broadband (1-30 Hz) and frequency-specific (i.e., delta, theta, alpha, beta bands) decompositions. In the broadband comparisons, the centro-posterior maximum microstate (map E) occurred significantly less frequently (d = -0.64, p FWE = 0.03) and had a significantly shorter mean duration in participants with PTSD as compared to controls (d = -0.71, p> FWE < 0.01). These differences were reflected in the narrow frequency bands as well, with lower frequency bands like delta (d = -0.78, p FWE < 0.01), theta ( d = -0.74, p FWE = 0.01), and alpha (d = -0.65, p FWE = 0.02) repeating these group-level trends, only with larger effect sizes. Interestingly, a support vector machine classification analysis comparing broadband and frequency-specific measures revealed that models containing only alpha band features significantly out-perform broadband models. When classifying PTSD, the classification accuracy was 76% and 65% for the alpha band and the broadband model, respectively (p = 0.03). Taken together, we provide original evidence supporting the clinical utility of microstates as diagnostic markers of PTSD, and demonstrate that filtering EEG into distinct frequency bands significantly improves microstate-based classification of a psychiatric disorder.Funding Information: This work was supported by infrastructure funds from the Canada Foundation for Innovation Grant (JT; grant number: 31724) and Lawson Health Research Institute, as well as operating funds from the Canadian Institute of Military and Veteran Health Research (CIMWHR), Green Shield Canada, the Centre of Excellence on PTSD, and the Canadian Institutes of Health Research (CIHR) (RAL and MCM; grant number: 148784). RAL is supported by the Harris-Woodman Chair in Psyche and Soma at Western University, while MCM is supported by the Homewood Chair in Mental Health and Trauma at McMaster University. BAT is supported by Mitacs Elevate funding, partnered generously by Homewood Research Institute.Conflict of Interests: No known conflicts of interest to discloseEthical Approval: Investigations were approved by the Research Ethics Board at Western University in accordance with the Code of Ethics of the World Medical Association (Declaration of Helsinki) for experiments involving human participants.

Authors

Terpou BA; Shaw SB; Théberge J; Férat V; Michel CM; McKinnon MC; Lanius R; Ros T

Publication date

January 1, 2022

DOI

10.2139/ssrn.4061516

Preprint server

SSRN Electronic Journal

Labels

Sustainable Development Goals (SDG)

View published work (Non-McMaster Users)

Contact the Experts team