Classification of Trauma-Related Outcomes in US Veterans Using Magnetoencephalography (MEG)

Previous research has demonstrated highly accurate classification of veterans with posttraumatic stress disorder (PTSD) and controls based on synchronous neural interactions (SNI), highlighting the utility of SNI as a biomarker of PTSD. Here we extend that research to classify additional trauma-related outcomes including subthreshold PTSD, partial recovery, and full recovery according to SNI. A total of 219 U.S. veterans completed diagnostic interviews and underwent a magnetoencephalography (MEG) scan from which SNI was computed. Linear discriminant analysis was used to classify the PTSD and control brains, achieving 100% accuracy. That discriminant function was then used to classify each brain in the subthreshold PTSD, partial recovery, and full recovery diagnostic groups as PTSD or Control. All of the subthreshold PTSD diagnostic group were classified as PTSD, as were three-quarters of the partial recovery group. Findings regarding the full recovery group were mixed, documenting variability in the functional brain status of PTSD recovery. The results of the present study add to the literature supporting the discriminatory power of MEG SNI and demonstrate the utility of SNI as a biomarker of various PTSD-related trajectories.