Classifying post-traumatic stress disorder using the magnetoencephalographic connectome and machine learning

Abstract

Given the subjective nature of conventional diagnostic methods for post-traumatic stress disorder (PTSD), an objectively measurable biomarker is highly desirable; especially to clinicians and researchers. Macroscopic neural circuits measured using magnetoencephalography (MEG) has previously been shown to be indicative of the PTSD phenotype and severity. In the present study, we employed a machine learning-based classification framework using MEG neural synchrony to distinguish combat-related PTSD from trauma-exposed controls. Support vector machine (SVM) was used as the core classification algorithm. A recursive random forest feature selection step was directly incorporated in the nested SVM cross validation process (CV-SVM-rRF-FS) for identifying the most important features for PTSD classification. For the five frequency bands tested, the CV-SVM-rRF-FS analysis selected the minimum numbers of edges per frequency that could serve as a PTSD signature and be used as the basis for SVM modelling. Many of the selected edges have been reported previously to be core in PTSD pathophysiology, with frequency-specific patterns also observed. Furthermore, the independent partial least squares discriminant analysis suggested low bias in the machine learning process. The final SVM models built with selected features showed excellent PTSD classification performance (area-under-curve value up to 0.9). Testament to its robustness when distinguishing individuals from a heavily traumatised control group, these developments for a classification model for PTSD also provide a comprehensive machine learning-based computational framework for classifying other mental health challenges using MEG connectome profiles.

Resting‐state magnetoencephalography source magnitude imaging with deep‐learning neural network for classification of symptomatic combat‐related mild traumatic brain injury

“…This may entail refinement of DL algorithms along with testing different features of rs‐MEG, to identify the most stable classifiers of mTBI or cmTBI conditions. If successful, the 3D MEGNET approach could also be extended to the prediction of recovery from PCS using longitudinal study designs or to classification of other clinical conditions that can be challenging to diagnose such as PTSD, which was recently explored using rs‐MEG functional connectivity measures and an SVM machine‐learning approach (Zhang, Richardson, & Dunkley, 2020).…”

The Impact of Psychopathology, Social Adversity and Stress-relevant DNAm on Prospective Risk for Post-traumatic Stress: A Machine Learning Approach

“…Using these identified factors, ML models predicted the prospective risk of PTSD with high accuracy. We could not compare the accuracy of models in this study with existing approaches for PTSD (Dean et al, 2019; Karstoft et al, 2015; Schultebraucks et al, 2020; Wshah et al, 2019; Zhang et al, 2020) because this prior work used classification approaches, whereas we applied a regression task on a continuous outcome, PTSS, and different performance measures are used for classification and regression.…”

“…ML refers to those approaches that do not use explicit programming but instead learn from data and experience to make decisions or predictions. For example, ML has recently been used to differentiate between combat-related PTSD and trauma-exposed controls (Zhang, Richardson, & Dunkley, 2020), and for diagnosing PTSD (Dean et al, 2019). With respect to PTSD, identifying factors that prospectively predict PTSD can potentially help target such factors to reduce the likelihood of PTSD following a traumatic event, and/or reduce the likelihood of a more chronic course of PTSD.…”

Magnetoencephalography in the Detection and Characterization of Brain Abnormalities Associated with Traumatic Brain Injury: A Comprehensive Review

“…In a step closer to using MEG clinically to diagnose PTSD, Zhang et al (2020) developed a machine learning classifier to identify military service members with PTSD [ 29 ]. They compared resting-state MEG data from 23 soldiers diagnosed with PTSD with those from 21 soldiers without PTSD but who had similar traumatic experiences in battlefield deployment.…”