Detection of Low Resilience Using Data-Driven Effective Connectivity Measures

Abstract

Conventional thresholding techniques for graph theory analysis, such as absolute, proportional and mean degree, have often been used in characterizing human brain networks under different mental disorders, such as mental stress. However, these approaches may not always be reliable as conventional thresholding approaches are subjected to human biases. Using a mental resilience study, we investigate if data-driven thresholding techniques such as Global Cost Efficiency (GCE-abs) and Orthogonal Minimum Spanning Trees (OMSTs) could provide equivalent results, whilst eliminating human biases. We implemented Phase Slope Index (PSI) to compute effective brain connectivity, and applied data-driven thresholding approaches to filter the brain networks in order to identify key features of low resilience within a cohort of healthy individuals. Our dataset encompassed resting-state EEG recordings gathered from a total of 36 participants (31 females and 5 males). Relevant features were extracted to train and validate a classifier model (Support Vector Machine, SVM). The detection of low stress resilience among healthy individuals using the SVM model scores an accuracy of 80.6% with GCE-abs, and 75% with OMSTs, respectively.

Keywords

• Electroencephalography (EEG)
• graph theory analysis
• mental stress
• network thresholding
• orthogonal minimal spanning trees (OMSTs)
• resilience