Decoding the Stressed Brain with Geometric Machine Learning

TL;DR

This paper presents a novel geometric machine learning framework using EEG data and graph convolutional networks to objectively detect stress, outperforming traditional methods and improving interpretability.

Contribution

It introduces a new graph-based approach combining structural and functional connectivity for stress detection from EEG signals.

Findings

ST-GCN outperforms standard models on all metrics

Enhanced interpretability through ablation analyses

Paves the way for objective stress detection

Abstract

Stress significantly contributes to both mental and physical disorders, yet traditional self-reported questionnaires are inherently subjective. In this study, we introduce a novel framework that employs geometric machine learning to detect stress from raw EEG recordings. Our approach constructs graphs by integrating structural connectivity (derived from electrode spatial arrangement) with functional connectivity from pairwise signal correlations. A spatio-temporal graph convolutional network (ST-GCN) processes these graphs to capture spatial and temporal dynamics. Experiments on the SAM-40 dataset show that the ST-GCN outperforms standard machine learning models on all key classification metrics and enhances interpretability, explored through ablation analyses of key channels and brain regions. These results pave the way for more objective and accurate stress detection methods.