Investigating Brain Connectivity with Graph Neural Networks and GNNExplainer

TL;DR

This paper introduces a graph neural network framework to analyze EEG data during speech tasks, enabling disorder prediction, state differentiation, and connectivity analysis in schizophrenia and healthy controls.

Contribution

It presents a novel GNN-based approach for functional connectivity analysis in EEG data, improving disorder classification and interpretability in neuroscience.

Findings

Accurately differentiates schizophrenia patients from controls

Identifies characteristic connectivity patterns during speech tasks

Provides meaningful insights into brain functional connectivity

Abstract

Functional connectivity plays an essential role in modern neuroscience. The modality sheds light on the brain's functional and structural aspects, including mechanisms behind multiple pathologies. One such pathology is schizophrenia which is often followed by auditory verbal hallucinations. The latter is commonly studied by observing functional connectivity during speech processing. In this work, we have made a step toward an in-depth examination of functional connectivity during a dichotic listening task via deep learning for three groups of people: schizophrenia patients with and without auditory verbal hallucinations and healthy controls. We propose a graph neural network-based framework within which we represent EEG data as signals in the graph domain. The framework allows one to 1) predict a brain mental disorder based on EEG recording, 2) differentiate the listening state from the resting state for each group and 3) recognize characteristic task-depending connectivity. Experimental results show that the proposed model can differentiate between the above groups with state-of-the-art performance. Besides, it provides a researcher with meaningful information regarding each group's functional connectivity, which we validated on the current domain knowledge.