Parkinson's Disease Detection from Resting State EEG using Multi-Head Graph Structure Learning with Gradient Weighted Graph Attention Explanations

TL;DR

This paper introduces a novel graph neural network approach for Parkinson's disease detection from resting state EEG, emphasizing explainability and improved modeling of brain connectivity with limited data.

Contribution

It proposes a multi-head graph structure learner and gradient-weighted graph attention explanations to enhance PD detection and interpretability from EEG data.

Findings

Achieved 69.40% accuracy in subject-wise cross-validation.

Provided intuitive explanations of neural connectivity.

Addressed challenges of limited data and model explainability.

Abstract

Parkinson's disease (PD) is a debilitating neurodegenerative disease that has severe impacts on an individual's quality of life. Compared with structural and functional MRI-based biomarkers for the disease, electroencephalography (EEG) can provide more accessible alternatives for clinical insights. While deep learning (DL) techniques have provided excellent outcomes, many techniques fail to model spatial information and dynamic brain connectivity, and face challenges in robust feature learning, limited data sizes, and poor explainability. To address these issues, we proposed a novel graph neural network (GNN) technique for explainable PD detection using resting state EEG. Specifically, we employ structured global convolutions with contrastive learning to better model complex features with limited data, a novel multi-head graph structure learner to capture the non-Euclidean structure of EEG data, and a head-wise gradient-weighted graph attention explainer to offer neural connectivity insights. We developed and evaluated our method using the UC San Diego Parkinson's disease EEG dataset, and achieved 69.40% detection accuracy in subject-wise leave-one-out cross-validation while generating intuitive explanations for the learnt graph topology.