Graph Attention Networks for Detecting Epilepsy from EEG Signals Using Accessible Hardware in Low-Resource Settings

2025-07-20

AI Summary

In low-income countries, epilepsy diagnosis rates remain low due to severe neurologist shortages and the high cost of EEG equipment. To address this, we propose a lightweight, resource-aware automated epilepsy detection framework. Our method models EEG signals as spatiotemporal graphs and extends node-oriented Graph Attention Networks (GATs) to edge-level attention, thereby enhancing sensitivity to clinically critical functional pathways—particularly frontal-temporal connections. The framework integrates robust preprocessing for low-quality signals, interpretable biomarker discovery, and Raspberry Pi–based lightweight deployment. Evaluated on real-world clinical EEG data from Nigeria and Guinea-Bissau, our approach outperforms Random Forest and standard GCN baselines in both accuracy and robustness. Notably, it is the first to systematically identify clinically meaningful, epilepsy-specific functional connectivity patterns. This advances accessibility, equity, and interpretability in primary-level epilepsy screening.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Economics, Online Markets and Human Computation: Sustainability of Web economics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Goal: Epilepsy remains under-diagnosed in low-income countries due to scarce neurologists and costly diagnostic tools. We propose a graph-based deep learning framework to detect epilepsy from low-cost Electroencephalography (EEG) hardware, tested on recordings from Nigeria and Guinea-Bissau. Our focus is on fair, accessible automatic assessment and explainability to shed light on epilepsy biomarkers. Methods: We model EEG signals as spatio-temporal graphs, classify them, and identify interchannel relationships and temporal dynamics using graph attention networks (GAT). To emphasize connectivity biomarkers, we adapt the inherently node-focused GAT to analyze edges. We also designed signal preprocessing for low-fidelity recordings and a lightweight GAT architecture trained on Google Colab and deployed on RaspberryPi devices. Results: The approach achieves promising classification performance, outperforming a standard classifier based on random forest and graph convolutional networks in terms of accuracy and robustness over multiple sessions, but also highlighting specific connections in the fronto-temporal region. Conclusions: The results highlight the potential of GATs to provide insightful and scalable diagnostic support for epilepsy in underserved regions, paving the way for affordable and accessible neurodiagnostic tools.

Problem

• Detect epilepsy using low-cost EEG hardware
• Improve diagnosis in low-resource settings
• Explain epilepsy biomarkers via graph networks

Innovation

• Graph attention networks for EEG signal analysis
• Lightweight GAT architecture for RaspberryPi deployment
• Edge-focused GAT adaptation for connectivity biomarkers