REST: Efficient and Accelerated EEG Seizure Analysis through Residual State Updates

TL;DR

This paper presents REST, a graph-based residual state update method that significantly accelerates EEG seizure detection while reducing memory usage, enabling real-time clinical applications.

Contribution

REST introduces a novel graph neural network with residual state updates for efficient, accurate, and real-time EEG seizure analysis.

Findings

9-fold faster inference than existing models

Substantially lower memory requirements

High accuracy in seizure detection and classification

Abstract

EEG-based seizure detection models face challenges in terms of inference speed and memory efficiency, limiting their real-time implementation in clinical devices. This paper introduces a novel graph-based residual state update mechanism (REST) for real-time EEG signal analysis in applications such as epileptic seizure detection. By leveraging a combination of graph neural networks and recurrent structures, REST efficiently captures both non-Euclidean geometry and temporal dependencies within EEG data. Our model demonstrates high accuracy in both seizure detection and classification tasks. Notably, REST achieves a remarkable 9-fold acceleration in inference speed compared to state-of-the-art models, while simultaneously demanding substantially less memory than the smallest model employed for this task. These attributes position REST as a promising candidate for real-time implementation in clinical devices, such as Responsive Neurostimulation or seizure alert systems.