SlimSeiz: Efficient Channel-Adaptive Seizure Prediction Using a Mamba-Enhanced Network

TL;DR

SlimSeiz is a lightweight, channel-adaptive neural network framework for seizure prediction that reduces electrode channels while maintaining high accuracy, making it suitable for mobile applications.

Contribution

Introduces a novel adaptive channel selection and lightweight neural network framework for efficient seizure prediction across different EEG datasets.

Findings

Achieves 94.8% accuracy with only 8 channels on CHB-MIT dataset.

Uses 21.2K parameters, outperforming larger models.

Validates effectiveness on a new dataset from Shanghai Renji Hospital.

Abstract

Epileptic seizures cause abnormal brain activity, and their unpredictability can lead to accidents, underscoring the need for long-term seizure prediction. Although seizures can be predicted by analyzing electroencephalogram (EEG) signals, existing methods often require too many electrode channels or larger models, limiting mobile usability. This paper introduces a SlimSeiz framework that utilizes adaptive channel selection with a lightweight neural network model. SlimSeiz operates in two states: the first stage selects the optimal channel set for seizure prediction using machine learning algorithms, and the second stage employs a lightweight neural network based on convolution and Mamba for prediction. On the Children's Hospital Boston-MIT (CHB-MIT) EEG dataset, SlimSeiz can reduce channels from 22 to 8 while achieving a satisfactory result of 94.8% accuracy, 95.5% sensitivity, and 94.0% specificity with only 21.2K model parameters, matching or outperforming larger models' performance. We also validate SlimSeiz on a new EEG dataset, SRH-LEI, collected from Shanghai Renji Hospital, demonstrating its effectiveness across different patients. The code and SRH-LEI dataset are available at https://github.com/guoruilu/SlimSeiz.