Early Prediction of Epileptic Seizure Based on the BNLSTM-CASA Model

Mengnan Ma,Ziyi Chen,Yi Zhou,Qianxiang Mao,Yao Wang,Zhen Zhang,Xingyu Li,Yinlin Cheng

doi:10.1109/access.2021.3084635

Abstract

Epilepsy is one of the world's most common neurological diseases. Reliable early prediction and warning of seizures can provide timely treatment for patients with epilepsy, and improve their quality of life. Compared with most hand-designed prediction methods, an automatic prediction model that can process the original electroencephalogram (EEG) signals directly and take into account the leads optimization problem is needed. In this paper, we proposed an end-to-end automatic seizure prediction model based on the Batch Normalization Long Short Term Memory networks (BNLSTM) and Channel and Spatial attention (CASA). Firstly, raw EEG signals without any preprocessing are used as the input to the system, which can reduce the computation amount. Secondly, BNLSTM and CASA retained the time and spatial information of the raw EEG data respectively. Channel attention (CA) achieved the automatic optimization of EEG full-lead data and improved the prediction accuracy. Spatial attention (SA) achieved the adaptive learning of feature parameters. Finally, a fully connected layer is applied to predict the seizures. The performance of the seizure prediction model we proposed is evaluated on the data of 14 patients with Area Under the Curve (AUC) of 0.986, accuracy (Acc) of 0.956, specificity (Spe) of 0.968, and sensitivity (Sen) of 0.942. In addition, the proposed method provided an accurate prediction for all 50 seizures of the other 5 patients in the generalization dataset. Experimental results show that the proposed model has a certain generalization performance, which can provide a reliable basis for early warning of epileptic seizures.

Highlights

Epilepsy is a chronic cerebral dysfunction syndrome
The main contributions of our work are the following aspects: (1) We propose a novel seizure prediction model based on the Batch Normalization Long Short Term Memory networks (BNLSTM) and Channel and Spatial attention (CASA) architecture, which can directly process the original EEG of all leads and retain as much temporal and spatial information of EEG signals as possible
The epileptic seizure prediction model we proposed achieved Area Under the Curve (AUC) of 0.986, Acc of 0.956, Spe of 0.968, and Sen of 0.942

Summary

Introduction

Epilepsy is a chronic cerebral dysfunction syndrome. 65 million people worldwide suffered from epilepsy, accounting for about 1% of the world’s population [1]. The seizures of the patients with epilepsy are transient, repetitive, and unpredictable. Patients spend most of their lives unsure of when and where epilepsy will occur [2]–[5]. Uncontrollability is a major problem with epilepsy. About a third of patients have drug-resistant epilepsy. It is of great practical significance to design a reliable epileptic seizure

Methods

Results

Conclusion