Epilepsy prediction through optimized multidimensional sample entropy and Bi-LSTM. (February 2021)

• Record Type: Journal Article
• Authors: Zhang, Qizhong; Ding, Ji; Kong, Wanzeng; Liu, Yang; Wang, Qian; Jiang, Tiejia
• Is Part Of: Biomedical signal processing and control. Volume 64(2021)
• Publication Date: 2021-02
• Subjects: M-SampEn multidimensional sample entropy -- EEG electroencephalogram -- Bi-LSTM bidirectional long short-term memory -- PPV positive predictive value -- SampEn sample entropy -- FPR false prediction rate; Epilepsy -- Prediction -- Electroencephalograms -- Sample entropy -- Bi-LSTM; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2020.102293
• Languages: English
• ISSNs: 1746-8094

Abstract

Graphical abstract: Highlights: Multidimensional sample entropy combined with multichannel EEG signal calculation can show the difference between pre-ictal and ictal better than ordinary sample entropy. The calculation speed of multidimensional sample entropy decreases with the increase of time series, and the calculation efficiency can be improved after optimization, which is more suitable for clinical diagnosis. Bidirectional long short-term memory can be used for both prediction and classification. Bidirectional long short-term memory neural network provides a epilepsy prediction method that predicts first and then classifies. Abstract: Objective: Epilepsy is a repetitive and transient brain dysfunction caused by abnormal discharge of brain neurons. Sudden epileptic seizures may affect the daily life of patients. Therefore, real-time monitoring and prediction of epilepsy has important clinical meaning. Methods: In this paper, the characteristics of M-SampEn were extracted from 23 EEG signals and M-SampEn was specifically optimized to enhance efficiency. Then the Bi-LSTM may predict the trend of M-SampEn. The predicted M-SampEn was classified to determine if an epileptic seizure is imminent. Results: Comparing the classification accuracy, sensitivity, specificity and PPV of SampEn and M-SampEn, M-SampEn is found to have better performance. The prediction time is 5 minutes. The results demonstrate an accuracy of 80.09% and a FPR of 0.26/h for epileptic seizure prediction. Comparison with existing method(s): The optimized multidimensional sample entropy presented in this paper is more able to distinguish between the normal state and ictal of epilepsy. This paper also proposes a backward prediction method that is different from traditional epileptic seizure prediction. Conclusions: The research provides a high comprehensive performance epileptic prediction method with a F1 score of 0.83. The accuracy of 80.09% and the FPR of 0.26/h prove that the proposed method is able to predict seizures.