Automated Seizure Onset Detection and Prediction Using EEG: A Comprehensive Model with Multiscale Analysis and Machine Learning

Hassan Aridy; Rayan Abu-Hanifa; Jabbar Thaqib; Naser Al-athiry

Authors

Hassan Aridy New Technologies Department, Al Iraqia University, Baghdad, Iraq
Rayan Abu-Hanifa New Technologies Department, Al Iraqia University, Baghdad, Iraq
Jabbar Thaqib Electrical and Electronic Engineering Department, Al Iraqia University, Baghdad, Iraq
Naser Al-athiry University of Information Technology and Communications, Iraq

Abstract

Accurate and timely detection of seizure onset is crucial for effectively managing epilepsy. This paper presents a novel and fully specified model for automated seizure onset detection and prediction based on electroencephalography (EEG) measurements. The model is evaluated using two widely recognized EEG databases, namely Freiburg (intracranial EEG) and CHB-MIT (scalp EEG), to assess its performance against state-of-the-art models. The proposed model incorporates four key components to enhance its effectiveness: (1) multiscale principal component analysis for EEG de-noising to improve signal quality, (2) EEG signal decomposition using empirical mode decomposition, discrete wavelet transform, or wavelet packet decomposition to capture relevant signal characteristics, (3) statistical measures for extracting informative features, and (4) machine learning algorithms for accurate classification. Experimental results demonstrate the superior performance of our model in comparison to existing approaches. It achieves an impressive overall accuracy of 100% in distinguishing between ictal and inter-ictal EEG for both the Freiburg and CHB-MIT databases. Furthermore, the model exhibits high accuracy in seizure onset prediction, successfully discriminating between inter-ictal, pre-ictal, and ictal EEG states with an accuracy of 99.78% and distinguishing between inter-ictal and pre-ictal EEG states with an accuracy of 99.72%. Importantly, the proposed model's versatility extends beyond seizure detection and prediction. It can be applied to other classification tasks involving bio-signals, such as electromyography (EMG) and electrocardiography (ECG). Thus, our model holds promise as a comprehensive tool for various biomedical signal analysis applications.

References

Alickovic E, Kevric J, Subasi A. Performance evaluation of empirical mode decomposition, discrete wavelet transform, and wavelet packed decomposition for automated epileptic seizure detection and prediction. Biomedical signal processing and control. 2018 Jan 1;39:94-102.

Slimen IB, Boubchir L, Mbarki Z, Seddik H. EEG epileptic seizure detection and classification based on dual-tree complex wavelet transform and machine learning algorithms. Journal of biomedical research. 2020 May;34(3):151.

A. Najari, F. Shabani, and M. Hosseynzadeh, "INTEGRATED INTELLIGENT CONTROL SYSTEM DESIGN TO IMPROVE VEHICLE ROTATIONAL STABILITY USING ACTIVE DIFFERENTIAL," Acta Technica Corviniensis-Bulletin of Engineering, vol. 14, no. 1, pp. 79-82, 2021.

M. Cheraghifard, G. Taghizadeh, M. Akbarfahimi, A. M. Eakman, S.-H. Hosseini, and A. Azad, "Psychometric properties of Meaningful Activity Participation Assessment (MAPA) in chronic stroke survivors," Topics in Stroke Rehabilitation, vol. 28, no. 6, pp. 422-431, 2021.

Carvalho VR, Moraes MF, Braga AP, Mendes EM. Evaluating five different adaptive decomposition methods for EEG signal seizure detection and classification. Biomedical Signal Processing and Control. 2020 Sep 1;62:102073.

Boonyakitanont P, Lek-Uthai A, Chomtho K, Songsiri J. A review of feature extraction and performance evaluation in epileptic seizure detection using EEG. Biomedical Signal Processing and Control. 2020 Mar 1;57:101702.

Tzimourta KD, Tzallas AT, Giannakeas N, Astrakas LG, Tsalikakis DG, Angelidis P, Tsipouras MG. A robust methodology for classification of epileptic seizures in EEG signals. Health and Technology. 2019 Mar 15;9:135-42.

Karabiber Cura O, Kocaaslan Atli S, Türe HS, Akan A. Epileptic seizure classifications using empirical mode decomposition and its derivative. Biomedical engineering online. 2020 Dec;19:1-22.

Chakraborty J, Nandy A. Discrete wavelet transform based data representation in deep neural network for gait abnormality detection. Biomedical Signal Processing and Control. 2020 Sep 1;62:102076.

Mamli S, Kalbkhani H. Gray-level co-occurrence matrix of Fourier synchro-squeezed transform for epileptic seizure detection. Biocybernetics and Biomedical Engineering. 2019 Jan 1;39(1):87-99.

George ST, Subathra MS, Sairamya NJ, Susmitha L, Premkumar MJ. Classification of epileptic EEG signals using PSO based artificial neural network and tunable-Q wavelet transform. Biocybernetics and Biomedical Engineering. 2020 Apr 1;40(2):709-28.

Radman M, Moradi M, Chaibakhsh A, Kordestani M, Saif M. Multi-feature fusion approach for epileptic seizure detection from EEG signals. IEEE sensors journal. 2020 Sep 23;21(3):3533-43.

Martis RJ, Acharya UR, Tan JH, Petznick A, Yanti R, Chua CK, Ng EK, Tong L. Application of empirical mode decomposition (EMD) for automated detection of epilepsy using EEG signals. International journal of neural systems. 2012 Dec 13;22(06):1250027.

Jia J, Goparaju B, Song J, Zhang R, Westover MB. Automated identification of epileptic seizures in EEG signals based on phase space representation and statistical features in the CEEMD domain. Biomedical Signal Processing and Control. 2017 Sep 1;38:148-57.

Aydemir E, Tuncer T, Dogan S. A Tunable-Q wavelet transform and quadruple symmetric pattern based EEG signal classification method. Medical hypotheses. 2020 Jan 1;134:109519.

S. Izadi, K. Jabari, M. Izadi, B. Khadem Hamedani, and A. Ghaffari, "Identification and Diagnosis of Dynamic and Static Misalignment in Induction Motor Using Unscented Kalman Filter," in 2021 13th Iranian Conference on Electrical Engineering and Computer Science (ICEESC), 2021.