An Overview of EEG-based Machine Learning Methods in Seizure Prediction and Opportunities for Neurologists in this Field. (15th January 2022)

• Record Type: Journal Article
• Authors: Maimaiti, Buajieerguli; Meng, Hongmei; Lv, Yudan; Qiu, Jiqing; Zhu, Zhanpeng; Xie, Yinyin; Li, Yue; Yu-Cheng, ; Zhao, Weixuan; Liu, Jiayu; Li, Mingyang
• Is Part Of: Neuroscience. Volume 481(2022)
• Page Start: 197
• Page End: 218
• Publication Date: 2022-01-15
• Subjects: ApE approximate entropy -- AR autoregressive -- BLDA Bayesian linear discriminant analysis -- CCA canonical correlation analysis -- CNN convolutional neural networks -- CSP common spatial pattern -- CWT continuous wavelet transform -- DL deep learning -- DWT discrete wavelet transform -- EEG electroencephalography -- ELM extreme learning machine -- EMD empirical mode decomposition -- FD Fractality dimension -- FLDA Fisher linear discriminant analysis -- FPR false-positive rate -- FT Fourier transform -- HOS higher order spectra -- HP Hjorth parameter -- ICA independent component analysis -- iEEG intracranial electroencephalography -- LDA linear discriminant analysis -- LZC Lempel-Ziv complexity -- MF-DFA multi-fractal detrended fluctuation analysis -- MI mutual information -- ML machine learning -- MLP multilayer perceptron -- PCA Principal component analysis -- PE permutation entropy -- PH prediction horizon -- PP prediction period -- PSD power spectral density -- RF random forest -- RLDA regularized linear discriminant analysis -- SOP seizure occurrence period -- SpE Spectral entropy -- SVM support vector machine -- TIW time in warning -- WE Wavelet entropy -- WPD wavelet packet decomposition -- WT wavelet transformation; artificial intelligence (AI) -- machine learning (ML) -- seizure prediction -- epilepsy -- electroencephalography; Neurochemistry -- Periodicals; Neurophysiology -- Periodicals; Neurology -- Periodicals; Neurochimie -- Périodiques; Neurophysiologie -- Périodiques; Neurochemistry; Neurophysiology; Electronic journals; Periodicals; Electronic journals; 612.8
• DOI: 10.1016/j.neuroscience.2021.11.017
• Languages: English
• ISSNs: 0306-4522

Abstract

Highlights: EEG-based ML techniques for seizure prediction achieved promising results. Various factors can influence the performance of EEG-based ML algorithms. ML-based algorithms provide considerable opportunities for clinicians in the field. Prediction model including patient clinical characteristics can be further developed. With cooperation of related fields, the area can be advanced by novel ML based techniques. Abstract: The unpredictability of epileptic seizures is one of the most problematic aspects of the field of epilepsy. Methods or devices capable of detecting seizures minutes before they occur may help prevent injury or even death and significantly improve the quality of life. Machine learning (ML) is an emerging technology that can markedly enhance algorithm performance by interpreting data. ML has gained increasing attention from medical researchers in recent years. Its epilepsy applications range from the localization of the epileptic region, predicting the medical or surgical outcome of epilepsy, and automated electroencephalography (EEG) analysis to seizure prediction. While ML has good prospects with regard to detecting epileptic seizures via EEG signals, many clinicians are still unfamiliar with this field. This work briefly summarizes the history and recent significant progress made in this field and clarifies the essential components of the automatic seizure detection system using ML methodologies for clinicians. This review also proposes how neurologists can actively contribute to ensure improvements in seizure prediction using EEG-based ML.