Feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio-signals

IntroductionEpilepsy is a neurological disorder in which patients experience recurrent seizures, with the frequency of occurrence more than twice a day, which highly affects a patient's life. In recent years, multiple researchers have proposed multiple machine learning and deep learning-based m...

Full description

Saved in:
Bibliographic Details
Main Authors: Yazeed Alkhrijah, Shehzad Khalid, Syed Muhammad Usman, Amina Jameel, Muhammad Zubair, Haya Aldossary, Aamir Anwar, Saad Arif
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-08-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1566870/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344206734098432
author Yazeed Alkhrijah
Yazeed Alkhrijah
Shehzad Khalid
Shehzad Khalid
Syed Muhammad Usman
Amina Jameel
Muhammad Zubair
Haya Aldossary
Aamir Anwar
Saad Arif
author_facet Yazeed Alkhrijah
Yazeed Alkhrijah
Shehzad Khalid
Shehzad Khalid
Syed Muhammad Usman
Amina Jameel
Muhammad Zubair
Haya Aldossary
Aamir Anwar
Saad Arif
author_sort Yazeed Alkhrijah
collection DOAJ
description IntroductionEpilepsy is a neurological disorder in which patients experience recurrent seizures, with the frequency of occurrence more than twice a day, which highly affects a patient's life. In recent years, multiple researchers have proposed multiple machine learning and deep learning-based methods to predict the onset of seizures using electroencephalogram (EEG) signals before they occur; however, robust preprocessing to mitigate the effect of noise, channel selection to reduce dimensionality, and feature extraction remain challenges in accurate prediction.MethodsThis study proposes a novel method for accurately predicting epileptic seizures. In the first step, a Butterworth filter is applied, followed by a wavelet and a Fourier transform for the denoising of EEG signals. A non-overlapping window of 15 s is selected to segment the EEG signals, and an optimal spatial filter is applied to reduce the dimensionality. Handcrafted features, including both time and frequency domains, have been extracted and concatenated with the customized one-dimensional convolutional neural network-based features to form a comprehensive feature vector. It is then fed into three classifiers, including support vector machines, random forest, and long short-term memory (LSTM) units. The output of these classifiers is then fed into the model-agnostic meta learner ensemble classifier with LSTM as the base classifier for the final prediction of interictal and preictal states.ResultsThe proposed methodology is trained and tested on the publicly available CHB-MIT dataset while achieving 99.34% sensitivity, 98.67% specificity, and a false positive alarm rate of 0.039.DiscussionThe proposed method not only outperforms the existing methods in terms of sensitivity and specificity but is also computationally efficient, making it suitable for real-time epileptic seizure prediction systems.
format Article
id doaj-art-5708608b92c4480b95ef659d75eead2c
institution Kabale University
issn 2296-858X
language English
publishDate 2025-08-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-5708608b92c4480b95ef659d75eead2c2025-08-20T03:42:44ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-08-011210.3389/fmed.2025.15668701566870Feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio-signalsYazeed Alkhrijah0Yazeed Alkhrijah1Shehzad Khalid2Shehzad Khalid3Syed Muhammad Usman4Amina Jameel5Muhammad Zubair6Haya Aldossary7Aamir Anwar8Saad Arif9Department of Electrical Engineering, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh, Saudi ArabiaKing Salman Center for Disability Research (KSCDR), Riyadh, Saudi ArabiaComputer and Information Sciences Research Center (CISRC), Imam Mohammad Ibn Saud Islamic University, Riyadh, Saudi ArabiaDepartment of Computer Engineering, Bahria University, Islamabad, PakistanDepartment of Computer Science, Bahria University, Islamabad, PakistanDepartment of Computer Engineering, Bahria University, Islamabad, PakistanInterdisciplinary Research Center for Finance and Digital Economy, King Fahd University of Petroleum and Minerals, Dhahran, Saudi ArabiaComputer Science Department, College of Science and Humanities, Imam Abdulrahman Bin Faisal University, Jubail, Saudi ArabiaSchool of Computing, University of Portsmouth, London Campus, London, United KingdomDepartment of Mechanical Engineering, College of Engineering, King Faisal University, Al Ahsa, Saudi ArabiaIntroductionEpilepsy is a neurological disorder in which patients experience recurrent seizures, with the frequency of occurrence more than twice a day, which highly affects a patient's life. In recent years, multiple researchers have proposed multiple machine learning and deep learning-based methods to predict the onset of seizures using electroencephalogram (EEG) signals before they occur; however, robust preprocessing to mitigate the effect of noise, channel selection to reduce dimensionality, and feature extraction remain challenges in accurate prediction.MethodsThis study proposes a novel method for accurately predicting epileptic seizures. In the first step, a Butterworth filter is applied, followed by a wavelet and a Fourier transform for the denoising of EEG signals. A non-overlapping window of 15 s is selected to segment the EEG signals, and an optimal spatial filter is applied to reduce the dimensionality. Handcrafted features, including both time and frequency domains, have been extracted and concatenated with the customized one-dimensional convolutional neural network-based features to form a comprehensive feature vector. It is then fed into three classifiers, including support vector machines, random forest, and long short-term memory (LSTM) units. The output of these classifiers is then fed into the model-agnostic meta learner ensemble classifier with LSTM as the base classifier for the final prediction of interictal and preictal states.ResultsThe proposed methodology is trained and tested on the publicly available CHB-MIT dataset while achieving 99.34% sensitivity, 98.67% specificity, and a false positive alarm rate of 0.039.DiscussionThe proposed method not only outperforms the existing methods in terms of sensitivity and specificity but is also computationally efficient, making it suitable for real-time epileptic seizure prediction systems.https://www.frontiersin.org/articles/10.3389/fmed.2025.1566870/fullAI in healthcareepilepsyelectroencephalogramepileptic seizure predictionsignal quality indexoptimal spatial filter
spellingShingle Yazeed Alkhrijah
Yazeed Alkhrijah
Shehzad Khalid
Shehzad Khalid
Syed Muhammad Usman
Amina Jameel
Muhammad Zubair
Haya Aldossary
Aamir Anwar
Saad Arif
Feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio-signals
Frontiers in Medicine
AI in healthcare
epilepsy
electroencephalogram
epileptic seizure prediction
signal quality index
optimal spatial filter
title Feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio-signals
title_full Feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio-signals
title_fullStr Feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio-signals
title_full_unstemmed Feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio-signals
title_short Feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio-signals
title_sort feature fusion ensemble classification approach for epileptic seizure prediction using electroencephalographic bio signals
topic AI in healthcare
epilepsy
electroencephalogram
epileptic seizure prediction
signal quality index
optimal spatial filter
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1566870/full
work_keys_str_mv AT yazeedalkhrijah featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT yazeedalkhrijah featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT shehzadkhalid featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT shehzadkhalid featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT syedmuhammadusman featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT aminajameel featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT muhammadzubair featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT hayaaldossary featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT aamiranwar featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals
AT saadarif featurefusionensembleclassificationapproachforepilepticseizurepredictionusingelectroencephalographicbiosignals