ORCID

Abstract

One of the most prevalent neurological disorders is epilepsy. Epileptic seizures can occurrepeatedly in people with the condition for no recognisable reason. The diagnostic methodsdependent on EEG are promising. EEG has uncovered the dynamic functioning of all brain areasthroughout time. Its low cost, non-invasiveness, and simply make it crucial for clinicalevaluations of brain function. Integrating multiple EEG biomarkers as a compound biomarkercould provide a high performance that may accelerate the diagnosis speeds. Artificial intelligencetechniques such as machine learning and deep learning provide a significant result in healthcareapplications. Logistic Regression (LR), Naive Bayes (NB), and Neural Network (NN) wereevaluated using a compound biomarker containing eleven EEG features that were extracted fromthe Bonn EEG dataset. The aim of this study is to evaluate the feasibility of integrating multipleEEG biomarkers as compound biomarkers for identifying epileptic people. The outcomes showedthe performance of all LR, NB, and NN detection models provide a high performance withsensitivity and specificity of greater than 90%.

Publication Date

2025-01-01

Publication Title

Journal of Information Systems Engineering and Management

Volume

10

Issue

39

Keywords

Epileptic seizures, Healthcare Applications, EEG Biomarkers, Machine Learning, Compound Biomarkers

First Page

21

Last Page

33

Download

Share

COinS