Predicting Epileptic Seizures From EEG Signals Using Machine Learning

Authors

• Hamzah Luqman, King Fahd University of Petroleum and Minerals, Saudi Arabia AND SDAIA-KFUPM Joint Research Center for Artificial Intelligence, KFUPM, Saudi ArabiaFollow
• Galal M BinMakhashen, King Fahd University of Petroleum and Minerals, Saudi ArabiaFollow
• Hanan AlAli, King Fahd University of Petroleum and Minerals, Saudi ArabiaFollow
• Marwa AlSleebi, King Fahd University of Petroleum and Minerals, Saudi ArabiaFollow
• Hamdi A. Al-Jamimi, King Fahd University of Petroleum and Minerals, Saudi Arabia AND SDAIA-KFUPM Joint Research Center for Artificial Intelligence, KFUPM, Saudi ArabiaFollow
• Motaz Alfarraj, King Fahd University of Petroleum and Minerals, Saudi Arabia AND SDAIA-KFUPM Joint Research Center for Artificial Intelligence, KFUPM, Saudi ArabiaFollow
• Shahid Bashir, Neuroscience Centre, King Fahad Specialist Hospital, Dammam, KSA AND King Salman Center for Disability Research, Riyadh 11614, Saudi ArabiaFollow
• Brent Hedgcock, Department of Neurophysiology, King Fahad Specialist Hospital, Dammam, Saudi ArabiaFollow
• Ali Mir, Department of Pediatric Neurology, King Fahad Specialist Hospital, Dammam, KSAFollow
• Raidah AlBaradie, Department of Pediatric Neurology, King Fahad Specialist Hospital, Dammam, KSAFollow

Abstract

Objective: To develop a machine learning-based model for predicting epileptic seizures by analyzing electroencephalogram (EEG) signals and classifying the interictal and preictal phases.

Methods: The EEG signals were analyzed in both the time and frequency domains using advanced feature extraction techniques. Three different machine learning approaches were employed, with special focus on long short-term memory (LSTM) networks. Features were extracted and classified to differentiate between seizure and non-seizure phases. The proposed models were evaluated using the publicly available CHB-MIT EEG dataset. The study was conducted between September 2022 and September 2024.

Results: Among the tested models, the LSTM-based approach using the full-feature extraction pipeline achieved the highest prediction accuracy of 97.73%. This performance demonstrates strong potential for real-time seizure forecasting.

Conclusion: Machine learning, particularly LSTM models, can accurately predict epileptic seizures by analyzing EEG signal patterns. These findings support the development of automated seizure prediction systems that could significantly improve the quality of life for epilepsy patients.

Article Type

Original Study

First Page

133

Last Page

139

Recommended Citation

Luqman, Hamzah; BinMakhashen, Galal M; AlAli, Hanan; AlSleebi, Marwa; Al-Jamimi, Hamdi A.; Alfarraj, Motaz; Bashir, Shahid; Hedgcock, Brent; Mir, Ali; and AlBaradie, Raidah (2026) "Predicting Epileptic Seizures From EEG Signals Using Machine Learning," Neurosciences: Vol. 31: Iss. 2, Article 4.
DOI: https://doi.org/10.17712/1658-3183.2789