RESEARCH ARTICLE


Online Seizure Prediction System: A Novel Probabilistic Approach for Efficient Prediction of Epileptic Seizure with iEEG Signal



Behrooz Abbaszadeh1, *, Cesar A. D. Teixeira2, Mustapha C.E. Yagoub1
1 School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada
2 Unive Coimbra, CISUC-Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, Coimbra, Portugal


Article Metrics

CrossRef Citations:
0
Total Statistics:

Full-Text HTML Views: 144
Abstract HTML Views: 49
PDF Downloads: 93
ePub Downloads: 38
Total Views/Downloads: 324
Unique Statistics:

Full-Text HTML Views: 88
Abstract HTML Views: 45
PDF Downloads: 52
ePub Downloads: 35
Total Views/Downloads: 220



Creative Commons License
© 2022 Abbaszadeh et al.

open-access license: This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

* Address correspondence to this author at School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Ontario, Canada; E-mail: babba027@uottawa.ca


Abstract

Background:

1% of people around the world are suffering from epilepsy. It is, therefore crucial to propose an efficient automated seizure prediction tool implemented in a portable device that uses the electroencephalogram (EEG) signal to enhance epileptic patients’ life quality.

Methods:

In this study, we focused on time-domain features to achieve discriminative information at a low CPU cost extracted from the intracranial electroencephalogram (iEEG) signals of six patients. The probabilistic framework based on XGBoost classifier requires the mean and maximum probability of the non-seizure and the seizure occurrence period segments. Once all these parameters are set for each patient, the medical decision maker can send alarm based on well-defined thresholds.

Results:

While finding a unique model for all patients is really challenging, and our modelling results demonstrated that the proposed algorithm can be an efficient tool for reliable and clinically relevant seizure forecasting. Using iEEG signals, the proposed algorithm can forecast seizures, informing a patient about 75 minutes before a seizure would occur, a period large enough for patients to take practical actions to minimize the potential impacts of the seizure.

Conclusion:

We posit that the ability to distinguish interictal intracranial EEG from pre-ictal signals at some low computational cost may be the first step towards an implanted portable semi-automatic seizure suppression system in the near future. It is believed that our seizure prediction technique can conceivably be coupled with treatment techniques aimed at interrupting the process even prior to a seizure initiates to develop.

Keywords: Epileptic seizure, Time domain features, Intracranial EEG, XGBoost classifier, Matthews’s correlation coefficient, Probabilistic framework, Low CPU cost.