An overview of machine learning and deep learning techniques for predicting epileptic seizures - Abstract and review

Aug 3, 2026

Upload by Skyler

Epilepsy is a common neurological disorder in which seizures can emerge without a known cause, and future events may occur unpredictably. This review summarizes the current state of machine learning for detecting and predicting epileptic seizures, focusing on how existing methods trade off prediction time, sensitivity, and specificity. The study highlights EEG-based approaches and notes that deep learning can help achieve a better balance, while combining techniques and features can further improve performance at the cost of added computation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages9

Reading Time23 min

AccessFree to download

1 Introduction

1.1 Issues

Feature Extraction and Application

Table 1: Features for seizure prediction and detection

Table 2: Feature extraction application

Feature Selection Methods

Table 3: Feature selection methods

Review Article Marco Zurdo-Tabernero*, Ángel Canal-Alonso*, Fernando de la Prieta, Sara Rodríguez, Javier Prieto and Juan Manuel Corchado An overview of machine learning and deep learning techniques for predicting epileptic seizures [https://doi.org/10.1515/jib-2023-0002](https://doi.org/10.1515/jib-2023-0002) Received January 17, 2023; accepted August 1, 2023; published online December 15, 2023 Abstract: Epilepsy is a neurological disorder (the third most common, following stroke and migraines). A key aspect of its diagnosis is the presence of seizures that occur without a known cause and the potential for new seizures to occur. Machine learning has shown potential as a cost-effective alternative for rapid diagnosis. In this study, we review the current state of machine learning in the detection and prediction of epileptic seizures. The objective of this study is to portray the existing machine learning methods for seizure prediction. Internet bibliographical searches were conducted to identify relevant literature on the topic. Through cross-referencing from key articles, additional references were obtained to provide a comprehensive overview of the techniques. As the aim of this paper aims is not a pure bibliographical review of the subject, the publications here cited have been selected among many others based on their number of citations. To implement accurate diagnostic and treatment tools, it is necessary to achieve a balance between prediction time, sensitivity, and speciﬁcity. This balance can be achieved using deep learning algorithms. The best performance and results are often achieved by combining multiple techniques and features, but this approach can also increase computational requirements. Keywords: seizure prediction; machine learning; epilepsy; electroencephalogram 1 Introduction Epilepsy is a neurological disorder that affects over 39 million people in the United States [1], making it the third most common disorder after stroke and migraines [2] . This chronic condition is known to impact the quality of life signiﬁcantly, making it a focus of ongoing research and development of new therapies. According to the International League Against Epilepsy, an epileptic seizure is a “transient occurrence of signs and/or symptoms due to abnormal excessive or synchronous neuronal activity in the brain” [3] . *Corresponding authors: Marco Zurdo-Tabernero and Ángel Canal-Alonso, BISITE Research Group, University of Salamanca, Sala manca, Spain, [E-mail: marcohperez@usal.es](E-mail: marcohperez@usal.es) (M. Zurdo-Tabernero), [acanal@usal.es](acanal@usal.es) (Á. Canal-Alonso). [https://orcid.org/0000-0002-6381-](https://orcid.org/0000-0002-6381-) 5149 (M. Zurdo-Tabernero). [https://orcid.org/0000-0002-4254-5944](https://orcid.org/0000-0002-4254-5944) (Á. Canal-Alonso). Fernando de la Prieta, Sara Rodríguez, Javier Prieto and Juan Manuel Corchado, BISITE Research Group, University of Salamanca, Salamanca, Spain, E-mail: [fer@usal.es](fer@usal.es) ([F. de](F. de) la Prieta), [srg@usal.es](srg@usal.es) (S. Rodríguez), [javierp@usal.es](javierp@usal.es) (J. Prieto), [corchado@usal.es](corchado@usal.es) (J.M. Corchado). [https://orcid.org/0000-0002-8239-5020](https://orcid.org/0000-0002-8239-5020) ([F. de](F. de) la Prieta). [https://orcid.org/0000-0002-3081-5177](https://orcid.org/0000-0002-3081-5177) (S. Rodríguez). [https://](https://) [orcid.org/0000-0001-8175-2201](orcid.org/0000-0001-8175-2201) (J. Prieto). [https://orcid.org/0000-0002-2829-1829](https://orcid.org/0000-0002-2829-1829) (J.M. Corchado) Open Access. © 2023 the author(s), published by De Gruyter. This work is licensed under the Creative Commons Attribution 4 .0 International License. 2 — M. Zurdo-Tabernero et al.: An overview of ML and DL techniques for epileptic seizure prediction 1.1 Issues Electroencephalography (EEG) is the most commonly used method for diagnosing epilepsy. This technique involves recording the brain

FAQs

What is the core aim of the review on epileptic seizure prediction?

It reviews the existing machine learning methods used for epileptic seizure detection and prediction and summarizes the state of ML approaches in this area.

Why is balancing prediction time, sensitivity, and specificity important?

Accurate diagnostic and treatment support depends on achieving an appropriate trade-off among these metrics, since faster prediction must still maintain reliable detection performance.

How does deep learning relate to machine learning in seizure prediction?

Deep learning algorithms are presented as a way to help achieve the desired balance of performance metrics, and combining multiple techniques and features can further improve results though it may increase computational requirements.

Aug 3, 2026

Upload by Skyler