Deep learning‐based seizure prediction using EEG signals: A comparative analysis of classification methods on the CHB‐MIT dataset

• Published in: Engineering reports (Hoboken, N.J.) N.J.), 2024-11, Vol.6 (11), p.n/a
• Main Authors: Esmaeilpour, Ali, Tabarestani, Shaghayegh Shahiri, Niazi, Alireza
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial neural networks; Brain; Brain research; Classification; convolutional neural network (CNN); Convulsions & seizures; Datasets; Deep learning; electroencephalogram; Electroencephalography; Epilepsy; Feature extraction; Machine learning; Neural networks; Noise prediction; Patients; Performance evaluation; predicting epileptic Seizures; Predictive control; random forest; Seizures; Signal classification; support vector machine (SVM); Support vector machines
• ISSN: 2577-8196; 2577-8196
• DOI: 10.1002/eng2.12918

Epilepsy is a brain disorder that causes patients to have multiple seizures. About 30% of patients with epilepsy are not treated with medication or surgery. The abnormal activity of brain before occurring of a seizure (about a few minutes before a seizure occurs) are known as the preictal area. Therefore, if we can predict this state, we can control possible seizures by using appropriate medications. In this study, we present a method for predicting epileptic seizures using electroencephalogram (EEG) signals. The method can identify the preictal region that occurs before the onset of seizures. In our proposed method, first the noise removal of EEG signals is performed, and then the necessary features are extracted using a convolution neural network. Finally, we use the feature vectors in order to train multiple classifiers, fully connected layer, random forest, and support vector machines with linear kernel. Additionally, we apply maximum voting, which is an ensemble method, to classify preictal segments from interictal ones. In this study, using EEG signals of patients from CHB‐MIT dataset, we were able to achieve sensitivity of 90.76%. The high sensitivity rate is indicative of the model's ability to accurately predict seizures, which can be critical for timely intervention. The low false prediction rate minimizes unnecessary interventions, thereby reducing the burden on patients and healthcare systems.