Finding Predictive EEG Complexity Features for Classification of Epileptic and Psychogenic Nonepileptic Seizures Using Imperialist Competitive Algorithm

Abstract

DOI to the publisher's website. • The final author version and the galley proof are versions of the publication after peer review. • The final published version features the final layout of the paper including the volume, issue and page numbers. Link to publication General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal. If the publication is distributed under the terms of Article 25fa of the Dutch Copyright Act, indicated by the "Taverne" license above, please follow below link for the End User Agreement:

Permutation Entropy-Based Interpretability of Convolutional Neural Network Models for Interictal EEG Discrimination of Subjects with Epileptic Seizures vs. Psychogenic Non-Epileptic Seizures

“…In the literature there are several promising results achieved by AI algorithms on neurological conditions [ 9 , 10 , 63 , 64 ]. Only two works have presented classification studies differentiating ES and PNES [ 18 , 65 ], both based on ML. The first study [ 18 ] performed a classification of 20 epilepsy and 20 PNES patients by using the imperialist competitive algorithm for feature extraction, achieving an accuracy higher than 90%.…”

“…Only two works have presented classification studies differentiating ES and PNES [ 18 , 65 ], both based on ML. The first study [ 18 ] performed a classification of 20 epilepsy and 20 PNES patients by using the imperialist competitive algorithm for feature extraction, achieving an accuracy higher than 90%. However, they used the EEGs including periods of seizures: this was likely to result in a significant difference between the two groups.…”

“…Clarke et al [ 16 ] reports on a deep learning algorithm for computer-assisted EEG review with mean sensitivity of >95% and corresponding mean false positive rate of 1 detection per minute. Ahmadi et al [ 18 ] have classified ES and PNES using the imperialist competitive algorithm on EEG including ictal recordings finding that spectral entropy and Rényi entropy were the most important EEG features, with good classification results using support vector machine (SVM).…”

Electroencephalogram Connectivity for the Diagnosis of Psychogenic Non-epileptic Seizures

“…Feature selection has shown to be an effective method to improve classifiers diagnosing PNES [10], [14]. Two meth- ods of feature selection were chosen based on their opposing techniques: the first used correlation and tree analysis to remove the unhelpful features; and the second ranked using statistical analysis and chose the k-best features.…”

Effect of linear mixing in EEG on synchronization and complex network measures studied using the Kuramoto model

“…Fig. 3 shows a sample of EEG data recorded with two different time samplings, 1/128 and 1/32 s [23]. It is evident that EEG recordings differ as a result of changes in resolution.…”