Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods.

Details

Serval ID
serval:BIB_9A69A1B259DD
Type
Article: article from journal or magazin.
Collection
Publications
Title
Preprocessing effects of 22 linear univariate features on the performance of seizure prediction methods.
Journal
Journal of neuroscience methods
Author(s)
Rasekhi J., Mollaei M.R., Bandarabadi M., Teixeira C.A., Dourado A.
ISSN
1872-678X (Electronic)
ISSN-L
0165-0270
Publication state
Published
Issued date
15/07/2013
Peer-reviewed
Oui
Volume
217
Number
1-2
Pages
9-16
Language
english
Notes
Publication types: Journal Article ; Research Support, Non-U.S. Gov't
Publication Status: ppublish
Abstract
Combining multiple linear univariate features in one feature space and classifying the feature space using machine learning methods could predict epileptic seizures in patients suffering from refractory epilepsy. For each patient, a set of twenty-two linear univariate features were extracted from 6 electroencephalogram (EEG) signals to make a 132 dimensional feature space. Preprocessing and normalization methods of the features, which affect the output of the seizure prediction algorithm, were studied in terms of alarm sensitivity and false prediction rate (FPR). The problem of choosing an optimal preictal time was tackled using 4 distinct values of 10, 20, 30, and 40 min. The seizure prediction problem has traditionally been considered a two-class classification problem, which is also exercised here. These studies have been conducted on the features obtained from 10 patients. For each patient, 48 different combinations of methods are compared to find the best configuration. Normalization by dividing by the maximum and smoothing are found to be the best configuration in most of the patients. The results also indicate that applying machine learning methods on a multidimensional feature space of 22 univariate features predicted seizure onsets with high performance. On average, the seizures were predicted in 73.9% of the cases (34 out of 46 in 737.9h of test data), with a FPR of 0.15 h(-1).
Keywords
Adolescent, Adult, Algorithms, Brain/physiopathology, Diagnosis, Computer-Assisted/methods, Electroencephalography/methods, Female, Humans, Linear Models, Middle Aged, Multivariate Analysis, Pattern Recognition, Automated/methods, Reproducibility of Results, Seizures/diagnosis, Seizures/physiopathology, Sensitivity and Specificity, Support Vector Machine, Young Adult
Pubmed
Web of science
Create date
06/07/2021 15:28
Last modification date
04/05/2024 7:07
Usage data