Comparison of epileptic seizure prediction performance for different EEG derivation schemes
DOI:
https://doi.org/10.20535/RADAP.2017.68.54-58Keywords:
epilepsy, epileptic seizure, correlation, electroencephalography, EEG, seizure prediction, derivation schemeAbstract
Introduction. The influence of EEG derivation scheme on performance of epileptic seizure prediction is considered in the paper. Comparison of epileptic seizure prediction performance for different EEG derivation schemes is conducted. Database of EEG recordings from 20 patients (between 1 and 25 years old) suffering epilepsy was used. Correlation coefficients between channels of signal extracted with different combination of window and preictal lengths were used as features. Support vector machine was used to classify EEG data into interictal and preictal classes. Epileptic seizures prediction performance was evaluated using area under the ROC-curve for two types of derivation schemes: monopolar scheme with reference electrode on ipsilateral ear and scheme with averaged reference. Conclusions. It was found that there is a difference in epileptic seizures prediction performance for different schemes and patients. For subgroup of patients (9 of 20) usage of scheme with reference electrode in ipsilateral ear shows higher performance for window length between 2 and 10 seconds and in entire range of preictal lengths. Scheme with averaged reference shows higher performance when window length is in the range between 90 and 300 seconds.Downloads
Published
2017-03-30
Issue
Section
Radioelectronics Medical Technologies
License
Copyright (c) 2020 O. Yu. Panichev, A. O. Popov, V. I. Kharytonov
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).