Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis

Yissel Rodríguez Aldana*, Borbála Hunyadi, Enrique J.Marañón Reyes, Valia Rodríguez Rodríguez, Sabine Van Huffel

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

Nonconvulsive status epilepticus is a condition where the patient is exposed to abnormally prolonged epileptic seizures without evident physical symptoms. Since these continuous seizures may cause permanent brain damage, it constitutes a medical emergency. This paper proposes a method to detect nonconvulsive seizures for a further nonconvulsive status epilepticus diagnosis. To differentiate between the normal and seizure electroencephalogram (EEG), a K-Nearest Neighbor, a Radial Basis Support Vector Machine, and a Linear Discriminant Analysis classifier are used. The classifier features are obtained from the Canonical Polyadic Decomposition (CPD) and Block Term Decomposition (BTD) of the EEG data represented as third order tensor. To expand the EEG into a tensor, Wavelet or Hilbert-Huang transform are used. The algorithm is tested on a scalp EEG database of 139 seizures of different duration. The experimental results suggest that a Hilbert-Huang tensor representation and the CPD analysis provide the most suitable framework for nonconvulsive seizure detection. The Radial Basis Support Vector Machine classifier shows the best performance with sensitivity, specificity, and accuracy values over 98%. A rough comparison with other methods proposed in the literature shows the superior performance of the proposed method for nonconvulsive epileptic seizure detection.

Original languageEnglish
Article number8351633
Pages (from-to)660-671
Number of pages12
JournalIEEE Journal of Biomedical and Health Informatics
Volume23
Issue number2
Early online date27 Apr 2018
DOIs
Publication statusPublished - 1 Mar 2019

Fingerprint

Electroencephalography
Scalp
Epilepsy
Seizures
Tensors
Classifiers
Decomposition
Status Epilepticus
Support vector machines
Discriminant analysis
Discriminant Analysis
Brain
Emergencies
Databases
Sensitivity and Specificity
Support Vector Machine

Bibliographical note

© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Keywords

  • Hilbert Huang Transform
  • Multiway Data Analysis
  • Nonconvulsive epileptic seizures
  • Wavelet Transform

Cite this

Aldana, Y. R., Hunyadi, B., Reyes, E. J. M., Rodríguez, V. R., & Van Huffel, S. (2019). Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis. IEEE Journal of Biomedical and Health Informatics, 23(2), 660-671. [8351633]. https://doi.org/10.1109/JBHI.2018.2829877
Aldana, Yissel Rodríguez ; Hunyadi, Borbála ; Reyes, Enrique J.Marañón ; Rodríguez, Valia Rodríguez ; Van Huffel, Sabine. / Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis. In: IEEE Journal of Biomedical and Health Informatics. 2019 ; Vol. 23, No. 2. pp. 660-671.
@article{173f5c9aa55f4a709e25ad17326316b8,
title = "Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis",
abstract = "Nonconvulsive status epilepticus is a condition where the patient is exposed to abnormally prolonged epileptic seizures without evident physical symptoms. Since these continuous seizures may cause permanent brain damage, it constitutes a medical emergency. This paper proposes a method to detect nonconvulsive seizures for a further nonconvulsive status epilepticus diagnosis. To differentiate between the normal and seizure electroencephalogram (EEG), a K-Nearest Neighbor, a Radial Basis Support Vector Machine, and a Linear Discriminant Analysis classifier are used. The classifier features are obtained from the Canonical Polyadic Decomposition (CPD) and Block Term Decomposition (BTD) of the EEG data represented as third order tensor. To expand the EEG into a tensor, Wavelet or Hilbert-Huang transform are used. The algorithm is tested on a scalp EEG database of 139 seizures of different duration. The experimental results suggest that a Hilbert-Huang tensor representation and the CPD analysis provide the most suitable framework for nonconvulsive seizure detection. The Radial Basis Support Vector Machine classifier shows the best performance with sensitivity, specificity, and accuracy values over 98{\%}. A rough comparison with other methods proposed in the literature shows the superior performance of the proposed method for nonconvulsive epileptic seizure detection.",
keywords = "Hilbert Huang Transform, Multiway Data Analysis, Nonconvulsive epileptic seizures, Wavelet Transform",
author = "Aldana, {Yissel Rodr{\'i}guez} and Borb{\'a}la Hunyadi and Reyes, {Enrique J.Mara{\~n}{\'o}n} and Rodr{\'i}guez, {Valia Rodr{\'i}guez} and {Van Huffel}, Sabine",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2019",
month = "3",
day = "1",
doi = "10.1109/JBHI.2018.2829877",
language = "English",
volume = "23",
pages = "660--671",
number = "2",

}

Aldana, YR, Hunyadi, B, Reyes, EJM, Rodríguez, VR & Van Huffel, S 2019, 'Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis', IEEE Journal of Biomedical and Health Informatics, vol. 23, no. 2, 8351633, pp. 660-671. https://doi.org/10.1109/JBHI.2018.2829877

Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis. / Aldana, Yissel Rodríguez; Hunyadi, Borbála; Reyes, Enrique J.Marañón; Rodríguez, Valia Rodríguez; Van Huffel, Sabine.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 23, No. 2, 8351633, 01.03.2019, p. 660-671.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis

AU - Aldana, Yissel Rodríguez

AU - Hunyadi, Borbála

AU - Reyes, Enrique J.Marañón

AU - Rodríguez, Valia Rodríguez

AU - Van Huffel, Sabine

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Nonconvulsive status epilepticus is a condition where the patient is exposed to abnormally prolonged epileptic seizures without evident physical symptoms. Since these continuous seizures may cause permanent brain damage, it constitutes a medical emergency. This paper proposes a method to detect nonconvulsive seizures for a further nonconvulsive status epilepticus diagnosis. To differentiate between the normal and seizure electroencephalogram (EEG), a K-Nearest Neighbor, a Radial Basis Support Vector Machine, and a Linear Discriminant Analysis classifier are used. The classifier features are obtained from the Canonical Polyadic Decomposition (CPD) and Block Term Decomposition (BTD) of the EEG data represented as third order tensor. To expand the EEG into a tensor, Wavelet or Hilbert-Huang transform are used. The algorithm is tested on a scalp EEG database of 139 seizures of different duration. The experimental results suggest that a Hilbert-Huang tensor representation and the CPD analysis provide the most suitable framework for nonconvulsive seizure detection. The Radial Basis Support Vector Machine classifier shows the best performance with sensitivity, specificity, and accuracy values over 98%. A rough comparison with other methods proposed in the literature shows the superior performance of the proposed method for nonconvulsive epileptic seizure detection.

AB - Nonconvulsive status epilepticus is a condition where the patient is exposed to abnormally prolonged epileptic seizures without evident physical symptoms. Since these continuous seizures may cause permanent brain damage, it constitutes a medical emergency. This paper proposes a method to detect nonconvulsive seizures for a further nonconvulsive status epilepticus diagnosis. To differentiate between the normal and seizure electroencephalogram (EEG), a K-Nearest Neighbor, a Radial Basis Support Vector Machine, and a Linear Discriminant Analysis classifier are used. The classifier features are obtained from the Canonical Polyadic Decomposition (CPD) and Block Term Decomposition (BTD) of the EEG data represented as third order tensor. To expand the EEG into a tensor, Wavelet or Hilbert-Huang transform are used. The algorithm is tested on a scalp EEG database of 139 seizures of different duration. The experimental results suggest that a Hilbert-Huang tensor representation and the CPD analysis provide the most suitable framework for nonconvulsive seizure detection. The Radial Basis Support Vector Machine classifier shows the best performance with sensitivity, specificity, and accuracy values over 98%. A rough comparison with other methods proposed in the literature shows the superior performance of the proposed method for nonconvulsive epileptic seizure detection.

KW - Hilbert Huang Transform

KW - Multiway Data Analysis

KW - Nonconvulsive epileptic seizures

KW - Wavelet Transform

UR - http://www.scopus.com/inward/record.url?scp=85062585225&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2018.2829877

DO - 10.1109/JBHI.2018.2829877

M3 - Article

C2 - 29994034

AN - SCOPUS:85062585225

VL - 23

SP - 660

EP - 671

IS - 2

M1 - 8351633

ER -

Aldana YR, Hunyadi B, Reyes EJM, Rodríguez VR, Van Huffel S. Nonconvulsive Epileptic Seizure Detection in Scalp EEG Using Multiway Data Analysis. IEEE Journal of Biomedical and Health Informatics. 2019 Mar 1;23(2):660-671. 8351633. https://doi.org/10.1109/JBHI.2018.2829877