Online EEG seizure detection and localization

Amirsalar Mansouri, Sanjay P. Singh, Khalid Sayood

Research output: Contribution to journalArticle

Abstract

Epilepsy is one of the three most prevalent neurological disorders. A significant proportion of patients suffering from epilepsy can be effectively treated if their seizures are detected in a timely manner. However, detection of most seizures requires the attention of trained neurologists-a scarce resource. Therefore, there is a need for an automatic seizure detection capability. A tunable non-patient-specific, non-seizure-specific method is proposed to detect the presence and locality of a seizure using electroencephalography (EEG) signals. This multifaceted computational approach is based on a network model of the brain and a distance metric based on the spectral profiles of EEG signals. This computationally time-efficient and cost-effective automated epileptic seizure detection algorithm has a median latency of 8 s, a median sensitivity of 83%, and a median false alarm rate of 2.9%. Hence, it is capable of being used in portable EEG devices to aid in the process of detecting and monitoring epileptic patients.

Original languageEnglish (US)
Article number176
JournalAlgorithms
Volume12
Issue number9
DOIs
StatePublished - Sep 1 2019

Fingerprint

Electroencephalography
Epilepsy
Patient monitoring
False Alarm Rate
Distance Metric
Locality
Network Model
Latency
Disorder
Brain
Proportion
Monitoring
Resources
Costs

Keywords

  • EEG
  • Epilepsy
  • Network analysis
  • Non-patient-specific
  • On-line detection
  • PSD
  • Seizure

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Numerical Analysis
  • Computational Theory and Mathematics
  • Computational Mathematics

Cite this

Online EEG seizure detection and localization. / Mansouri, Amirsalar; Singh, Sanjay P.; Sayood, Khalid.

In: Algorithms, Vol. 12, No. 9, 176, 01.09.2019.

Research output: Contribution to journalArticle

Mansouri, Amirsalar ; Singh, Sanjay P. ; Sayood, Khalid. / Online EEG seizure detection and localization. In: Algorithms. 2019 ; Vol. 12, No. 9.
@article{d5380c1f9b024596b09768e164c95e5e,
title = "Online EEG seizure detection and localization",
abstract = "Epilepsy is one of the three most prevalent neurological disorders. A significant proportion of patients suffering from epilepsy can be effectively treated if their seizures are detected in a timely manner. However, detection of most seizures requires the attention of trained neurologists-a scarce resource. Therefore, there is a need for an automatic seizure detection capability. A tunable non-patient-specific, non-seizure-specific method is proposed to detect the presence and locality of a seizure using electroencephalography (EEG) signals. This multifaceted computational approach is based on a network model of the brain and a distance metric based on the spectral profiles of EEG signals. This computationally time-efficient and cost-effective automated epileptic seizure detection algorithm has a median latency of 8 s, a median sensitivity of 83{\%}, and a median false alarm rate of 2.9{\%}. Hence, it is capable of being used in portable EEG devices to aid in the process of detecting and monitoring epileptic patients.",
keywords = "EEG, Epilepsy, Network analysis, Non-patient-specific, On-line detection, PSD, Seizure",
author = "Amirsalar Mansouri and Singh, {Sanjay P.} and Khalid Sayood",
year = "2019",
month = "9",
day = "1",
doi = "10.3390/a12090176",
language = "English (US)",
volume = "12",
journal = "Algorithms",
issn = "1999-4893",
publisher = "MDPI AG",
number = "9",

}

TY - JOUR

T1 - Online EEG seizure detection and localization

AU - Mansouri, Amirsalar

AU - Singh, Sanjay P.

AU - Sayood, Khalid

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Epilepsy is one of the three most prevalent neurological disorders. A significant proportion of patients suffering from epilepsy can be effectively treated if their seizures are detected in a timely manner. However, detection of most seizures requires the attention of trained neurologists-a scarce resource. Therefore, there is a need for an automatic seizure detection capability. A tunable non-patient-specific, non-seizure-specific method is proposed to detect the presence and locality of a seizure using electroencephalography (EEG) signals. This multifaceted computational approach is based on a network model of the brain and a distance metric based on the spectral profiles of EEG signals. This computationally time-efficient and cost-effective automated epileptic seizure detection algorithm has a median latency of 8 s, a median sensitivity of 83%, and a median false alarm rate of 2.9%. Hence, it is capable of being used in portable EEG devices to aid in the process of detecting and monitoring epileptic patients.

AB - Epilepsy is one of the three most prevalent neurological disorders. A significant proportion of patients suffering from epilepsy can be effectively treated if their seizures are detected in a timely manner. However, detection of most seizures requires the attention of trained neurologists-a scarce resource. Therefore, there is a need for an automatic seizure detection capability. A tunable non-patient-specific, non-seizure-specific method is proposed to detect the presence and locality of a seizure using electroencephalography (EEG) signals. This multifaceted computational approach is based on a network model of the brain and a distance metric based on the spectral profiles of EEG signals. This computationally time-efficient and cost-effective automated epileptic seizure detection algorithm has a median latency of 8 s, a median sensitivity of 83%, and a median false alarm rate of 2.9%. Hence, it is capable of being used in portable EEG devices to aid in the process of detecting and monitoring epileptic patients.

KW - EEG

KW - Epilepsy

KW - Network analysis

KW - Non-patient-specific

KW - On-line detection

KW - PSD

KW - Seizure

UR - http://www.scopus.com/inward/record.url?scp=85072770656&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072770656&partnerID=8YFLogxK

U2 - 10.3390/a12090176

DO - 10.3390/a12090176

M3 - Article

AN - SCOPUS:85072770656

VL - 12

JO - Algorithms

JF - Algorithms

SN - 1999-4893

IS - 9

M1 - 176

ER -