Application of a multivariate seizure detection and prediction method to non-invasive and intracranial long-term EEG recordings

Ariane Schad, Kaspar Schindler, Bjoern Schelter, Thomas Maiwald, Armin Brandt, Jens Timmer, Andreas Schulze-Bonhage

Research output: Contribution to journalArticle

61 Citations (Scopus)

Abstract

Objective: Retrospective evaluation and comparison of performances of a multivariate method for seizure detection and prediction on simultaneous long-term EEG recordings from scalp and intracranial electrodes.

Methods: Two multivariate techniques based on simulated leaky integrate-and-fire neurons were investigated in order to detect and predict seizures. Both methods were applied and assessed on 423 h of EEG and 26 seizures in total, recorded simultaneously from the scalp and intracranially continuously over several days from six patients with pharmacorefractory epilepsy.

Results: Features generated from simultaneous scalp and intracranial EEG data showed a similar dynamical behavior. Significant performances with sensitivities of up to 73%/62%,, for scalp/invasive EEG recordings given an upper limit of 0.15 false detections per hour were obtained. Up to 59%/50% of all seizures could be predicted from scalp/invasive EEG, given a maximum number of 0.15 false predictions per hour. A tendency to better performances for scalp EEG was obtained for the detection algorithm.

Conclusions: The investigated methods originally developed for non-invasive EEG were successfully applied to intracranial EEG. Especially, concerning seizure detection the method shows a promising performance which is appropriate for practical applications in EEG monitoring. Concerning seizure prediction a significant prediction performance is indicated and a modification of the method is suggested.

Significance: This study evaluates simultaneously recorded non-invasive and intracranial continuous long-term EEG data with respect to seizure detection and seizure prediction for the first time. (c) 2007 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

Original languageEnglish
Pages (from-to)197-211
Number of pages15
JournalClinical Neurophysiology
Volume119
Issue number1
Early online date26 Nov 2007
DOIs
Publication statusPublished - Jan 2008

Keywords

  • epilepsy
  • long-term EEG analysis
  • intracranial EEG
  • non-invasive EEG
  • seizure detection
  • seizure prediction

Cite this

Application of a multivariate seizure detection and prediction method to non-invasive and intracranial long-term EEG recordings. / Schad, Ariane; Schindler, Kaspar; Schelter, Bjoern; Maiwald, Thomas; Brandt, Armin; Timmer, Jens; Schulze-Bonhage, Andreas.

In: Clinical Neurophysiology, Vol. 119, No. 1, 01.2008, p. 197-211.

Research output: Contribution to journalArticle

Schad, Ariane ; Schindler, Kaspar ; Schelter, Bjoern ; Maiwald, Thomas ; Brandt, Armin ; Timmer, Jens ; Schulze-Bonhage, Andreas. / Application of a multivariate seizure detection and prediction method to non-invasive and intracranial long-term EEG recordings. In: Clinical Neurophysiology. 2008 ; Vol. 119, No. 1. pp. 197-211.
@article{413b3fff1f854e3c91b3ec4b75e4a726,
title = "Application of a multivariate seizure detection and prediction method to non-invasive and intracranial long-term EEG recordings",
abstract = "Objective: Retrospective evaluation and comparison of performances of a multivariate method for seizure detection and prediction on simultaneous long-term EEG recordings from scalp and intracranial electrodes.Methods: Two multivariate techniques based on simulated leaky integrate-and-fire neurons were investigated in order to detect and predict seizures. Both methods were applied and assessed on 423 h of EEG and 26 seizures in total, recorded simultaneously from the scalp and intracranially continuously over several days from six patients with pharmacorefractory epilepsy.Results: Features generated from simultaneous scalp and intracranial EEG data showed a similar dynamical behavior. Significant performances with sensitivities of up to 73{\%}/62{\%},, for scalp/invasive EEG recordings given an upper limit of 0.15 false detections per hour were obtained. Up to 59{\%}/50{\%} of all seizures could be predicted from scalp/invasive EEG, given a maximum number of 0.15 false predictions per hour. A tendency to better performances for scalp EEG was obtained for the detection algorithm.Conclusions: The investigated methods originally developed for non-invasive EEG were successfully applied to intracranial EEG. Especially, concerning seizure detection the method shows a promising performance which is appropriate for practical applications in EEG monitoring. Concerning seizure prediction a significant prediction performance is indicated and a modification of the method is suggested.Significance: This study evaluates simultaneously recorded non-invasive and intracranial continuous long-term EEG data with respect to seizure detection and seizure prediction for the first time. (c) 2007 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.",
keywords = "epilepsy, long-term EEG analysis, intracranial EEG, non-invasive EEG, seizure detection, seizure prediction",
author = "Ariane Schad and Kaspar Schindler and Bjoern Schelter and Thomas Maiwald and Armin Brandt and Jens Timmer and Andreas Schulze-Bonhage",
year = "2008",
month = "1",
doi = "10.1016/j.clinph.2007.09.130",
language = "English",
volume = "119",
pages = "197--211",
journal = "Clinical Neurophysiology",
issn = "1388-2457",
publisher = "Elsevier Ireland Ltd",
number = "1",

}

TY - JOUR

T1 - Application of a multivariate seizure detection and prediction method to non-invasive and intracranial long-term EEG recordings

AU - Schad, Ariane

AU - Schindler, Kaspar

AU - Schelter, Bjoern

AU - Maiwald, Thomas

AU - Brandt, Armin

AU - Timmer, Jens

AU - Schulze-Bonhage, Andreas

PY - 2008/1

Y1 - 2008/1

N2 - Objective: Retrospective evaluation and comparison of performances of a multivariate method for seizure detection and prediction on simultaneous long-term EEG recordings from scalp and intracranial electrodes.Methods: Two multivariate techniques based on simulated leaky integrate-and-fire neurons were investigated in order to detect and predict seizures. Both methods were applied and assessed on 423 h of EEG and 26 seizures in total, recorded simultaneously from the scalp and intracranially continuously over several days from six patients with pharmacorefractory epilepsy.Results: Features generated from simultaneous scalp and intracranial EEG data showed a similar dynamical behavior. Significant performances with sensitivities of up to 73%/62%,, for scalp/invasive EEG recordings given an upper limit of 0.15 false detections per hour were obtained. Up to 59%/50% of all seizures could be predicted from scalp/invasive EEG, given a maximum number of 0.15 false predictions per hour. A tendency to better performances for scalp EEG was obtained for the detection algorithm.Conclusions: The investigated methods originally developed for non-invasive EEG were successfully applied to intracranial EEG. Especially, concerning seizure detection the method shows a promising performance which is appropriate for practical applications in EEG monitoring. Concerning seizure prediction a significant prediction performance is indicated and a modification of the method is suggested.Significance: This study evaluates simultaneously recorded non-invasive and intracranial continuous long-term EEG data with respect to seizure detection and seizure prediction for the first time. (c) 2007 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

AB - Objective: Retrospective evaluation and comparison of performances of a multivariate method for seizure detection and prediction on simultaneous long-term EEG recordings from scalp and intracranial electrodes.Methods: Two multivariate techniques based on simulated leaky integrate-and-fire neurons were investigated in order to detect and predict seizures. Both methods were applied and assessed on 423 h of EEG and 26 seizures in total, recorded simultaneously from the scalp and intracranially continuously over several days from six patients with pharmacorefractory epilepsy.Results: Features generated from simultaneous scalp and intracranial EEG data showed a similar dynamical behavior. Significant performances with sensitivities of up to 73%/62%,, for scalp/invasive EEG recordings given an upper limit of 0.15 false detections per hour were obtained. Up to 59%/50% of all seizures could be predicted from scalp/invasive EEG, given a maximum number of 0.15 false predictions per hour. A tendency to better performances for scalp EEG was obtained for the detection algorithm.Conclusions: The investigated methods originally developed for non-invasive EEG were successfully applied to intracranial EEG. Especially, concerning seizure detection the method shows a promising performance which is appropriate for practical applications in EEG monitoring. Concerning seizure prediction a significant prediction performance is indicated and a modification of the method is suggested.Significance: This study evaluates simultaneously recorded non-invasive and intracranial continuous long-term EEG data with respect to seizure detection and seizure prediction for the first time. (c) 2007 International Federation of Clinical Neurophysiology. Published by Elsevier Ireland Ltd. All rights reserved.

KW - epilepsy

KW - long-term EEG analysis

KW - intracranial EEG

KW - non-invasive EEG

KW - seizure detection

KW - seizure prediction

U2 - 10.1016/j.clinph.2007.09.130

DO - 10.1016/j.clinph.2007.09.130

M3 - Article

VL - 119

SP - 197

EP - 211

JO - Clinical Neurophysiology

JF - Clinical Neurophysiology

SN - 1388-2457

IS - 1

ER -