Anticipating the unobserved: prediction of subclinical seizures

Hinnerk Feldwisch-Drentrup, Matthias Ihle, Michel Le Van Quyen, Cesar Teixeira, Antonio Dourado, Jens Timmer, Francisco Sales, Vincent Navarro, Andreas Schulze-Bonhage, Bjoern Schelter

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

Subclinical seizures (SCS) have rarely been considered in the diagnosis and therapy of epilepsy and have not been systematically analyzed in studies on seizure prediction. Here, we investigate whether predictions of subclinical seizures are feasible and how their occurrence may affect the performance of prediction algorithms. Using the European database of long-term recordings of surface and invasive electroencephalography data, we analyzed the data from 21 patients with SCS, including in total 413 clinically manifest seizures (CS) and 3341 SCS. Based on the mean phase coherence we investigated the predictive performance of CS and SCS. The two types of seizures had similar prediction sensitivities. Significant performance was found considerably more often for SCS than for CS, especially for patients with invasive recordings. When analyzing false alarms triggered by predicting CS, a significant number of these false predictions were followed by SCS for 9 of 21 patients. Although currently observed prediction performance may not be deemed sufficient for clinical applications for the majority of the patients, it can be concluded that the prediction of SCS is feasible on a similar level as for CS and allows a prediction of more of the seizures impairing patients, possibly also reducing the number of false alarms that were in fact correct predictions of CS.

This article is part of a Supplemental Special Issue entitled The Future of Automated Seizure Detection and Prediction. (C) 2011 Elsevier Inc. All rights reserved.

Original languageEnglish
Pages (from-to)S119-S126
Number of pages8
JournalEpilepsy and Behavior
Volume22
Issue numberSuppl. 1
DOIs
Publication statusPublished - Dec 2011

Keywords

  • subclinical seizure
  • electrographic seizure
  • epilepsy
  • seizure prediction
  • mean phase coherence
  • random predictor

Cite this

Feldwisch-Drentrup, H., Ihle, M., Le Van Quyen, M., Teixeira, C., Dourado, A., Timmer, J., ... Schelter, B. (2011). Anticipating the unobserved: prediction of subclinical seizures. Epilepsy and Behavior, 22(Suppl. 1), S119-S126. https://doi.org/10.1016/j.yebeh.2011.08.023

Anticipating the unobserved : prediction of subclinical seizures. / Feldwisch-Drentrup, Hinnerk; Ihle, Matthias; Le Van Quyen, Michel; Teixeira, Cesar; Dourado, Antonio; Timmer, Jens; Sales, Francisco; Navarro, Vincent; Schulze-Bonhage, Andreas; Schelter, Bjoern.

In: Epilepsy and Behavior, Vol. 22, No. Suppl. 1, 12.2011, p. S119-S126.

Research output: Contribution to journalArticle

Feldwisch-Drentrup, H, Ihle, M, Le Van Quyen, M, Teixeira, C, Dourado, A, Timmer, J, Sales, F, Navarro, V, Schulze-Bonhage, A & Schelter, B 2011, 'Anticipating the unobserved: prediction of subclinical seizures', Epilepsy and Behavior, vol. 22, no. Suppl. 1, pp. S119-S126. https://doi.org/10.1016/j.yebeh.2011.08.023
Feldwisch-Drentrup H, Ihle M, Le Van Quyen M, Teixeira C, Dourado A, Timmer J et al. Anticipating the unobserved: prediction of subclinical seizures. Epilepsy and Behavior. 2011 Dec;22(Suppl. 1):S119-S126. https://doi.org/10.1016/j.yebeh.2011.08.023
Feldwisch-Drentrup, Hinnerk ; Ihle, Matthias ; Le Van Quyen, Michel ; Teixeira, Cesar ; Dourado, Antonio ; Timmer, Jens ; Sales, Francisco ; Navarro, Vincent ; Schulze-Bonhage, Andreas ; Schelter, Bjoern. / Anticipating the unobserved : prediction of subclinical seizures. In: Epilepsy and Behavior. 2011 ; Vol. 22, No. Suppl. 1. pp. S119-S126.
@article{dfc15051917c40369c87f0307288f3f7,
title = "Anticipating the unobserved: prediction of subclinical seizures",
abstract = "Subclinical seizures (SCS) have rarely been considered in the diagnosis and therapy of epilepsy and have not been systematically analyzed in studies on seizure prediction. Here, we investigate whether predictions of subclinical seizures are feasible and how their occurrence may affect the performance of prediction algorithms. Using the European database of long-term recordings of surface and invasive electroencephalography data, we analyzed the data from 21 patients with SCS, including in total 413 clinically manifest seizures (CS) and 3341 SCS. Based on the mean phase coherence we investigated the predictive performance of CS and SCS. The two types of seizures had similar prediction sensitivities. Significant performance was found considerably more often for SCS than for CS, especially for patients with invasive recordings. When analyzing false alarms triggered by predicting CS, a significant number of these false predictions were followed by SCS for 9 of 21 patients. Although currently observed prediction performance may not be deemed sufficient for clinical applications for the majority of the patients, it can be concluded that the prediction of SCS is feasible on a similar level as for CS and allows a prediction of more of the seizures impairing patients, possibly also reducing the number of false alarms that were in fact correct predictions of CS.This article is part of a Supplemental Special Issue entitled The Future of Automated Seizure Detection and Prediction. (C) 2011 Elsevier Inc. All rights reserved.",
keywords = "subclinical seizure, electrographic seizure, epilepsy, seizure prediction, mean phase coherence, random predictor",
author = "Hinnerk Feldwisch-Drentrup and Matthias Ihle and {Le Van Quyen}, Michel and Cesar Teixeira and Antonio Dourado and Jens Timmer and Francisco Sales and Vincent Navarro and Andreas Schulze-Bonhage and Bjoern Schelter",
year = "2011",
month = "12",
doi = "10.1016/j.yebeh.2011.08.023",
language = "English",
volume = "22",
pages = "S119--S126",
journal = "Epilepsy and Behavior",
issn = "1525-5050",
publisher = "Academic Press Inc.",
number = "Suppl. 1",

}

TY - JOUR

T1 - Anticipating the unobserved

T2 - prediction of subclinical seizures

AU - Feldwisch-Drentrup, Hinnerk

AU - Ihle, Matthias

AU - Le Van Quyen, Michel

AU - Teixeira, Cesar

AU - Dourado, Antonio

AU - Timmer, Jens

AU - Sales, Francisco

AU - Navarro, Vincent

AU - Schulze-Bonhage, Andreas

AU - Schelter, Bjoern

PY - 2011/12

Y1 - 2011/12

N2 - Subclinical seizures (SCS) have rarely been considered in the diagnosis and therapy of epilepsy and have not been systematically analyzed in studies on seizure prediction. Here, we investigate whether predictions of subclinical seizures are feasible and how their occurrence may affect the performance of prediction algorithms. Using the European database of long-term recordings of surface and invasive electroencephalography data, we analyzed the data from 21 patients with SCS, including in total 413 clinically manifest seizures (CS) and 3341 SCS. Based on the mean phase coherence we investigated the predictive performance of CS and SCS. The two types of seizures had similar prediction sensitivities. Significant performance was found considerably more often for SCS than for CS, especially for patients with invasive recordings. When analyzing false alarms triggered by predicting CS, a significant number of these false predictions were followed by SCS for 9 of 21 patients. Although currently observed prediction performance may not be deemed sufficient for clinical applications for the majority of the patients, it can be concluded that the prediction of SCS is feasible on a similar level as for CS and allows a prediction of more of the seizures impairing patients, possibly also reducing the number of false alarms that were in fact correct predictions of CS.This article is part of a Supplemental Special Issue entitled The Future of Automated Seizure Detection and Prediction. (C) 2011 Elsevier Inc. All rights reserved.

AB - Subclinical seizures (SCS) have rarely been considered in the diagnosis and therapy of epilepsy and have not been systematically analyzed in studies on seizure prediction. Here, we investigate whether predictions of subclinical seizures are feasible and how their occurrence may affect the performance of prediction algorithms. Using the European database of long-term recordings of surface and invasive electroencephalography data, we analyzed the data from 21 patients with SCS, including in total 413 clinically manifest seizures (CS) and 3341 SCS. Based on the mean phase coherence we investigated the predictive performance of CS and SCS. The two types of seizures had similar prediction sensitivities. Significant performance was found considerably more often for SCS than for CS, especially for patients with invasive recordings. When analyzing false alarms triggered by predicting CS, a significant number of these false predictions were followed by SCS for 9 of 21 patients. Although currently observed prediction performance may not be deemed sufficient for clinical applications for the majority of the patients, it can be concluded that the prediction of SCS is feasible on a similar level as for CS and allows a prediction of more of the seizures impairing patients, possibly also reducing the number of false alarms that were in fact correct predictions of CS.This article is part of a Supplemental Special Issue entitled The Future of Automated Seizure Detection and Prediction. (C) 2011 Elsevier Inc. All rights reserved.

KW - subclinical seizure

KW - electrographic seizure

KW - epilepsy

KW - seizure prediction

KW - mean phase coherence

KW - random predictor

U2 - 10.1016/j.yebeh.2011.08.023

DO - 10.1016/j.yebeh.2011.08.023

M3 - Article

VL - 22

SP - S119-S126

JO - Epilepsy and Behavior

JF - Epilepsy and Behavior

SN - 1525-5050

IS - Suppl. 1

ER -