Prediction of human epileptic seizures based on optimization and phase changes of brain electrical activity

Leonidas D. Iasemidis, Panos M. Pardalos, Deng Shan Shiau, Wanpracha Chaovalitwongse, Narayanan Krishnamurthi, Shiv Kumar, Paul R. Carney, J. Chris Sakellares

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

The phenomenon of epilepsy, one of the most common neurological disorders, constitutes a unique opportunity to study the dynamics of spatiotemporal state transitions in real, complex, nonlinear dynamical systems. We previously demonstrated that measures of chaos and angular frequency obtained from electroencephalographic (EEG) signals generated by critical sites in the cerebral cortex converge progressively (dynamical entrainment) from the asymptomatic interictal state to the ictal state (seizure) [L.D. Iasemidis, P. Pardalos, J.C. Sackellares and D.-S. Shiau (2001). Quadratic binary programming and dynamical system approach to determine the predictability of epileptic seizures. J. Combinatorial Optimization, 5, 9-26; L.D. Iasemidis, D.-S. Shiau, P.M. Pardalos and J.C. Sackellares (2002). Phase entrainment and predictability of epileptic seizures. In: P.M. Pardalos and J. Principe (Eds.), Biocomputing, pp. 59-84. Kluwer Academic Publishers]. This observation suggests the possibility of developing algorithms to predict seizures. One of the central points of those investigations was the application of optimization theory, specifically quadratic zero-one programming, for the selection of the cortical sites that exhibit preictal dynamical entrainment. In this study we present results from the application of this methodology to the prediction of epileptic seizures. Analysis of continuous, long-term (18-140 h), multielectrode EEG recordings from 5 patients resulted in the prediction of 88% of the impending 50 seizures, on average about 83 min prior to seizure onset, with an average false warning rate of one every 5.26 h. These results suggest that this seizure prediction algorithm performs well enough to be used in diagnostic and therapeutic applications in epileptic patients. Similar algorithms may be useful for certain spatiotemporal state transitions in other physical and biological systems.

Original languageEnglish (US)
Pages (from-to)81-104
Number of pages24
JournalOptimization Methods and Software
Volume18
Issue number1
DOIs
StatePublished - Feb 2003

Fingerprint

Entrainment
Phase Change
Brain
Predictability
State Transition
Optimization
Prediction
Programming
Nonlinear dynamical systems
Epilepsy
Optimization Theory
Combinatorial optimization
Nonlinear Dynamical Systems
Combinatorial Optimization
Biological systems
Cortex
Biological Systems
Chaos theory
Disorder
Diagnostics

Keywords

  • Automated seizure warning algorithm
  • Global optimization
  • Phase change
  • T-index

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Software
  • Applied Mathematics
  • Control and Optimization
  • Management Science and Operations Research

Cite this

Prediction of human epileptic seizures based on optimization and phase changes of brain electrical activity. / Iasemidis, Leonidas D.; Pardalos, Panos M.; Shiau, Deng Shan; Chaovalitwongse, Wanpracha; Krishnamurthi, Narayanan; Kumar, Shiv; Carney, Paul R.; Sakellares, J. Chris.

In: Optimization Methods and Software, Vol. 18, No. 1, 02.2003, p. 81-104.

Research output: Contribution to journalArticle

Iasemidis, LD, Pardalos, PM, Shiau, DS, Chaovalitwongse, W, Krishnamurthi, N, Kumar, S, Carney, PR & Sakellares, JC 2003, 'Prediction of human epileptic seizures based on optimization and phase changes of brain electrical activity', Optimization Methods and Software, vol. 18, no. 1, pp. 81-104. https://doi.org/10.1080/1055678021000054998
Iasemidis, Leonidas D. ; Pardalos, Panos M. ; Shiau, Deng Shan ; Chaovalitwongse, Wanpracha ; Krishnamurthi, Narayanan ; Kumar, Shiv ; Carney, Paul R. ; Sakellares, J. Chris. / Prediction of human epileptic seizures based on optimization and phase changes of brain electrical activity. In: Optimization Methods and Software. 2003 ; Vol. 18, No. 1. pp. 81-104.
@article{e5a019d327824181ae3305501b7b4c94,
title = "Prediction of human epileptic seizures based on optimization and phase changes of brain electrical activity",
abstract = "The phenomenon of epilepsy, one of the most common neurological disorders, constitutes a unique opportunity to study the dynamics of spatiotemporal state transitions in real, complex, nonlinear dynamical systems. We previously demonstrated that measures of chaos and angular frequency obtained from electroencephalographic (EEG) signals generated by critical sites in the cerebral cortex converge progressively (dynamical entrainment) from the asymptomatic interictal state to the ictal state (seizure) [L.D. Iasemidis, P. Pardalos, J.C. Sackellares and D.-S. Shiau (2001). Quadratic binary programming and dynamical system approach to determine the predictability of epileptic seizures. J. Combinatorial Optimization, 5, 9-26; L.D. Iasemidis, D.-S. Shiau, P.M. Pardalos and J.C. Sackellares (2002). Phase entrainment and predictability of epileptic seizures. In: P.M. Pardalos and J. Principe (Eds.), Biocomputing, pp. 59-84. Kluwer Academic Publishers]. This observation suggests the possibility of developing algorithms to predict seizures. One of the central points of those investigations was the application of optimization theory, specifically quadratic zero-one programming, for the selection of the cortical sites that exhibit preictal dynamical entrainment. In this study we present results from the application of this methodology to the prediction of epileptic seizures. Analysis of continuous, long-term (18-140 h), multielectrode EEG recordings from 5 patients resulted in the prediction of 88{\%} of the impending 50 seizures, on average about 83 min prior to seizure onset, with an average false warning rate of one every 5.26 h. These results suggest that this seizure prediction algorithm performs well enough to be used in diagnostic and therapeutic applications in epileptic patients. Similar algorithms may be useful for certain spatiotemporal state transitions in other physical and biological systems.",
keywords = "Automated seizure warning algorithm, Global optimization, Phase change, T-index",
author = "Iasemidis, {Leonidas D.} and Pardalos, {Panos M.} and Shiau, {Deng Shan} and Wanpracha Chaovalitwongse and Narayanan Krishnamurthi and Shiv Kumar and Carney, {Paul R.} and Sakellares, {J. Chris}",
year = "2003",
month = "2",
doi = "10.1080/1055678021000054998",
language = "English (US)",
volume = "18",
pages = "81--104",
journal = "Optimization Methods and Software",
issn = "1055-6788",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

TY - JOUR

T1 - Prediction of human epileptic seizures based on optimization and phase changes of brain electrical activity

AU - Iasemidis, Leonidas D.

AU - Pardalos, Panos M.

AU - Shiau, Deng Shan

AU - Chaovalitwongse, Wanpracha

AU - Krishnamurthi, Narayanan

AU - Kumar, Shiv

AU - Carney, Paul R.

AU - Sakellares, J. Chris

PY - 2003/2

Y1 - 2003/2

N2 - The phenomenon of epilepsy, one of the most common neurological disorders, constitutes a unique opportunity to study the dynamics of spatiotemporal state transitions in real, complex, nonlinear dynamical systems. We previously demonstrated that measures of chaos and angular frequency obtained from electroencephalographic (EEG) signals generated by critical sites in the cerebral cortex converge progressively (dynamical entrainment) from the asymptomatic interictal state to the ictal state (seizure) [L.D. Iasemidis, P. Pardalos, J.C. Sackellares and D.-S. Shiau (2001). Quadratic binary programming and dynamical system approach to determine the predictability of epileptic seizures. J. Combinatorial Optimization, 5, 9-26; L.D. Iasemidis, D.-S. Shiau, P.M. Pardalos and J.C. Sackellares (2002). Phase entrainment and predictability of epileptic seizures. In: P.M. Pardalos and J. Principe (Eds.), Biocomputing, pp. 59-84. Kluwer Academic Publishers]. This observation suggests the possibility of developing algorithms to predict seizures. One of the central points of those investigations was the application of optimization theory, specifically quadratic zero-one programming, for the selection of the cortical sites that exhibit preictal dynamical entrainment. In this study we present results from the application of this methodology to the prediction of epileptic seizures. Analysis of continuous, long-term (18-140 h), multielectrode EEG recordings from 5 patients resulted in the prediction of 88% of the impending 50 seizures, on average about 83 min prior to seizure onset, with an average false warning rate of one every 5.26 h. These results suggest that this seizure prediction algorithm performs well enough to be used in diagnostic and therapeutic applications in epileptic patients. Similar algorithms may be useful for certain spatiotemporal state transitions in other physical and biological systems.

AB - The phenomenon of epilepsy, one of the most common neurological disorders, constitutes a unique opportunity to study the dynamics of spatiotemporal state transitions in real, complex, nonlinear dynamical systems. We previously demonstrated that measures of chaos and angular frequency obtained from electroencephalographic (EEG) signals generated by critical sites in the cerebral cortex converge progressively (dynamical entrainment) from the asymptomatic interictal state to the ictal state (seizure) [L.D. Iasemidis, P. Pardalos, J.C. Sackellares and D.-S. Shiau (2001). Quadratic binary programming and dynamical system approach to determine the predictability of epileptic seizures. J. Combinatorial Optimization, 5, 9-26; L.D. Iasemidis, D.-S. Shiau, P.M. Pardalos and J.C. Sackellares (2002). Phase entrainment and predictability of epileptic seizures. In: P.M. Pardalos and J. Principe (Eds.), Biocomputing, pp. 59-84. Kluwer Academic Publishers]. This observation suggests the possibility of developing algorithms to predict seizures. One of the central points of those investigations was the application of optimization theory, specifically quadratic zero-one programming, for the selection of the cortical sites that exhibit preictal dynamical entrainment. In this study we present results from the application of this methodology to the prediction of epileptic seizures. Analysis of continuous, long-term (18-140 h), multielectrode EEG recordings from 5 patients resulted in the prediction of 88% of the impending 50 seizures, on average about 83 min prior to seizure onset, with an average false warning rate of one every 5.26 h. These results suggest that this seizure prediction algorithm performs well enough to be used in diagnostic and therapeutic applications in epileptic patients. Similar algorithms may be useful for certain spatiotemporal state transitions in other physical and biological systems.

KW - Automated seizure warning algorithm

KW - Global optimization

KW - Phase change

KW - T-index

UR - http://www.scopus.com/inward/record.url?scp=0038359358&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0038359358&partnerID=8YFLogxK

U2 - 10.1080/1055678021000054998

DO - 10.1080/1055678021000054998

M3 - Article

AN - SCOPUS:0038359358

VL - 18

SP - 81

EP - 104

JO - Optimization Methods and Software

JF - Optimization Methods and Software

SN - 1055-6788

IS - 1

ER -