Seizure warning algorithm based on optimization and nonlinear dynamics

  • Authors:

  • Panos M. Pardalos; Wanpracha Chaovalitwongse;Leonidas D. Iasemidis;J. Chris Sackellares;Deng-Shan Shiau;Paul R. Carney;Oleg A. Prokopyev;Vitaliy A. Yatsenko

  • Affiliations:

  • University of Florida, Departments of Industrial and Systems Engineering and Biomedical Engineering, USA;University of Florida, Departments of Industrial and Systems Engineering and Neuroscience, USA;Arizona State University, Departments of Biomedical Engineering and Electrical Engineering, USA;University of Florida, Departments of Neuroscience, Neurology and Biomedical Engineering, USA;University of Florida, Department of Neuroscience, USA;University of Florida, Departments of Pediatrics, Neuroscience, and Neurology, USA;University of Florida, Department of Industrial and Systems Engineering, USA;University of Florida, Department of Neuroscience, USA

  • Venue:
  • Mathematical Programming: Series A and B
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

There is growing evidence that temporal lobe seizures are preceded by a preictal transition, characterized by a gradual dynamical change from asymptomatic interictal state to seizure. We herein report the first prospective analysis of the online automated algorithm for detecting the preictal transition in ongoing EEG signals. Such, the algorithm constitutes a seizure warning system. The algorithm estimates STLmax, a measure of the order or disorder of the signal, of EEG signals recorded from individual electrode sites. The optimization techniques were employed to select critical brain electrode sites that exhibit the preictal transition for the warning of epileptic seizures. Specifically, a quadratically constrained quadratic 0-1 programming problem is formulated to identify critical electrode sites. The automated seizure warning algorithm was tested in continuous, long-term EEG recordings obtained from 5 patients with temporal lobe epilepsy. For individual patient, we use the first half of seizures to train the parameter settings, which is evaluated by ROC (Receiver Operating Characteristic) curve analysis. With the best parameter setting, the algorithm applied to all cases predicted an average of 91.7% of seizures with an average false prediction rate of 0.196 per hour. These results indicate that it may be possible to develop automated seizure warning devices for diagnostic and therapeutic purposes.