Epilepsy Research 64 (2005) 93–113 Performance of a seizure warning algorithm based on the dynamics of intracranial EEG W. Chaovalitwongse a,b,c,d,e,h,m , L.D. Iasemidis b,l , P.M. Pardalos b,e,f,g , P.R. Carney b,d,f,h,i,j , D.-S. Shiau b,d,h,m , J.C. Sackellares b,d,f,h,i,j,k,m,∗ a Department of Industrial and Systems Engineering, Rutgers, The State University of New Jersey, Piscataway, NJ 08854, USA b Bioengineering Research Partnership in Brain Dynamics, University of Florida, Gainesville, FL 32611, USA c Center for Applied Optimization, University of Florida, Gainesville, FL 32611, USA d McKnight Brain Institute, University of Florida, Gainesville, FL 32611, USA e Departments of Industrial and Systems Engineering, University of Florida, Gainesville, FL 32611, USA f Department of Biomedical Engineering, University of Florida, Gainesville, FL 32611, USA g Departments of Computer and Information Science and Engineering, University of Florida, Gainesville, FL 32611, USA h Department of Neuroscience, University of Florida, Gainesville, FL 32611, USA i Department of Pediatrics, University of Florida, Gainesville, FL 32611, USA j Department of Neurology, University of Florida, Gainesville, FL 32611, USA k Department of Psychiatry, University of Florida, Gainesville, FL 32611, USA l The Harrington Department of Bioengineering, Arizona State University, Tempe, AZ 85287, USA m Malcolm Randall V.A. Medical Center, Gainesville, FL 32611, USA Received 9 February 2004; received in revised form 30 September 2004; accepted 10 March 2005 Abstract During the past decade, several studies have demonstrated experimental evidence that temporal lobe seizures are preceded by changes in dynamical properties (both spatial and temporal) of electroencephalograph (EEG) signals. In this study, we evaluate a method, based on chaos theory and global optimization techniques, for detecting pre-seizure states by monitoring the spatio- temporal changes in the dynamics of the EEG signal. The method employs the estimation of the short-term maximum Lyapunov exponent (STL max ), a measure of the order (chaoticity) of a dynamical system, to quantify the EEG dynamics per electrode site. A global optimization technique is also employed to identify critical electrode sites that are involved in the seizure development. An important practical result of this study was the development of an automated seizure warning system (ASWS). The algorithm was tested in continuous, long-term EEG recordings, 3–14 days in duration, obtained from 10 patients with refractory temporal lobe epilepsy. In this analysis, for each patient, the EEG recordings were divided into training and testing ∗ Corresponding author. Present address: Department of Neuroscience, McKnight Brain Institute, P.O. Box 100244, University of Florida, FL 32610-0244, USA. Tel.: +1 352 2735409; fax: +1 352 2735411. E-mail address: sackellares@mbi.ufl.edu (J.C. Sackellares). 0920-1211/$ – see front matter © 2005 Elsevier B.V. All rights reserved. doi:10.1016/j.eplepsyres.2005.03.009