A Comparative Study of Intracranial EEG Files Using Nonlinear Classification Methods

This study is a comparative evaluation of nonlinear classification methods with a focus on nonlinear decision functions and the standard method of support vector machines for seizure detection. These nonlinear classification methods are used on key features that were extracted on subdural EEG data after a thorough evaluation of all the frequency bands from 1 to 44 Hz. The sensitivity, specificity, and accuracy of seizure detection reveal that the gamma frequencies (36–44 Hz) are most suitable for detecting seizure files using a unique 2D decisional plane. We evaluated 157 intracranial EEG files from 14 patients by calculating the spectral power using nonoverlapping 1-s windows on different frequency bands. A key finding is in establishing a 2D decision plane, where duration of the seizure is used as the first dimension (x coordinate) and the maximum of the gamma frequency components is used as the second dimension (y coordinate). Within this 2D plane, the best results were observed when the nonlinearity degree is three for the proposed nonlinear decision functions, with a sensitivity of 96.3%, a specificity of 96.8%, and accuracy of 96.7%.

[1]  Giancarlo Calvagno,et al.  A multiresolution approach to spike detection in EEG , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[2]  Brian Litt,et al.  Epileptic seizure prediction using hybrid feature selection over multiple intracranial EEG electrode contacts: a report of four patients , 2003, IEEE Transactions on Biomedical Engineering.

[3]  Itzhak Fried,et al.  Analysis of Seizure Onset on the Basis of Wideband EEG Recordings , 2005, Epilepsia.

[4]  J. Gotman.  Automatic recognition of epileptic seizures in the EEG. , 1982, Electroencephalography and clinical neurophysiology.

[5]  Malek Adjouadi,et al.  Pattern extraction in interictal EEG recordings towards detection of electrodes leading to seizures. , 2006, Biomedical sciences instrumentation.

[6]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[7]  Alfonso M Albano,et al.  Optimization of Embedding Parameters for Prediction of Seizure Onset with Mutual Information , 2001 .

[8]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[9]  Hojjat Adeli,et al.  Principal Component Analysis-Enhanced Cosine Radial Basis Function Neural Network for Robust Epilepsy and Seizure Detection , 2008, IEEE Transactions on Biomedical Engineering.

[10]  Dennis Dlugos,et al.  Neonatal seizure detection using multichannel display of envelope trend , 2008, Epilepsia.

[11]  P. Grassberger,et al.  A robust method for detecting interdependences: application to intracranially recorded EEG , 1999, chao-dyn/9907013.

[12]  Carmen Barba,et al.  Correlation between Provoked Ictal SPECT and Depth Recordings in Adult Drug‐Resistant Epilepsy Patients , 2007, Epilepsia.

[13]  J Gotman,et al.  Separation of spikes from background by independent component analysis with dipole modeling and comparison to intracranial recording , 2001, Clinical Neurophysiology.

[14]  J. Martinerie,et al.  Epileptic seizures can be anticipated by non-linear analysis , 1998, Nature Medicine.

[15]  George J. Vachtsevanos,et al.  Genetic programming of conventional features to detect seizure precursors , 2007, Eng. Appl. Artif. Intell..

[16]  R. Larter,et al.  A coupled ordinary differential equation lattice model for the simulation of epileptic seizures. , 1999, Chaos.

[17]  N. Thakor,et al.  Time-Dependent Entropy Estimation of EEG Rhythm Changes Following Brain Ischemia , 2003, Annals of Biomedical Engineering.

[18]  Ying-Cheng Lai,et al.  Inability of Lyapunov exponents to predict epileptic seizures. , 2003, Physical review letters.

[19]  A J Gabor,et al.  Seizure detection using a self-organizing neural network: validation and comparison with other detection strategies. , 1998, Electroencephalography and clinical neurophysiology.

[20]  G. Luef,et al.  Brain‐type Natriuretic Peptide Release and Seizure Activity during Vagal Nerve Stimulation , 2007, Epilepsia.

[21]  Ilker Yaylali,et al.  Interictal spike detection using the Walsh transform , 2004, IEEE Transactions on Biomedical Engineering.

[22]  M. Okada,et al.  Effects of Antiepileptic Drugs on K+‐Induced Glutamate Release and Spreading Depression in the Hippocampus Determined with an In Vivo Microdialysis Glutamate Biosensor (MGB) , 1998 .

[23]  Ali Shoeb,et al.  Patient-specific seizure onset detection. , 2004, Epilepsy & behavior : E&B.

[24]  Christopher Essex,et al.  Chaotic time series analyses of epileptic seizures , 1990 .

[25]  J Gotman,et al.  Automatic detection of seizures and spikes. , 1999, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[26]  B. Hjorth.  The physical significance of time domain descriptors in EEG analysis. , 1973, Electroencephalography and clinical neurophysiology.

[27]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[28]  Ilker Yaylali,et al.  Detection of Interictal Spikes and Artifactual Data Through Orthogonal Transformations , 2005, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.