Is Using Threshold-Crossing Method and Single Type of Features Sufficient to Achieve Realistic Application of Seizure Prediction?

Objective. This study aims to verify whether the simple threshold-crossing method can work well enough to achieve the realistic application of seizure prediction on the basis of a large public database, and examines how a more complex classifier can improve prediction performance. It also verified whether the combination of multiple types of features with a complex classifier can improve prediction performance. Method. Phase synchronization and spectral power features were extracted from electroencephalogram recordings. The threshold-crossing method and a support vector machine (SVM) were used to identify preictal and interictal samples. Based on the type of selected features and the manner of classification, 5 different methods were conducted on 19 patients. The performances of these methods were directly compared and tested using a random predictor. In-sample optimization problems were avoided in the feature and parameter selection procedure to obtain credible results. Results. The threshold-crossing method could only obtain satisfying prediction results for approximately half of the selected patients. The SVM classifier could significantly improve prediction performance compared with the threshold-crossing method for both types of features. Although the average performance was further improved when both types of features were combined with the SVM classifier, the improvement was insignificant. Conclusion. A complex classifier, such as the SVM, is recommended in a realistic prediction device, although it will increase the complexity of the device. Indeed, the simple threshold-crossing method performs well enough for some of the patients. The combination of phase synchronization and spectral power features is unnecessary because of the increased computation complexity.

[1]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[2]  A. Kraskov,et al.  On the predictability of epileptic seizures , 2005, Clinical Neurophysiology.

[3]  A. Schulze-Bonhage,et al.  Joining the benefits: Combining epileptic seizure prediction methods , 2010, Epilepsia.

[4]  J. Martinerie,et al.  Seizure anticipation in human neocortical partial epilepsy. , 2002, Brain : a journal of neurology.

[5]  Keshab K. Parhi,et al.  Seizure Prediction With Spectral Power of EEG Using Cost-Sensitive Support Vector Machines , 2010 .

[6]  Reza Fazel-Rezai,et al.  Seizure prediction using adaptive neuro-fuzzy inference system , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[7]  A. Schulze-Bonhage,et al.  How well can epileptic seizures be predicted? An evaluation of a nonlinear method. , 2003, Brain : a journal of neurology.

[8]  D. P. Mandic,et al.  Measuring phase synchrony using complex extensions of EMD , 2009, 2009 IEEE/SP 15th Workshop on Statistical Signal Processing.

[9]  W. J. Williams,et al.  Phase space topography and the Lyapunov exponent of electrocorticograms in partial seizures , 2005, Brain Topography.

[10]  F. Mormann,et al.  Epileptic seizures are preceded by a decrease in synchronization , 2003, Epilepsy Research.

[11]  Andreas Schulze-Bonhage,et al.  Testing statistical significance of multivariate time series analysis techniques for epileptic seizure prediction. , 2006, Chaos.

[12]  Gabriel Rilling,et al.  On empirical mode decomposition and its algorithms , 2003 .

[13]  Christopher J. C. Burges,et al.  A Tutorial on Support Vector Machines for Pattern Recognition , 1998, Data Mining and Knowledge Discovery.

[14]  Steve S. Chung,et al.  Electrical stimulation of the anterior nucleus of thalamus for treatment of refractory epilepsy , 2010, Epilepsia.

[15]  I. Gath,et al.  On the prediction of epileptic seizures , 1981, Biological Cybernetics.

[16]  Gabriel Rilling,et al.  Bivariate Empirical Mode Decomposition , 2007, IEEE Signal Processing Letters.

[17]  Mojtaba Bandarabadi,et al.  Epileptic seizure prediction using relative spectral power features , 2015, Clinical Neurophysiology.

[18]  Brian Litt,et al.  Detection of seizure precursors from depth-EEG using a sign periodogram transform , 2003, IEEE Transactions on Biomedical Engineering.

[19]  Lee M. Hively,et al.  Epileptic Event Forewarning From Scalp EEG , 2001, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[20]  James R. Williamson,et al.  Seizure prediction using EEG spatiotemporal correlation structure , 2012, Epilepsy & Behavior.

[21]  A. Burkitt,et al.  Patient-specific bivariate-synchrony-based seizure prediction for short prediction horizons , 2010, Epilepsy Research.

[22]  P. Pardalos,et al.  Performance of a seizure warning algorithm based on the dynamics of intracranial EEG , 2005, Epilepsy Research.

[23]  Mary Jane England,et al.  Summary: a reprint from epilepsy across the spectrum: promoting health and understanding. , 2012, Epilepsy currents.

[24]  Theoden Netoff,et al.  Seizure prediction using cost-sensitive support vector machine , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[25]  Heng Guo,et al.  Temporal lobe seizure prediction based on a complex Gaussian wavelet , 2011, Clinical Neurophysiology.

[26]  J. Martinerie,et al.  Anticipating epileptic seizures in real time by a non-linear analysis of similarity between EEG recordings. , 1999, Neuroreport.

[27]  F. Mormann,et al.  Seizure prediction: Any better than chance? , 2009, Clinical Neurophysiology.

[28]  Roger Cerf,et al.  Spectral analysis of stereo-electroencephalograms: preictal slowing in partial epilepsies , 2000, Biological Cybernetics.

[29]  Brian Litt,et al.  The statistics of a practical seizure warning system , 2008, Journal of neural engineering.

[30]  Takeshi Yamakawa,et al.  Cooling of the epileptic focus suppresses seizures with minimal influence on neurologic functions , 2012, Epilepsia.

[31]  F. Mormann,et al.  Mean phase coherence as a measure for phase synchronization and its application to the EEG of epilepsy patients , 2000 .

[32]  M. Smyth,et al.  Focal cooling for epilepsy: An alternative therapy that might actually work , 2005, Epilepsy & Behavior.

[33]  Yang Zheng,et al.  Epileptic seizure prediction using phase synchronization based on bivariate empirical mode decomposition , 2014, Clinical Neurophysiology.

[34]  Yann LeCun,et al.  Classification of patterns of EEG synchronization for seizure prediction , 2009, Clinical Neurophysiology.

[35]  J. Martinerie,et al.  Preictal state identification by synchronization changes in long-term intracranial EEG recordings , 2005, Clinical Neurophysiology.

[36]  B. Scholkopf,et al.  Fisher discriminant analysis with kernels , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[37]  C. Elger,et al.  CAN EPILEPTIC SEIZURES BE PREDICTED? EVIDENCE FROM NONLINEAR TIME SERIES ANALYSIS OF BRAIN ELECTRICAL ACTIVITY , 1998 .

[38]  Sheau-Ling Hsieh,et al.  High-Performance Seizure Detection System Using a Wavelet-Approximate Entropy-fSVM Cascade With Clinical Validation , 2013, Clinical EEG and neuroscience.

[39]  F. Mormann,et al.  Seizure prediction: the long and winding road. , 2007, Brain : a journal of neurology.

[40]  Luigi Chisci,et al.  Real-Time Epileptic Seizure Prediction Using AR Models and Support Vector Machines , 2010, IEEE Transactions on Biomedical Engineering.

[41]  Michel Le Van Quyen,et al.  Spatio-temporal dynamics prior to neocortical seizures: amplitude versus phase couplings , 2003, IEEE Transactions on Biomedical Engineering.