A tunable support vector machine assembly classifier for epileptic seizure detection

Automating the detection of epileptic seizures could reduce the significant human resources necessary for the care of patients suffering from intractable epilepsy and offer improved solutions for closed-loop therapeutic devices such as implantable electrical stimulation systems. While numerous detection algorithms have been published, an effective detector in the clinical setting remains elusive. There are significant challenges facing seizure detection algorithms. The epilepsy EEG morphology can vary widely among the patient population. EEG recordings from the same patient can change over time. EEG recordings can be contaminated with artifacts that often resemble epileptic seizure activity. In order for an epileptic seizure detector to be successful, it must be able to adapt to these different challenges. In this study, a novel detector is proposed based on a support vector machine assembly classifier (SVMA). The SVMA consists of a group of SVMs each trained with a different set of weights between the seizure and non-seizure data and the user can selectively control the output of the SVMA classifier. The algorithm can improve the detection performance compared to traditional methods by providing an effective tuning strategy for specific patients. The proposed algorithm also demonstrates a clear advantage over threshold tuning. When compared with the detection performances reported by other studies using the publicly available epilepsy dataset hosted by the University of BONN, the proposed SVMA detector achieved the best total accuracy of 98.72%. These results demonstrate the efficacy of the proposed SVMA detector and its potential in the clinical setting.

[1]  S. Sanei,et al.  Support vector machines for seizure detection , 2003, Proceedings of the 3rd IEEE International Symposium on Signal Processing and Information Technology (IEEE Cat. No.03EX795).

[2]  Scott B. Wilson.  Algorithm architectures for patient dependent seizure detection , 2006, Clinical Neurophysiology.

[3]  Ivan Osorio,et al.  Strategies for adapting automated seizure detection algorithms. , 2007, Medical engineering & physics.

[4]  Ali H. Shoeb,et al.  Patient-specific seizure onset detection , 2004, Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[5]  J. F. Kaiser,et al.  On a simple algorithm to calculate the 'energy' of a signal , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[6]  José María Amigó,et al.  Estimating the Entropy Rate of Spike Trains via Lempel-Ziv Complexity , 2004, Neural Computation.

[7]  Elif Derya íbeyli.  Statistics over features: EEG signals analysis , 2009 .

[8]  Nurettin Acir,et al.  Automatic spike detection in EEG by a two-stage procedure based on support vector machines , 2004, Comput. Biol. Medicine.

[9]  Dominique M Durand,et al.  Effects of Potassium Concentration on Firing Patterns of Low‐Calcium Epileptiform Activity in Anesthetized Rat Hippocampus: Inducing of Persistent Spike Activity , 2006, Epilepsia.

[10]  Nurettin Acir,et al.  Automatic detection of epileptiform events in EEG by a three-stage procedure based on artificial neural networks , 2005, IEEE Transactions on Biomedical Engineering.

[11]  Daniel Friedman,et al.  Continuous Electroencephalogram Monitoring in the Intensive Care Unit , 2009, Anesthesia and analgesia.

[12]  J. Daunizeau,et al.  The combination of EEG Source Imaging and EEG‐correlated functional MRI to map epileptic networks , 2010, Epilepsia.

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

[14]  J. Gotman,et al.  A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: possible use as a warning device , 1997, IEEE Transactions on Biomedical Engineering.

[15]  U. Rajendra Acharya,et al.  Entropies for detection of epilepsy in EEG , 2005, Comput. Methods Programs Biomed..

[16]  Elif Derya Ubeyli,et al.  Statistics over features: EEG signals analysis. , 2009, Computers in biology and medicine.

[17]  Lei Wang,et al.  26th Annual International Conference of the IEEE EMBS , 2004 .

[18]  J. Gotman,et al.  A system to detect the onset of epileptic seizures in scalp EEG , 2005, Clinical Neurophysiology.

[19]  H. M. Teager,et al.  Evidence for Nonlinear Sound Production Mechanisms in the Vocal Tract , 1990 .

[20]  I. Guler,et al.  Multiclass Support Vector Machines for EEG-Signals Classification , 2007, IEEE Transactions on Information Technology in Biomedicine.

[21]  Eun-Hyoung Park,et al.  Diffusive coupling and network periodicity: a computational study. , 2008, Biophysical journal.

[22]  Amitava Chatterjee,et al.  Cross-correlation aided support vector machine classifier for classification of EEG signals , 2009, Expert Syst. Appl..

[23]  Jing Hu,et al.  Analysis of Biomedical Signals by the Lempel-Ziv Complexity: the Effect of Finite Data Size , 2006, IEEE Transactions on Biomedical Engineering.

[24]  R. Hopfengärtner,et al.  Epilepsy monitoring for therapy: Challenges and perspectives , 2009, Clinical Neurophysiology.

[25]  Ali H. Shoeb,et al.  Impact of Patient-Specificity on Seizure Onset Detection Performance , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[26]  Dominique M Durand,et al.  Low-calcium epileptiform activity in the hippocampus in vivo. , 2003, Journal of neurophysiology.

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

[28]  Brian Litt,et al.  One-Class Novelty Detection for Seizure Analysis from Intracranial EEG , 2006, J. Mach. Learn. Res..

[29]  B.V. Vahdat,et al.  Epileptic Seizure Detection using AR Model on EEG Signals , 2008, 2008 Cairo International Biomedical Engineering Conference.

[30]  Elif Derya Übeyli,et al.  Recurrent neural networks employing Lyapunov exponents for EEG signals classification , 2005, Expert Syst. Appl..