Online Prediction of Onsets of Seizure-like Events in Hippocampal Neural Networks Using Wavelet Artificial Neural Networks

It has been previously shown that wavelet artificial neural networks (WANNs) are able to classify the different states of epileptiform activity and predict the onsets of seizure-like events (SLEs) by offline processing (Ann. Biomed. Eng. 33(6):798–810, 2005) of the electrical data from the in-vitro hippocampal slice model of recurrent spontaneous SLEs. The WANN design entailed the assumption that time-varying frequency information from the biological recordings can be used to estimate the times at which onsets of SLEs would most likely occur in the future. Progressions of different frequency components were captured by the artificial neural network (ANN) using selective frequency inputs from the initial wavelet transform of the biological data. The training of the WANN had been established using 184 SLE episodes in 34 slices from 21 rats offline. Nine of these rats also exhibited periods of interictal bursts (IBs). These IBs were included as part of the training to help distinguish the difference in dynamics of bursting activities between the preictal- and interictal type. In this paper, we present the results of an online processing using WANN on 23 in-vitro rat hippocampal slices from 9 rats having 93 spontaneous SLE episodes generated under low magnesium conditions. Over the test cases, three of the nine rats exhibited over 30 min of IB activities. We demonstrated that the WANN was able to classify the different states, namely, interictal, preictal, ictal, and IB activities with an accuracy of 86.6, 72.6, 84.5, and 69.1%, respectively. Prediction of state transitions into ictal events was achieved using regression of initial “normalized time-to-onset” estimates. The SLE onsets can be estimated up to 36.4 s ahead of their actual occurrences, with a mean error of 14.3 ± 27.0 s. The prediction errors decreased progressively as the actual time-to-onset decreased and more initial “normalized time-to-onset” estimates were used for the regression procedure.

[1]  I. Osorio,et al.  Real‐Time Automated Detection and Quantitative Analysis of Seizures and Short‐Term Prediction of Clinical Onset , 1998, Epilepsia.

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

[3]  Houman Khosravani,et al.  The control of seizure-like activity in the rat hippocampal slice. , 2003, Biophysical journal.

[4]  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.

[5]  Leonidas D. Iasemidis,et al.  Chaos Theory and Epilepsy , 1996 .

[6]  B. Litt,et al.  High-frequency oscillations and seizure generation in neocortical epilepsy. , 2004, Brain : a journal of neurology.

[7]  W. Art Chaovalitwongse,et al.  Adaptive epileptic seizure prediction system , 2003, IEEE Transactions on Biomedical Engineering.

[8]  Leonidas D. Iasemidis,et al.  ■ REVIEW : Chaos Theory and Epilepsy , 1996 .

[9]  Berj L. Bardakjian,et al.  Prediction of Seizure Onset in an In-Vitro Hippocampal Slice Model of Epilepsy Using Gaussian-Based and Wavelet-Based Artificial Neural Networks , 2005, Annals of Biomedical Engineering.

[10]  D. Coulter,et al.  Long-duration self-sustained epileptiform activity in the hippocampal-parahippocampal slice: a model of status epilepticus. , 1995, Journal of neurophysiology.

[11]  Randy K. Young.  Wavelet theory and its applications , 1993, The Kluwer international series in engineering and computer science.

[12]  Jerome Engel,et al.  Outcome with respect to epileptic seizures. , 1993 .

[13]  Stiliyan Kalitzin,et al.  Enhancement of phase clustering in the EEG/MEG gamma frequency band anticipates transitions to paroxysmal epileptiform activity in epileptic patients with known visual sensitivity , 2002, IEEE Transactions on Biomedical Engineering.

[14]  S. Mallat.  VI – Wavelet zoom , 1999 .

[15]  Bruce J. Gluckman,et al.  Adaptive Electric Field Control of Epileptic Seizures , 2001, The Journal of Neuroscience.

[16]  Bálint Lasztóczi,et al.  High‐frequency synaptic input contributes to seizure initiation in the low‐[Mg2+] model of epilepsy , 2004, The European journal of neuroscience.

[17]  T. Valiante,et al.  Neural Codes in Human Extracranial EEG: Identification of Epilepsy Features , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[18]  L H Finkel,et al.  Neuroengineering models of brain disease. , 2000, Annual review of biomedical engineering.

[19]  Marc W. Slutzky,et al.  Manipulating epileptiform bursting in the rat hippocampus using chaos control and adaptive techniques , 2003, IEEE Transactions on Biomedical Engineering.

[20]  Klaus Lehnertz,et al.  Testing the null hypothesis of the nonexistence of a preseizure state. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[21]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[22]  Charles L. Wilson,et al.  High‐frequency oscillations in human brain , 1999, Hippocampus.

[23]  J. P. Dreier,et al.  Regional and time dependent variations of low Mg2+ induced epileptiform activity in rat temporal cortex slices , 2004, Experimental Brain Research.

[24]  Kevin J. Staley,et al.  Mechanisms of Fast Ripples in the Hippocampus , 2004, The Journal of Neuroscience.

[25]  A. Babloyantz,et al.  Low-dimensional chaos in an instance of epilepsy. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[26]  A. Wolf,et al.  Determining Lyapunov exponents from a time series , 1985 .

[27]  K. Staley,et al.  Transition from Interictal to Ictal Activity in Limbic Networks In Vitro , 2003, The Journal of Neuroscience.

[28]  D. Durand,et al.  Suppression and control of epileptiform activity by electrical stimulation: a review , 2001, Proc. IEEE.

[29]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[30]  J. Milton,et al.  Brain Defibrillators: Synopsis, Problems and Future Directions , 2003 .

[31]  Klaus Lehnertz,et al.  Reduced signal complexity of intracellular recordings: a precursor for epileptiform activity? , 1999, Brain Research.

[32]  E. Basar.  Brain Function and Oscillations , 1998 .

[33]  Houman Khosravani,et al.  The effects of high-frequency oscillations in hippocampal electrical activities on the classification of epileptiform events using artificial neural networks , 2006, Journal of neural engineering.

[34]  W. Ditto,et al.  Controlling chaos in the brain , 1994, Nature.

[35]  Mingui Sun,et al.  Extraction and Analysis of Early Ictal Activity in Subdural Electroencephalogram , 2001, Annals of Biomedical Engineering.

[36]  Berj L. Bardakjian,et al.  Control of state transitions in an in silico model of epilepsy using small perturbations , 2004, IEEE Transactions on Biomedical Engineering.

[37]  Louis M. Pecora,et al.  Comparison of Methods for Seizure Detection , 2003 .

[38]  J. C. Sackellares,et al.  Measurement and Quantification of Spatio-Temporal Dynamics of Human Epileptic Seizures , 1999 .

[39]  K Lehnertz,et al.  Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: dependence on recording region and brain state. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[40]  D. Coulter,et al.  Generation and propagation of epileptiform discharges in a combined entorhinal cortex/hippocampal slice. , 1993, Journal of neurophysiology.

[41]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[42]  Péter Érdi,et al.  Hippocampal rhythm generation: gamma related theta frequency , 2000 .

[43]  Leon D. Iasemidis,et al.  Epileptic seizure prediction and control , 2003, IEEE Transactions on Biomedical Engineering.

[44]  S J Schiff,et al.  Periodic orbits: a new language for neuronal dynamics. , 1998, Biophysical journal.

[45]  G. Vachtsevanos,et al.  Epileptic Seizures May Begin Hours in Advance of Clinical Onset A Report of Five Patients , 2001, Neuron.

[46]  Metin Akay,et al.  Measurement and Quantification of Spatiotemporal Dynamics of Human Epileptic Seizures , 2000 .

[47]  R. Wennberg,et al.  Type III intermittency in human partial epilepsy , 1999, The European journal of neuroscience.

[48]  R. Traub,et al.  Electrical coupling underlies high-frequency oscillations in the hippocampus in vitro , 1998, Nature.

[49]  S. Haykin,et al.  Monitoring neuronal oscillations and signal transmission between cortical regions using time-frequency analysis of electroencephalographic activity , 1996, Proc. IEEE.