Clinical Neurophysiology
Volume 120, Issue 11 , Pages 1927-1940 , November 2009

Classification of patterns of EEG synchronization for seizure prediction

  • Piotr Mirowski

      Affiliations

    • Courant Institute of Mathematical Sciences, New York University, 719 Broadway, New York, NY 10003, USA
    • Corresponding Author InformationCorresponding Author. Address: Courant Institute of Mathematical Sciences, New York University, 719 Broadway, 12th Floor, New York, NY 10003, USA. Tel.: +1 203 278 1803; fax: +1 212 263 8342.
    • ,
  • Deepak Madhavan

      Affiliations

    • Department of Neurological Sciences, 982045 University of Nebraska Medical Center, Omaha, NE 68198, USA
    • ,
  • Yann LeCun

      Affiliations

    • Courant Institute of Mathematical Sciences, New York University, 719 Broadway, New York, NY 10003, USA
    • ,
  • Ruben Kuzniecky

      Affiliations

    • New York University Comprehensive Epilepsy Center, 223 East 34th St., New York, NY 10016, USA

,Accepted 2 September 2009.

References 

  1. Andrzejak RG, Mormann F, Kreuz T, Rieke C, Kraskov A, Elger CE, et al. Testing the null hypothesis of the non-existence of the pre-seizure state. Phys Rev E. 2003;67
  2. Arnhold J, Grassberger P, Lehnertz K, Elger CE. A robust method for detecting interdependence. applications to intracranially recorded EEG. Physica D. 1999;134:419–430
  3. Aschenbrenner-Scheibe R, Maiwald T, Winterhalder M, Voss HU, Timmer J. How well can epileptic seizures be predicted? An evaluation of a nonlinear method. Brain. 2003;126:2616–2626
  4. Bottou L, LeCun Y. Lush: Lisp universal shell programming language; 2002. Available from: http://lush.sourceforge.net/index.html.
  5. Chang CC, Lin CJ. LIBSVM: a library for support vector machines; 2001. Available from: http://www.csie.nyu.edu.tw/cjlin/libsvm.
  6. Cortes C, Vapnik V. Support-vector networks. Mach Learn. 1995;20(3):273–297
  7. D’Alessandro M, Esteller R, Vachtsevanos G, Hinson A, Echauz J, Litt B. Epileptic seizure prediction using hybrid feature selection over multiple EEG electrode contacts: a report of four patients. IEEE Trans Biomed Eng. 2003;50(5):603–615
  8. D’Alessandro M, Vachtsevanos G, Esteller R, Echauz J, Cranstoun S, Worrell G, et al. A multi-feature and multi-channel univariate selection process for seizure prediction. Clin Neurophy. 2005;116:505–516
  9. Delorme A, Makeig S. EEGLab: an open-source toolbox for analysis of single-trial EEG dynamics including ICA. J Neurosci Method. 2004;134(1):9–21
  10. Esteller R, Echauz J, D’Alessandro M, Worell G, Cranstoun S, Vachtsevanos G, et al. Continuous energy variation during the seizure cycle: towards an online accumulated energy. Clin Neurophy. 2005;116:517–526
  11. Harrison MA, Frei MG, Osorio I. Accumulated energy revisited. Clin Neurophy. 2005;116:527–531
  12. Iasemidis LD, Principe JC, Sackellares JC. Measurement and quantification of spatio-temporal dynamics of human epileptic seizures. In:  Akay M editors. Nonlinear signal processing in medicine. IEEE Press; 1999;
  13. Iasemidis LD, Shiau DS, Pardalos PM, Chaovalitwongse W, Narayanana K, Prasada A, et al. Long-term prospective online real-time seizure prediction. Clin Neurophy. 2005;116:532–544
  14. Jerger KK, Weinstein SL, Sauer T, Schiff SJ. Multivariate linear discrimination of seizures. Clin Neurophy. 2005;116:545–551
  15. Jouny C, Franaszczuk P, Bergey G. Signal complexity and synchrony of epileptic seizures: is there an identifiable preictal period. Clin Neurophy. 2005;116:552–558
  16. Le Van Quyen M, Foucher J, Lachaux J-P, Rodriguez E, Lutz A, Martinerie J, et al. Comparison of Hilbert transform and wavelet methods for the analysis of neuronal synchrony. J Neurosci Method. 2001;11:83–98
  17. Le Van Quyen M, Navarro V, Martinerie J, Baulac M, Varela FJ. Toward a neurodynamical understanding of ictogenesis. Epilepsia. 2003;44(12):30–43
  18. Le Van Quyen M, Soss J, Navarro V, Robertson R, Chavez M, Baulac M, et al. Preictal state identification by synchronization changes in long-term intracranial recordings. Clin Neurophy. 2005;116:559–568
  19. LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE. 1998;86(11):2278–2324
  20. LeCun Y, Bottou L, Orr GB, Muller KR. Efficient backprop. In:  Orr GB,  Müller K-R editor. Neural networks: tricks of the trade. Springer; 1998;
  21. LeCun Y, Muller U, Ben J, Cosatto E, Flepp B. Off-road obstacle avoidance through end-to-end learning. In: Advances in neural information processing systems NIPS’97. Cambridge, MA: Morgan Kaufmann, MIT Press; 2005;
  22. Lehnertz K, Litt B. The first international collaborative workshop on seizure prediction: summary and data description. Clin Neurophy. 2005;116(3):493–505
  23. Lehnertz K, Mormann F, Osterhage H, Muller A, Prusseit J, Chernihovskyi A. State-of-the-art seizure prediction. J Clin Neurophy. 2007;24:(2)
  24. Litt B, Echauz J. Prediction of epileptic seizures. Lancet Neurol. 2002;1(1):22–30
  25. Maiwald T, Winterhalder M, Aschenbrenner-Scheibe R, Voss HU, Schulze-Bonhage A. Comparison of three nonlinear seizure prediction methods by means of the seizure prediction characteristic. Physica D. 2004;194:357–368
  26. Mirowski P, Madhavan D, LeCun Y. Time-delay neural networks and independent component analysis for EEG-based prediction of epileptic seizures propagation. In: Proceedings of the twenty-second AAAI conference on artificial intelligence, July 22–26, 2007, Vancouver, BC, Canada. AAAI Press; 2007. p. 1982–3.
  27. Mormann F, Kreuz T, Rieke C, Andrzejak RG, Kraskov A. On the predictability of epileptic seizures. Clin Neurophy. 2005;116:569–587
  28. Mormann F, Elger CE, Lehnertz K. Seizure anticipation: from algorithms to clinical practice. Curr Opin Neurol. 2006;19:187–193
  29. Mormann F, Andrzejak RG, Elger CE, Lehnertz K. Seizure prediction: the long and winding road. Brain. 2007;130:314–333
  30. Petrosian A, Prokhorov D, Homan R, Dasheiff R, Wunsh D. Recurrent neural network based prediction of epileptic seizures in intra- and extracranial EEG. Neurocomputing. 2000;30:201–218
  31. Rajna P, Clemens B, Csibri E. Hungarian multicentre epidemiologic study of the warning and initial symptoms (prodrome, aura) of epileptic seizures. Seizure. 1997;6:361–368
  32. Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error backpropagation. Cambridge, MA: MIT Press; 1986;
  33. Schelter B, Winterhalder M, Maiwald T, Brandt A, Schad A. Do false predictions of seizures depend on the state of vigilance? A report from two seizure-prediction methods and proposed remedies. Epilepsia. 2006;47:2058–2070
  34. Schelter B, Winterhalder M, Maiwald T, Brandt A, Schad A. Testing statistical significance of multivariate time series analysis techniques for epileptic seizure prediction. Chaos. 2006;16:013108
  35. Schulze-Bonhage A, Kurth C, Carius A, Steinhoff BJ, Mayer T. Seizure anticipation by patients with focal and generalized epilepsy: a multicentre assessment of premonitory symptoms. Epilepsy Res. 2006;70:83–88
  36. Stam CJ. Nonlinear dynamical analysis of EEG and MEG: Review of an emerging field. Clin Neurophy. 2005;116:2256–2301
  37. Takens F. Detecting strange attractors in turbulence. Lecture Notes Math. 1981;898:366–381
  38. Tibshirani R. Regression shrinkage and selection via the lasso. J Roy Stat Soc B. 1996;58(1):267–288
  39. Vapnik V. The nature of statistical learning theory. New York, NY: Springer Verlag; 1995;
  40. Winterhalder M, Maiwald T, Voss HU, Aschenbrenner-Scheibe R, Timmer J. The seizure prediction characteristic: a general framework to assess and compare seizure prediction methods. Epilepsy Behav. 2003;4(3):318–325

☆ Portions of this manuscript were presented at the 2008 American Epilepsy Society annual meeting and at the 2008 IEEE Workshop on Machine Learning for Signal Processing.

PII: S1388-2457(09)00526-4

doi: 10.1016/j.clinph.2009.09.002

Clinical Neurophysiology
Volume 120, Issue 11 , Pages 1927-1940 , November 2009

Article Tools

* Image Usage & Resolution