Advertisement

Probabilistic Forecasts of Epileptic Seizures and Evaluation by the Brier Score

  • M. Jachan
  • H. Feldwisch genannt Drentrup
  • F. Posdziech
  • A. Brandt
  • D. -M. Altenmüller
  • A. Schulze-Bonhage
  • J. Timmer
  • B. Schelter
Part of the IFMBE Proceedings book series (IFMBE, volume 22)

Abstract

We present a probabilistic epileptic seizure predictor and an according method for its statistical evaluation. The probabilistic predictor is based on a combination of feature channels, which are derived from the intracranial electroencephalogram (EEG), by a logistic regression map. The evaluation is done by the Brier score, an established assessment method in meteorology, which quantifies the prediction error. From the prediction features, the weights of the logistic regression are learned in a training phase and in a test phase the Brier score is assessed. A test for significance of the probabilistic predictor, based on seizure time surrogates, is computed. For 3 of 5 patients we obtained significant predictive power with the mean phase coherence and with the dynamical similarity index we obtained for 2 of the 5 patients significant results. The concept of probabilistic prediction can be a valuable tool for the development of future seizure intervention systems.

Keywords

Epileptic Seizure Prediction Brier-Score Mean Phase Coherence Dynamical Similarity Index 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mormann F, Andrzejak R G, Elger C E, and Lehnertz K (2007) Seizure prediction: the long and winding road. Brain 130:314–333CrossRefGoogle Scholar
  2. 2.
    Brier G W (1950) Verification of forecasts expressed in terms of probability. Monthly Weather Review 78:1–3CrossRefGoogle Scholar
  3. 3.
    Mormann F, Kreuz T, Andrzejak R G, David P, Lehnertz K, and Elger C E (2001) Epileptic seizures are preceded by a decrease in synchronization. Epilepsy. Res 53:173–185CrossRefGoogle Scholar
  4. 4.
    Le Van Quyen M, Martinerie J, Baulac M, and Varela F (1999) Anticipating epileptic seizures in real time by a non-linear analysis of similarity between EEG recordings. Neuroreport 10:2149–2155CrossRefGoogle Scholar
  5. 5.
    Rosenblum A S, Pikovsky A S, and Kurths L (1996) Phase synchronization of chaotic oscillators. Phys. Rev. Lett 76:1804–1807CrossRefGoogle Scholar
  6. 6.
    Winterhalder M, Maiwald T, Voss H U, Aschenbrenner-Scheibe R, Timmer J, and Schulze-Bonhage A (2003) The seizure prediction characteristic: A general framework to assess and compare seizure prediction methods. Epilepsy Behav. 4:318–325CrossRefGoogle Scholar
  7. 7.
    Maiwald T, Winterhalder M, Aschenbrenner-Scheibe R, Voss H U, Schulze-Bonhage A, Timmer J (2004) Comparison of three nonlinear seizure prediction methods by means of the seizure prediction characteristic. Physica D 194:357–368MATHCrossRefGoogle Scholar
  8. 8.
    Schelter B, Winterhalder M, Maiwald T, Brandt A, Schad A, Schulze-Bonhage A, and Timmer J (2006) Testing statistical significance of multivariate time series analysis techniques for epileptic seizure prediction. Chaos 16:013108CrossRefGoogle Scholar
  9. 9.
    Andrzejak R G, Mormann F, Kreuz T, Rieke C, Elger C E, and Lehnertz K (2003) Testing the null hypothesis of the nonexistence of a preseizure state. Phys. Rev. E 67:010901(R)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • M. Jachan
    • 1
    • 2
    • 3
  • H. Feldwisch genannt Drentrup
    • 1
    • 3
    • 4
  • F. Posdziech
    • 2
  • A. Brandt
    • 1
  • D. -M. Altenmüller
    • 1
  • A. Schulze-Bonhage
    • 1
    • 3
  • J. Timmer
    • 2
    • 3
    • 5
  • B. Schelter
    • 2
    • 3
  1. 1.Epilepsy CentreUniversity of FreiburgGermany
  2. 2.FDM, Center for Data Analysis and ModelingUniversity of FreiburgGermany
  3. 3.BCCN, Bernstein Center for Computational NeuroscienceUniversity of FreiburgGermany
  4. 4.Department of Neurobiology and BiophysicsUniversity of FreiburgGermany
  5. 5.FRIAS, Freiburg Institute of Advanced StudiesGermany

Personalised recommendations