Seizure detection of newborn EEG using a model-based approach

Seizures are often the first sign of neurological disease or dysfunction in the newborn. However, their clinical manifestation is often subtle, which tends to hinder their diagnosis at the earliest possible time. This represents an undesirable situation since the failure to quickly and accurately diagnose seizure can lead to longer-term brain injury or even death. Here, the authors consider the problem of automatic seizure detection in the neonate based on electroencephalogram (EEG) data. They propose a new approach based on a model for the generation of the EEG, which is derived from the histology and biophysics of a localized portion of the brain. They show that by using this approach, good detection performance of electrographic seizure is possible. The model for seizure is first presented along with an estimator for the model parameters. Then the authors present a seizure-detection scheme based on the model parameter estimates. This scheme is compared with the quadratic detection filter (QDF), and is shown to give superior performance over the latter. This is due to the ability of the model-based detector to account for the variability (nonstationarity) of the EEG by adjusting its parameters appropriately.

[1]  Athanasios Papoulis,et al.  Probability, Random Variables and Stochastic Processes , 1965 .

[2]  Robert H. Shumway,et al.  On Detecting a Signal in N Stationarily Correlated Noise Series , 1971 .

[3]  A.S. Gevins,et al.  Automated analysis of the electrical activity of the human brain (EEG): A progress report , 1975, Proceedings of the IEEE.

[4]  R. Brent.  Table errata: Algorithms for minimization without derivatives (Prentice-Hall, Englewood Cliffs, N. J., 1973) , 1975 .

[5]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[6]  W Gersch,et al.  Automatic classification of electroencephalograms: Kullback-Leibler nearest neighbor rules. , 1979, Science.

[7]  J. Volpe.  Neurology of the Newborn , 1959, Major problems in clinical pediatrics.

[8]  Paul L. Nunez,et al.  A Study of Origins of the Time Dependencies of Scalp EEG: I - Theoretical Basis , 1981, IEEE Transactions on Biomedical Engineering.

[9]  R. H. Shumway,et al.  1 Discriminant analysis for time series , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[10]  A. Yaglom,et al.  Spectrum Parameter Estimation in Time Series Analysis† †Part of this work was supported by the Netherlands Organization for the Advancement of Pure Research (Z.W.O.) under Grant B62-165. , 1983 .

[11]  William H. Press,et al.  Numerical recipes in C. The art of scientific computing , 1987 .

[12]  William H. Press,et al.  Book-Review - Numerical Recipes in Pascal - the Art of Scientific Computing , 1989 .

[13]  Alan V. Oppenheim,et al.  Discrete-Time Signal Pro-cessing , 1989 .

[14]  R R Clancy,et al.  Interictal Sharp EEG Transients in Neonatal Seizures , 1989, Journal of Child Neurology.

[15]  Reginald G. Bickford,et al.  Atlas of Neonatal Electroencephalography , 1992 .

[16]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[17]  James J. Wright,et al.  The electroencephalogram and cortical neural networks , 1992 .

[18]  A. Liu,et al.  Detection of neonatal seizures through computerized EEG analysis. , 1992, Electroencephalography and clinical neurophysiology.

[19]  Boualem Boashash,et al.  Seizure analysis of newborn EEG using a model based approach , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[20]  Boualem Boashash,et al.  Modeling of newborn EEG data for seizure detection , 1995, Optics & Photonics.