Combining newborn EEG and HRV information for automatic seizure detection

We propose a new seizure detection framework based on combination of information extracted from newborn multi-channel electroencephalogram (EEG) and heart rate variability (HRV). Two approaches are investigated for the combination of EEG and HRV, namely; feature fusion and classifier/decision fusion. The feature fusion was performed by concatenating the features vectors extracted from the EEG and the HRV signals while the classifier fusion was accomplished by fusing the independent decisions from individual classifiers of EEG and HRV. Both proposed schemes consist of a sequence of processing steps, namely; preprocessing, feature extraction, feature selection and finally the combination. We have shown that both proposed approaches lead to improved performance of newborn seizure detection compared to either EEG or HRV based seizure detectors.

[1]  L. Sörnmo,et al.  Delineation of the QRS complex using the envelope of the e.c.g. , 1983, Medical and Biological Engineering and Computing.

[2]  Peggy Zarjam.  EEG Data acquisition and automatic seizure detection using wavelet transforms in the newborn EEG. , 2003 .

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

[4]  B Boashash,et al.  A time-frequency approach for newborn seizure detection. , 2001, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[5]  Mostefa Mesbah,et al.  Newborn seizure detection based on fusion of multichannel EEG , 2008 .

[6]  J. Gotman,et al.  Automatic seizure detection in the newborn: methods and initial evaluation. , 1997, Electroencephalography and clinical neurophysiology.

[7]  R. Reilly,et al.  Combination of EEG and ECG for improved automatic neonatal seizure detection , 2007, Clinical Neurophysiology.

[8]  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.

[9]  Mostefa Mesbah,et al.  Time-Frequency Analysis of Heart Rate Variability for Neonatal Seizure Detection , 2007, EURASIP J. Adv. Signal Process..

[10]  Hannah C. Glass,et al.  Neonatal seizures , 2009, Current treatment options in neurology.

[11]  Boualem Boashash,et al.  IF estimation for multicomponent signals , 2003 .

[12]  M. Mesbah,et al.  HRV feature selection based on discriminant and redundancy analysis for neonatal seizure detection , 2007, 2007 6th International Conference on Information, Communications & Signal Processing.

[13]  B. Boashash,et al.  HRV Feature Selection for Neonatal Seizure Detection: A Wrapper Approach , 2007, 2007 IEEE International Conference on Signal Processing and Communications.

[14]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  B. Hjorth.  The physical significance of time domain descriptors in EEG analysis. , 1973, Electroencephalography and clinical neurophysiology.