P. J. Cherian, W. Deburchgraeve, V. Matic, M. De Vos, R. M. Swarte, J. H. Blok, P. Govaert, S. Van Huffel, G. H. Visser


We present the improvements made to and subsequent validation of an automated approach to detect neonatal seizures. The evaluation of the algorithm has been performed on a new and extensive data set of neonatal EEGs. Previously, we have classified neonatal seizures visually into two types: the spike train and oscillatory type of seizures and developed two separate algorithms that run in parallel for their automated detection. The first algorithm analyzes the correlation between high-energetic segments of the EEG, whereas the second one detects increases in low-frequency activity (<8 Hz) and then uses an autocorrelation. An improved version of our automated system (called ‘NeoGuard’) uses more informative features for classification and optimized parameters for thresholding. The validation was performed on 756 hours of ‘unseen’ continuous EEG monitoring data from 24 neonates with encephalopathy and recorded seizures. The seizure detection system showed a median sensitivity of 86.9 % per patient, positive predictive value (PPV) of 89.5 % and false positive rate of 0.28 per hour. The modified algorithm has a high sensitivity combined with a good PPV whereas false positive rate is much lower compared to the previous version of the algorithm.


  1. Aarabi A., Wallois F. and Grebe R., Automated neonatal seizure detection: a multistage classification system through feature selection based on relevance and redundancy analysis, Clin Neurophysiol 117(2006), pp. 328-440.
  2. Celka P. and Colditz P., A computer-aided detection of EEG seizures in infants: a singular spectrum approach and performance comparison, IEEE Trans Biomed Eng 49 (2002), pp. 455-462.
  3. Cherian P. J., Swarte R. M., Visser G. H. Technical standards for recording and interpretation of neonatal electroencephalogram in clinical practice. Ann Indian Acad Neurol 2009; 12: 58-70.
  4. Connell J., Oozeer R., de Vries L., Dubowitz L. M. and Dubowitz V., Continuous EEG monitoring of neonatal seizures: diagnostic and prognostic considerations, Arch Dis Child 64 (1989), pp. 452- 458.
  5. Deburchgraeve W., Cherian P. J., De Vos M., Swarte R. M., Blok J. H., Visser G. H., Govaert P. and Van Huffel S., Automated neonatal seizure detection mimicking a human observer reading EEG, Clin. Neurophysiol. 119 (11) (2008), pp. 2447-2454.
  6. Gotman J., Flanagan D., Zhang J. and Rosenblatt B., Automatic seizure detection in the newborn: methods and initial evaluation, Electroencephalogr Clin Neurophysiol 103 (1997), pp. 356-362.
  7. Greene B. R., Boylan G. B., Reilly R. B., de Chazal P. and Connolly S., Combination of EEG and ECG for improved automatic neonatal seizure detection, Clin Neurophysiol 118 (2007), pp. 1348-1359.
  8. Holmes G. L., Gairsa J. L., Chevassus-Au-Louis N. and Ben-Ari Y., Consequences of neonatal seizures in the rat: morphological and behavioral effects, Ann Neurol 44 (1998), pp. 845-857.
  9. Xiaoyan L., Ping Z. and Aruin S. A., Teager-Kaiser energy operation of surface EMG improves muscle activity onset detection, Ann Biomed Eng 35 (2007), pp. 1532-1538.
  10. Liu A., Hahn J.S., Heldt G. P. and Coen R. W., Detection of neonatal seizures through computerized EEG analysis, Electroencephalogr Clin Neurophysiol 82 (1992), pp. 363-369.
  11. Lombroso C. T., Neonatal seizures: a clinician's overview, Brain Dev 18 (1996), pp. 1-28.
  12. Malone, A. and Ryan, C. A. and Fitzgerald, A. and Burgoyne, L. and Connolly, S. and Boylan, G.BInterobserver agreement in neonatal seizure identification. Epilepsia, volume 50, 2009, 2097-2101 Miller S. P., Weiss J., Barnwell A., Ferriero D. M., LatalHajnal B. and Ferrer-Rogers A., Seizure-associated brain injury in term newborns with perinatal asphyxia, Neurology 58 (2002), pp. 542-548.
  13. Mitra J, Glover J. R., Ktonas P. Y., Thitai Kumar A, Mukherjee A, Karayiannis N. B., et al. A multistage system for the automated detection of epileptic seizures in neonatal electroencephalography. J Clin Neurophysiol 2009; 26: 218-26.
  14. Shewmon D. A., What is a neonatal seizure? Problems in definition and quantification for investigative and clinical purposes. J Clin Neurophysiol 1990; 7: 315- 68.
  15. Volpe J., Neurology of the newborn (4th ed.), WB Saunders, Philadelphia (2001).
  16. Zarjam P., Mesbah M. and Boashash B., An optimal feature set for seizure detection systems for newborn EEG signal, Proc Int Symp Circuits Syst ISCAS 5 (2003), pp. 33-36.

Paper Citation

in Harvard Style

J. Cherian P., Deburchgraeve W., Matic V., De Vos M., M. Swarte R., H. Blok J., Govaert P., Van Huffel S. and H. Visser G. (2011). IMPROVEMENT AND VALIDATION OF AN AUTOMATED NEONATAL SEIZURE DETECTOR . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2011) ISBN 978-989-8425-35-5, pages 31-37. DOI: 10.5220/0003127700310037

in Bibtex Style

author={P. J. Cherian and W. Deburchgraeve and V. Matic and M. De Vos and R. M. Swarte and J. H. Blok and P. Govaert and S. Van Huffel and G. H. Visser},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2011)},

in EndNote Style

JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2011)
SN - 978-989-8425-35-5
AU - J. Cherian P.
AU - Deburchgraeve W.
AU - Matic V.
AU - De Vos M.
AU - M. Swarte R.
AU - H. Blok J.
AU - Govaert P.
AU - Van Huffel S.
AU - H. Visser G.
PY - 2011
SP - 31
EP - 37
DO - 10.5220/0003127700310037