Determinant characteristics in EEG signal based on bursts amplitude segmentation for predicting pathological outcomes of a premature newborn, with validation using ANN

  • Yasser Al Hajjar
  • Abd El Salam Al HajjarEmail author
  • Bassam Daya
  • Pierre Chauvet


EEG signal contains some specific patterns that predict neuro-developmental impairments of a premature newborn. Extracting these patterns from a set of EEG records provides a dataset to be used in machine learning in order to implement an intelligent classification system that predict prognosis of the baby. In a previous work we proved that inter-burst intervals (IBI) found in the EEG records predicts abnormal outcomes of the premature. A bibliographic study on the amplitude of an EEG signal, with the annotations of the neuro-pediatricians, showed that low amplitudes in EEG signal are strongly correlated with an abnormal prognosis of the premature, similar to that of IBI. According to these hypotheses, we present in this paper, a segmentation methodology on the amplitude of bursts intervals of EEG signal into 3 segments: low, medium and high, in addition to the inter-burst intervals. We create a new algorithm that detects 6 important parameters in each interval of these 4 segments. After applying this new methodology, we obtain a new classified dataset that contains 24 parameters extracted from these 4 segments to obtain with gestational age of the preterm and the day of recording 26 input attributes and one output which is the class (normal, sick or risky). Finally we validate the pertinence of these attributes using artificial neural network.


EEG signal Inter-burst interval IBI Signal amplitude Prediction e-learning EEG signal characteristics Inetlligent modes Artificial Neural Network (ANN) 



This work has been done as a part of the project “Prediction of premature neonates’ prognosis based on their electroencephalogram” supported by the Lebanese University.


  1. 1.
    Wikström, S. (2011). Background aEEG/EEG measures in very preterm infants. Uppsala University, Department of Women’s and Children’s Health, Doctoral thesis, Comprehensive summary.Google Scholar
  2. 2.
    Matié, V., Cherian, P., Jansen, K., Koolen, N., Naulaers, G., Swarte, R., et al. (2012). Automated EEG inter-burst interval detection in neonates with mild to moderate postasphyxial encephalopathy. In 34th Annual international conference of the IEEE EMBS, San Diego, California, USA, 28 Aug–1 Sept 2012.Google Scholar
  3. 3.
    Nandish, M., Stafford, M., Hemanth, K., & Faizan, A. (2012). Feature extraction and classification of EEG signal using neural network based techniques. International Journal of Engineering and Innovative Technology (IJEIT), 2(4).Google Scholar
  4. 4.
    Azami, H., Khosravi, A., Malekzadeh, M., & Sanei, S. (2012). A new adaptive signal segmentation approach based on Hiaguchi’s fractal dimension. In D. S. Huang, P. Gupta, X. Zhang, & P. Premaratne (Eds.), Emerging intelligent computing technology and applications. ICIC: Communications in computer and information science (Vol. 304). Berlin: Springer.Google Scholar
  5. 5.
    Koolen, N., Jansen, K., Vervisch, J., Matic, V., De Vos, M., Naulaers, G., et al. (2013). Automatic burst detection based on line length in the premature EEG. In International conference on bio-inspired systems and signal processing, Barcelona.Google Scholar
  6. 6.
    Abdulla, W. (2011). Neonatal EEG signal characteristics using time frequency analysis. Physica A: Statistical Mechanics and its Applications, 390(6), 1096–1110.CrossRefGoogle Scholar
  7. 7.
    Kalaivani, M., Kalaivani, V., & Anusuya Devi, V. (2014). Analysis of EEG signal for the detection of brain abnormalities. International Journal of Computer Applications ® (IJCA). In International conference on simulations in computing nexus, ICSCN.Google Scholar
  8. 8.
    Omidvarnia, A. (2014). Newborn EEG connectivity analysis using time-frequency signal processing techniques. A thesis submitted for the degree of Doctor of Philosophy at The University of Queensland in 2014 School of Medicine.Google Scholar
  9. 9.
    Lofhede, J., Thordstein, M., Lofgren, N., Flisberg, A., Rosa-Zurera, M., & Kjellmer, I. (2010). Automatic classification of background EEG activity in healthy and sick neonates. Journal of Neural Engineering, 7, 16007.CrossRefGoogle Scholar
  10. 10.
    Willacy, H., Gandhi, A., & Bonsall, A. (2014). Premature babies and their problems. Patient web site.
  11. 11.
    Norman, E., Wikström, S., Rosén, I., Fellman, V., & Hellström-Westas, L. (2013). Premedication for intubation with morphine causes prolonged depression of electrocortical background activity in preterm infants. Pediatric Research, 2013(73), 87–94. Scholar
  12. 12.
    Chauvet, P., & Nguyen, S. (2013). EEGDiag, une application d’analyse de l’EEG pour la plateforme de télésanté BBEEG, 4ièmes Journées Démonstrateurs, Angers.Google Scholar
  13. 13.
    Hajjar, Y., Al Hajjar, A., Daya, B., & Chauvet, P. (2015). Future prediction of premature newborn based on inter-burst intervals of EEG signals using artificial neural network. In SAI Intelligent Systems Conference 2015, London: IEEE, Nov 10–11, 2015.Google Scholar
  14. 14.
    Hajjar, Y., Al Hajjar, A., Dayya, B., & Chauvet, P. (2016). Intelligent models to predict the prognosis of premature neonates according to their EEG signals. International Journal of Biomedical and Clinical Engineering (IJBCE), 6, 57–66.CrossRefGoogle Scholar
  15. 15.
    Natalucci, G., Rousson, V., Bucher, H., Bernet, V., Hagmann, C., & Latal, B. (2012). Delayed cyclic activity development on early amplitude-integrated EEG in the preterm infant with brain lesions. Neonatology, 103(2), 134–140.CrossRefGoogle Scholar
  16. 16.
    Xindong, W., Vipin, K., Ross Quinlan, J., Joydeep, G., Qiang, Y., Hiroshi, M., et al. (2008). Top 10 algorithms in data mining. Knowledge and Information Systems, 14(1), 1–37.CrossRefGoogle Scholar
  17. 17.
    Palmu, K., Wikstrom, S., Hippelainen, E., Boylan, G., Hellstrom-Westas, L., & Vanhatalo, S. (2010). Detection of ’EEG bursts’ in the early preterm EEG: visual vs. automated detection. Clinical Neurophysiololgy, 121, 1015–1022.CrossRefGoogle Scholar
  18. 18.
    Brownlee, J. (2013). How to evaluate machine learning algorithms. Machine Learning Process.
  19. 19.
    Letham, B., Rudin, C., McCormick, T., & Madigan, D. (2015). Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model. The Annals of Applied Statistics, 9(3), 1350–1371.MathSciNetCrossRefzbMATHGoogle Scholar
  20. 20.
    Cireşan, D., Meier, U., Masci, J., & Schmidhuber, J. (2012). Multi-column deep neural network for traffic sign classification. Neural Networks: The Official Journal of the International Neural Network Society, 32, 333–338. Scholar
  21. 21.
    Tzallas, A. T., Tsipouras, M. G., & Fotiadis, D. I. (2007). Automatic seizure detection based on time-frequency analysis and artificial neural networks. Computational Intelligence and Neuroscience. Scholar
  22. 22.
    El-Dib, M., Chang, T., Tsuchida, T., & Clancy, R. (2009). Amplitude-integrated electroencephalography in neonates. Pediatric Neurology, 41(5), 315–326.CrossRefGoogle Scholar
  23. 23.
    James, G., Witten, D., Hastie, T., & Tibshirani, R. (2015). An introduction to statistical learning (p. 315). New York: Springer. ISBN 978-1-4614-7137-0.zbMATHGoogle Scholar
  24. 24.
    Wang, H., Shen, Y., Huang, T., & Zeng, Z. (2009). A novel nonparametric regression ensemble for rainfall forecasting using particle swarm optimization technique coupled with artificial neural network. In 6th International symposium on neural networks, ISNN 2009. Springer. ISBN 978-3-642-01215-0.

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Yasser Al Hajjar
    • 1
  • Abd El Salam Al Hajjar
    • 2
    Email author
  • Bassam Daya
    • 2
  • Pierre Chauvet
    • 1
  1. 1.LARIS LaboratoryAngers UniversityAngersFrance
  2. 2.CCNE, University Institute of TechnologyLebanese UniversitySaidaLebanon

Personalised recommendations