Unsupervised Machine Learning in Classification of Neurobiological Data

  • Konrad A. Ciecierski
  • Tomasz Mandat
Part of the Studies in Big Data book series (SBD, volume 40)


In many cases of neurophysiological data analysis, the best results can be obtained using supervised machine learning approaches. Such very good results were obtained in detection of neurophysiological recordings recorded within Subthalamic Nucleus (\({ STN}\)) during deep brain stimulation (DBS) surgery for Parkinson disease. Supervised machine learning methods relay however on external knowledge provided by an expert. This becomes increasingly difficult if the subject’s domain is highly specialized as is the case in neurosurgery. The proper computation of features that are to be used for classification without good domain knowledge can be difficult and their proper construction heavily influences quality of the final classification. In such case one might wonder whether, how much and to what extent the unsupervised methods might become useful. Good result of unsupervised approach would indicate presence of a natural grouping within recordings and would also be a further confirmation that features selected for classification and clustering provide good basis for discrimination of recordings recorded within Subthalamic Nucleus (\({ STN}\)). For this test, the set of over 12 thousand of brain neurophysiological recordings with precalculated attributes were used. This paper shows comparison of results obtained from supervised - random forest based - method with those obtained from unsupervised approaches, namely K-Means and Hierarchical clustering approaches. It is also shown, how inclusion of certain types of attributes influences the clustering based results.


STN DBS DWT (Discrete Wavelet Transform) decomposition Signal power Unsupervised learning K-means clustering Hierarchical clustering 


  1. 1.
    Israel, Z., Burchiel, K.J.: Microelectrode Recording in Movement Disorder Surgery. Thieme Medical Publishers, New York (2004)CrossRefGoogle Scholar
  2. 2.
    Nieuwenhuys, R., Huijzen, C., Voogd, J.: The Human Central Nervous System. Springer, Berlin (2008)CrossRefGoogle Scholar
  3. 3.
    Nolte, J.: The Human Brain: An Introduction to Its Functional Anatomy. Mosby (2002)Google Scholar
  4. 4.
    Ciecierski, K., Raś, Z.W., Przybyszewski, A.W.: Foundations of recommender system for STN localization during DBS surgery in Parkinson’s patients. Foundations of Intelligent Systems, ISMIS 2012 Symposium, LNAI, vol. 7661, pp. 234–243. Springer (2012)Google Scholar
  5. 5.
    Ciecierski, K., Raś, Z.W., Przybyszewski, A.W.: Discrimination of the micro electrode recordings for STN localization during DBS surgery in Parkinson’s patients. Flexible Query Answering Systems, FQAS 2013 Symposium, LNAI, vol. 8132, pp. 328–339. Springer (2013)CrossRefGoogle Scholar
  6. 6.
    Ciecierski, K., Raś, Z.W., Przybyszewski, A.W.: Foundations of automatic system for intrasurgical localization of subthalamic nucleus in Parkinson patients. Web Intelligence and Agent Systems, 2014/1, pp. , 63–82. IOS Press (2014)Google Scholar
  7. 7.
    Ciecierski, K.: Decision Support System for surgical treatment of Parkinsons disease, Ph.D. thesis, Warsaw University of technology Press (2013)Google Scholar
  8. 8.
    Ciecierski, K., Mandat, T., Rola, R., Raś, Z.W., Przybyszewski, A.W.: Computer aided subthalamic nucleus (STN) localization during deep brain stimulation (DBS) surgery in Parkinson’s patients. Annales Academiae Medicae Silesiensis, vol. 68, 5, pp. 275–283 (2014)Google Scholar
  9. 9.
    Mandat, T., Tykocki, T., Koziara, H., et al.: Subthalamic deep brain stimulation for the treatment of Parkinson disease. Neurologia i neurochirurgia polska 45(1), 32–36 (2011)CrossRefGoogle Scholar
  10. 10.
    Novak, P., Przybyszewski, A.W., Barborica, A., Ravin, P., Margolin, L., Pilitsis, J.G.: Localization of the subthalamic nucleus in Parkinson disease using multiunit activity. J. Neurol. Sci. 310(1), 44–49 (2011)CrossRefGoogle Scholar
  11. 11.
    Jensen, A.: A Ia Cour-Harbo. Ripples in Mathematics. Springer, Berlin (2001)CrossRefGoogle Scholar
  12. 12.
    Smith, S.W.: Digital Signal Processing. Elsevier (2003)CrossRefGoogle Scholar
  13. 13.
    Cha, S.-H.: Comprehensive survey on distance/similarity measures between probability density functions. City 1(2), 1 (2007)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Institute of Computer ScienceWarsaw University of TechnologyWarsawPoland
  2. 2.Department of NeurosurgeryM. Sklodowska-Curie Memorial Oncology CenterWarsawPoland
  3. 3.Department of NeurosurgeryInstitute of Psychiatry and NeurologyWarsawPoland

Personalised recommendations