Abstract
In Parkinson’s disease (PD) neurodegenerative processes related to nerve cell deaths have different time courses in individual patients, requiring individually adjusted treatments to be performed under the supervision of an experienced neurologists. In this project, we have compared results of treatments performed by a neurologist with predictions of the data mining systems: WEKA and RSES (Rough Sets). We have analyzed a PD patients database of 800 neurological records of 94 patients from three different groups: (1) BMT—best medical treatment—patients only on pharmacological treatment, (2) POP—postoperative patients that have received an implanted DBS electrode before our study, (3) DBS—patients with stimulating electrodes that were implanted during our study. We have divided the data into training and testing sets with help of the machine learning improved classifiers based on a Random Forest (WEKA) or on decomposition trees (RSES). These reached an accuracy of 87 % in LDOPA dosage estimation, 80 % for UPDRS III and over 90 % for UPDS IV estimations. The precision of our individual patients symptoms and medications dosage predictions should be sufficient to give neurologists objective advice on optimal treatment for particular patients.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Bazan, J.G., Szczuka, M.: The rough set exploration system. In: Peters, J.F., Skowron, A. (eds.) Transactions on Rough Sets III. Number 3400 in Lecture Notes in Computer Science, pp. 37–56. Springer, Berlin, Heidelberg (2005)
Das, S., Trutoiu, L., Murai, A., Alcindor, D., Oh, M., De la Torre, F., Hodgins, J.: Quantitative measurement of motor symptoms in Parkinson’s disease: a study with full-body motion capture data. In: Conference Proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, pp. 6789–6792 (2011)
Kubis, A., Szymański, A., Przybyszewski, A.W.: Fuzzy Rough sets theory applied to parameters of eye movements can help to predict effects of different treatments in Parkinson’s patients. In: Kryszkiewicz, M., Bandyopadhyay, S., Rybinski, H., Pal, S.K. (eds.) Pattern Recognition and Machine Intelligence. Number 9124 in Lecture Notes in Computer Science, pp. 325–334. Springer International Publishing (2015). doi:10.1007/978-3-319-19941-2_31
Kupryjanow, A., Kunka, B., Kostek, B.: UPDRS tests for diagnosis of Parkinson’s disease employing virtual-touchpad. In: 2010 Workshop on Database and Expert Systems Applications (DEXA), pp. 132–136 (2010)
Padma, A., Sukanesh, R.: Segmentation and classification of brain CT images using combined wavelet statistical texture features. Arab. J. Sci. Eng. 39(2), 767–776 (2013)
Prinzie, A., Van den Poel, D.: Random forests for multiclass classification: random MultiNomial logit. Expert Syst. Appl. 34(3), 1721–1732 (2008)
Przybyszewski, A.W., Boczarska, M., Kwiek, S., Wojciechowski, K.: Rough set based classifications of Parkinson’s patients gaits. In: Nguyen, N.T., Attachoo, B., Trawiński, B., Somboonviwat, K. (eds.) Intelligent Information and Database Systems. Number 8398 in Lecture Notes in Computer Science, pp. 525–534. Springer International Publishing (2014). doi:10.1007/978-3-319-05458-2_54
Szymański, A., Przybyszewski, A.W.: rough set rules help to optimize parameters of deep brain stimulation in Parkinson’s patients. In: Ślęzak, D., Tan, A.H., Peters, J.F., Schwabe, L. (eds.) Brain Informatics and Health. Number 8609 in Lecture Notes in Computer Science, pp. 345–356. Springer International Publishing (2014)
Szymański, A., Kubis, A., Przybyszewski, A.W.: Data mining and neural network simulations can help to improve deep brain stimulation effects in Parkinson’s disease. Comput. Sci. 16(2), 199 (2015)
Zhang, Y., Wang, S.: Classification of Alzheimer disease based on structural magnetic resonance imaging by kernel support vector machine decision tree. Prog. Electromagnet. Res. 144, 185–191 (2014)
Zhang, Y., Dong, Z., Phillips, P., Wang, S., Ji, G., Yang, J., Yuan, T.F.: Detection of subjects and brain regions related to Alzheimer’s disease using 3d MRI scans based on eigenbrain and machine learning. Front. Comput. Neurosci. 9, 66 (2015)
Acknowledgments
This work was partly supported by projects from Polish National Science Centre (Dec-2011/03/B/ST6/03816).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Szymański, A., Szlufik, S., Koziorowski, D.M., Habela, P., Przybyszewski, A.W. (2016). Building Intelligent Classifiers for Doctor-Independent Parkinson’s Disease Treatments. In: Piętka, E., Badura, P., Kawa, J., Wieclawek, W. (eds) Information Technologies in Medicine. ITiB 2016. Advances in Intelligent Systems and Computing, vol 471. Springer, Cham. https://doi.org/10.1007/978-3-319-39796-2_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-39796-2_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-39795-5
Online ISBN: 978-3-319-39796-2
eBook Packages: EngineeringEngineering (R0)