Rules Found by Multimodal Learning in One Group of Patients Help to Determine Optimal Treatment to Other Group of Parkinson’s Patients Andrzej W. Przybyszewski 1(&) , Stanislaw Szlufik 2 , Piotr Habela 1 , and Dariusz M. Koziorowski 2 1 Polish-Japanese Academy of Information Technology, 02-008 Warszaw, Poland {przy,piotr.habela}@pja.edu.pl 2 Department of Neurology, Faculty of Health Science, Medical University, Warsaw, Poland stanislaw.szlufik@gmail.com, dkoziorowski@esculap.pl Abstract. We have already demonstrated that measurements of eye movements in Parkinson’s disease (PD) are diagnostic. We have performed experimental measurements of fast reflexive saccades (RS) in PDs in order to predict effects of different therapies. We have also found rules by means of data mining and machine learning (ML) in order to classify how different doses of medication have determined motor symptoms (UPDRS III) improvements. These rules from one group of 23 patients only on medications were supplied to another group of 18 patients under medications and DBS (deep brain stimulation) therapies in order to predict motor symptoms changes. Such parameters as patient’s age, neurological and saccade’s parameters gave a global accuracy in the motor symptoms predictions of 76% based on the cross-validation. Our approach demonstrated that rough set rules are universal between groups of patients with different therapies that may help to predict optimal treatments for individual PDs. Keywords: Neurodegenerative disease  Rough set  Decision rules  Granularity 1 Introduction Our knowledge about brain‘s algorithms, especially about their plastic properties is still very limited. The compensatory mechanisms of the brain are many times better than in artificial NN, which gives a great advantage of the natural in comparison to artificial intelligent systems. A disadvantage of such great plastic system is that in the most cases, subject may notice first symptoms of brain dysfunctions when a big part of his/her brain is already dead. We still do not know how to recover dead cells, as it is a case in the neurodegenerative diseases (ND) such as Alzheimer (AD) or Parkinson’s (PD). Neurodegenerative are related to the brain inability to further compensate lost of many neurons in the Central Nervous System. As these diseases starts many years © Springer International Publishing AG 2017 N.T. Nguyen et al. (Eds.): ACIIDS 2017, Part II, LNAI 10192, pp. 359–367, 2017. DOI: 10.1007/978-3-319-54430-4_35