Machine Learning Methods for Managing Parkinson’s Disease
Kumar R1, E. Laxmi Lydia2, K. Shankar3, Phong Thanh Nguyen4, Satria Abadi5
1KumarT R.,T Department of Computer Science, Kristu Jayanti College, Bangalore (Karnataka), India.
2E.T Laxmi Lydia, Professor, Department of Computer Science and Engineering, Vignan’s Institute of Information Technology (A), Visakhapatnam (Andhra Pradesh), India.
3K.T Shankar, Department of Computer Applications, Alagappa University, Karaikudi (Tamil Nadu), India.
4PhongT Thanh Nguyen, Department of Project Management, Ho Chi Minh City Open University, Vietnam.
5Satria Abadi, Department of Information Systems, STMIKT Pringsewu, Lampung, Indonesia.
Manuscript received on 15 September 2019 | Revised Manuscript received on 24 September 2019 | Manuscript Published on 10 October 2019 | PP: 965-968 | Volume-8 Issue-6S2, August 2019 | Retrieval Number: F12910886S219/19©BEIESP | DOI: 10.35940/ijeat.F1291.0886S219
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: This is a fact that more than one and half million patients are suffering from Parkinson’s disease in the big countries like China, United States, Russia and worldwide is around 6 millions. Even after of many worldwide experiments and research the Parkinson’s disease is an major challenge for biomedical research, scientists and doctors. The problem of this research is that the symptoms of the disease can be investigated in the early and late early age. So that it becomes very difficult to know accurately about this disease. In order to do this research initially some random numbers of features are selected for the research. These features are extracted by many neural network algorithms with minimum redundancy and the maximum similar feature selection. The accuracy of the algorithms results is also a very big concern. It is assumed that the selection algorithms must provide overall 92.3%, precision 21.2% and MC coefficient values of 0.75 & ROC value 0.97%. If such results are achieved then that means it is better than previous research and the work is in improvement process. There are many machine learning algorithms used in different countries based on the research approaches like SVM, DT, PPDM, Artificial intelligence etc. Often the people are aware with the symptoms of this disease so if the proper treatment is given at proper time then the patients may get proper treatment on time and this leads to boost the recovery time. There are many machine learning algorithms and models are under development process which may help to predict the disease in early stage. In this research an automated diagnostic system is introduced. The Multilayer perception, BayesNet and other algorithms are used. This research also provides the observation that such models and methods can help to recover a patient in minimum time because of the early stage prediction of disease.
Keywords: Parkinson’s Prediction, Machine Learning Algorithms, Artificial Intelligence System, Bayesnet, Data Mining Algorithms.
Scope of the Article: Machine Learning