Machine learning techniques for prediction of Parkinson’s disease using big data

Citations of this article
Mendeley users who have this article in their library.
Get full text


The growth of data in the healthcare industry grows exponentially and the annual growth rate is about 40%, managing this amount of data is challenging task. Big Data architecture and frameworks affords the platform for data storage and processing of massive volume of data in healthcare industry. The paper aims to provide Big Data technologies and Machine Learning algorithms to predict Parkinson’s Disease (PD). The dataset from PPMI are used in the current study and observe the progression of the Parkinson’s Disease. The Movement Disorder Society-Unified Parkinson’s Disease (MDS-UPDRS) features are used for the prediction model. The current study focuses on machine learning algorithms from python libraries such as pandas, ski-kit learn, numpy and matplotlib. The important features obtained are tremor, bradykinesia, facial expression is observed as important features for classification. It is observed that logistic regression and multi class classifier performed with accuracy of 99.04% than the other algorithms such as Naïve Bayes, k-Nearest Neighbor, SVM and Neural Network.




Kanagaraj, S., Hema, M. S., & Nageswara Gupta, M. (2019). Machine learning techniques for prediction of Parkinson’s disease using big data. International Journal of Innovative Technology and Exploring Engineering, 8(10), 3788–3791.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free