Prediction of Parkinson’s Disease Using Machine Learning Approaches

Document Type

Capstone

Authors

Gnana Velagapalli, Grand Valley State University

Lead Author Type

MBI Masters Student

Advisors

Dr. Guenter Tusch, tuschg@gvsu.edu

Embargo Period

6-5-2017

Abstract

Parkinson’s disease(PD) is the second most common neurodegenerative disease after Alzheimer’s disease. Prediction of PD is most difficult and challenging issue for physicians. It’s hard for the physicians in most of the cases to take a decision on patient whether he/she can develop the disease in future or not. In such cases machine learning techniques, can be most helpful to the physicians for better clinical decision support and prediction of the disease. In this paper, I had performed 4 machine learning models were used to predict the Parkinson’s disease. It was observed that Random Forest and SVM has given the overall accuracy of 87% and 88% when compared to other approaches that were used in this paper. These techniques can help the physicians to make better decisions without reviewing of similar or prior cases.

ScholarWorks Citation

Velagapalli, Gnana, "Prediction of Parkinson’s Disease Using Machine Learning Approaches" (2017). Technical Library. 278.
https://scholarworks.gvsu.edu/cistechlib/278