Welcome to the InfoSci Platform
Classification of Parkinson's Disease Based on Machine Learning

Classification of Parkinson's Disease Based on Machine Learning

Puspita Dash, Susil Pani
Copyright: © 2023 |Pages: 11
ISBN13: 9781668476796|ISBN10: 1668476797|ISBN13 Softcover: 9781668476802|EISBN13: 9781668476819
DOI: 10.4018/978-1-6684-7679-6.ch004
Cite Chapter Cite Chapter

MLA

Dash, Puspita, and Susil Pani. "Classification of Parkinson's Disease Based on Machine Learning." Stochastic Processes and Their Applications in Artificial Intelligence, edited by Christo Ananth, et al., IGI Global, 2023, pp. 39-49. https://doi.org/10.4018/978-1-6684-7679-6.ch004

APA

Dash, P. & Pani, S. (2023). Classification of Parkinson's Disease Based on Machine Learning. In C. Ananth, N. Anbazhagan, & M. Goh (Eds.), Stochastic Processes and Their Applications in Artificial Intelligence (pp. 39-49). IGI Global. https://doi.org/10.4018/978-1-6684-7679-6.ch004

Chicago

Dash, Puspita, and Susil Pani. "Classification of Parkinson's Disease Based on Machine Learning." In Stochastic Processes and Their Applications in Artificial Intelligence, edited by Christo Ananth, N. Anbazhagan, and Mark Goh, 39-49. Hershey, PA: IGI Global, 2023. https://doi.org/10.4018/978-1-6684-7679-6.ch004

Export Reference

Mendeley
Favorite

Abstract

In recent years, brain-related illnesses like Parkinson's disease have gained increasing attention due to the economic strain caused by healthcare expenses associated with these diseases in developed nations. Parkinson's disease (PD) is a neurodegenerative disorder that affects nerve cells responsible for producing dopamine, a neurotransmitter in the brain. A recent study utilized the recursive feature elimination (RFE) algorithm in four academic papers to select features and apply machine learning techniques. These techniques included direct and indirect separation methods, as well as decision tree and potential separator approaches. The study evaluated the performance of each category using five selected features identified through the RFE approach. Notably, the indirect category, specifically random forest and bagging cart, demonstrated excellent performance with an accuracy of 96.93% and 97.43%, respectively. This analysis aids physicians in effectively classifying neurodegenerative diseases by utilizing gait symptoms to differentiate them from healthy individuals.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.