Welcome to the InfoSci Platform
Performance Analysis of Classification Techniques With Feature Selection Method for Prediction of Chronic Kidney Disease

Performance Analysis of Classification Techniques With Feature Selection Method for Prediction of Chronic Kidney Disease

Noopur Goel
Copyright: © 2021 |Pages: 25
ISBN13: 9781799844204|ISBN10: 179984420X|ISBN13 Softcover: 9781799852797|EISBN13: 9781799844211
DOI: 10.4018/978-1-7998-4420-4.ch010
Cite Chapter Cite Chapter

MLA

Goel, Noopur. "Performance Analysis of Classification Techniques With Feature Selection Method for Prediction of Chronic Kidney Disease." Innovations in Digital Branding and Content Marketing, edited by Subhankar Das and Subhra Rani Mondal, IGI Global, 2021, pp. 220-244. https://doi.org/10.4018/978-1-7998-4420-4.ch010

APA

Goel, N. (2021). Performance Analysis of Classification Techniques With Feature Selection Method for Prediction of Chronic Kidney Disease. In S. Das & S. Mondal (Eds.), Innovations in Digital Branding and Content Marketing (pp. 220-244). IGI Global. https://doi.org/10.4018/978-1-7998-4420-4.ch010

Chicago

Goel, Noopur. "Performance Analysis of Classification Techniques With Feature Selection Method for Prediction of Chronic Kidney Disease." In Innovations in Digital Branding and Content Marketing, edited by Subhankar Das and Subhra Rani Mondal, 220-244. Hershey, PA: IGI Global, 2021. https://doi.org/10.4018/978-1-7998-4420-4.ch010

Export Reference

Mendeley
Favorite

Abstract

Chronic kidney disease has become a very prevalent problem worldwide and almost 10% of the population is suffering and millions of people are dying every year because of chronic kidney disease. Numerous machine learning and data mining techniques are applied by many researchers around the world to diagnose the presence of chronic kidney disease, so that the patients of chronic kidney disease may get benefited in terms of getting proper healthcare follow-up. In this chapter, Experiment 1 is conducted by implementing different five different classifiers on the original chronic kidney disease dataset. In Experiment 2, feature selection using feature importance method is used to reduce the chronic kidney disease dataset. A subset of 15 independent features and one target feature ‘class' is obtained. Again, the same steps are implemented but on the newly obtained reduced dataset. The results of both the Experiments 1 and 2 are compared, and it is observed that the accuracy of classifiers with feature selection is far better than the accuracy of classifiers without feature selection.

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.