Performance Analysis of Various Machine Learning Classifiers on Reduced Chronic Kidney Disease Dataset
| Main Authors: | Md. Tanjeel Islam, Khan, Md. Sazzadul Islam, Prottasha, Tasneem Alam, Nasim, Abdullah Al, Mehedi, Md. Appel Mahmud, Pranto, Nafiz Al, Asad |
|---|---|
| Format: | Article Journal |
| Bahasa: | eng |
| Terbitan: |
, 2020
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/5760273 |
Daftar Isi:
- Chronic kidney disease (CKD) is considered as a lethal disease all over the world. Chronic kidney disease (CKD) is a condition where kidney shrinks in size and also changes its natural shape. Various machine learning algorithms can be very useful for prediction of CKD. This paper investigates the performance of various machine learning algorithm on chronic kidney disease dataset. Support Vector Machine (SVM), Decision Tree, Naïve Bayes, Random Forest and Logistic Regression are the algorithms considered in this paper. Initially a dataset of 400 instances having 24 attributes is considered. Later feature selection algorithm is used to identify the important attributes and we reduced the uncorrelated attributes and observed the results. Results show that Naïve Bayes achieved the maximum accuracy of 99.1% on reduced chronic kidney disease dataset of 23 attributes. In terms of time complexity decision tree performed better than the other classifiers. It is expected that the application of different machine learning algorithms can help to predict CKD with great accuracy in practice.