ItemArticle

Early CKD Prediction Using Ensemble and Basic Machine Learning Models

Title
Early CKD Prediction Using Ensemble and Basic Machine Learning Models
Creator
Srinivasaiah, Raghavendra; Jankatti, Santosh Kumar; Jinachandra, Niranjana Shravanabelagola; Lamani, Manjunath Ramanna; Channegowda, Ravikumar Hodikehosahally
Description
Chronic kidney disease (CKD) is a progressive illness that often remains undiagnosed until advanced stages and represents a significant global health burden. Proper and timely diagnosis of CKD can significantly improve patient prognosis and reduce treatment costs. This study evaluates several machine learning (ML) models, including support vector machine (SVM), random forest (RF), gradient boosting (GB), Nae Bayes (NB), AdaBoost, and a multilayer perceptron (MLP) neural network. Additionally, it proposes a stacking ensemble model combining RF and GB for accurate CKD prediction using a publicly available Kaggle dataset. Missing value handling and feature normalisation are performed during data preprocessing, and model performance is evaluated using an 80:20 traintest split with metrics such as the area under the curve (AUC), classification accuracy (CA), F1-score, precision, recall, and Matthews Correlation Coefficient (MCC). Experimental results indicate that RF and GB achieve the strongest individual performance, while the proposed stacking ensemble attains the highest CA of 99.4%. These findings highlight the potential of artificial intelligence (AI)-driven predictive models to support proactive CKD diagnosis and enhance clinical decision-making in healthcare systems. 2026 by the authors of this article. Published under CC-BY.
Source
International Journal of Online and Biomedical Engineering;Volume;22;Issue;5;pp.171-184
Date
01-01-2026
Publisher
International Federation of Engineering Education Societies (IFEES)
Subject
chronic kidney disease (CKD); ensemble learning; gradient boosting (GB); machine learning (ML); prediction
Coverage
Srinivasaiah R., CHRIST University, Bangalore, India; Jankatti S.K., Dayananda Sagar University, Bangalore, India; Jinachandra N.S., CHRIST University, Bangalore, India; Lamani M.R., Moodlakatte Institute of Technology, Kundapura, India; Channegowda R.H., Dayananda Sagar Academy of Technology and Management, Bengaluru, India
Rights
All Open Access; Gold Open Access
Relation
ISSN: 26268493;
Format
online
Language
English
Type
Article

Citation

Srinivasaiah, Raghavendra; Jankatti, Santosh Kumar; Jinachandra, Niranjana Shravanabelagola; Lamani, Manjunath Ramanna; Channegowda, Ravikumar Hodikehosahally, “Early CKD Prediction Using Ensemble and Basic Machine Learning Models,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/23599.

Output Formats