Identification and Classification of Chronic Kidney Disease: An Ensemble Learning Approach
Year: 2026
Type: conference-paper
Abstract: Chronic kidney disease (CKD) is a progressive disease that remains undetected in its early stages, where delay in diagnosis leads to permanent renal failure and increased mortality. Timely and precise staging of CKD plays a crucial role in reducing the risk of clinical complications such as anemia, hypertension, malnutrition, mineral bone disease, and neurological disorders through prompt medical intervention. In this paper, we investigated multiple Machine Learning (ML) and Ensemble Learning (EL) techniques for CKD prediction using an augmented dataset with 822 instances, which extends the conventional CKD dataset available in the UCI machine learning repository (400 instances) and is now available in IEEE DataPort. Multiple ML and EL models have been evaluated in a standardised experimental environment using stratified train-test partitioning and five-fold cross-validation, and the techniques were evaluated using various performance measures, including accuracy, recall, precision, F1-score, and ROC-AUC. Experimental results demonstrated the clear superiority of EL over ML, especially the Light Gradient Boosting Algorithm (LightGBM), which achieved higher accuracy and better crossvalidation stability. These findings validated that the effectiveness of augmenting the dataset with EL significantly enhanced prediction performance.
Authors: Swarnalatha Prathipati, Yellapu Jhansi
Institution: GITAM University
Language: English
Subfield: Health Information Management
Field: Health Professions
Domain: Health Sciences
Open Access status: hybrid
OpenAlex ID: W7203609782