• Nura Muhammad Sani
• Dr Mustapha Ismail
• Dr Mohammed Mansur Ibrahim

Abstract: Chronic kidney disease (CKD) is a prevalent and serious health condition affecting a significant proportion of the population worldwide. Early and accurate prediction of CKD can greatly aid in timely interventions and improve patient outcomes. This research proposes a hybrid ensemble learning model that combines the predictive power of three machine learning algorithms, namely Support Vector Machine (SVM), Decision Tree, and Nave Bayes, to enhance prediction accuracy of CKD prediction. The study uses a dataset comprising information from 400 patients diagnosed with CKD. The performance of the individual algorithms is assessed, revealing that the Naive bayes algorithm exhibited comparatively lower accuracy than the Decision Tree and Support Vector (VM). To leverage the strengths of each algorithm, a hybrid ensemble learning model is constructed by combining the Decision Tree, SVM and Nave Bayes algorithms predictions. The hybrid ensemble model demonstrates exceptional predictive capabilities, achieving an impressive accuracy of 98% when evaluated on the aforementioned CKD dataset. This signifies a substantial improvement over the individual algorithms ‘performance. The superior accuracy attained by the hybrid ensemble model suggests its potential as a reliable tool for CKD prediction.

Chronic Kidney Disease, Prediction, Machine learning, Hybrid Ensemble Model

"Chronic Kidney Disease Prediction Using Hybrid Ensemble Learning Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 8, page no.b220-b234, August-2023, Available :http://www.jetir.org/papers/JETIR2308127.pdf

"Chronic Kidney Disease Prediction Using Hybrid Ensemble Learning Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 8, page no. ppb220-b234, August-2023, Available at : http://www.jetir.org/papers/JETIR2308127.pdf