Chronic Kidney Disease Prediction Using Machine Learning Ensemble Algorithm

Abstract

Chronic Kidney Disease (CKD) Is A Non-communicable Illness That Affects A Significant Portion Of The Global Population. Major Risk Factors Include Diabetes, Hypertension, And Cardiovascular Disorders. CKD Often Remains Asymptomatic In Its Early Stages, Leading To Delayed Diagnosis And Potentially Fatal Outcomes. This Project Proposes A Machine Learning-based Approach For Early CKD Prediction Using Ensemble Algorithms. Four Ensemble Models—Random Forest, Gradient Boosting, Bagging, And AdaBoost—are Implemented To Diagnose CKD At An Early Stage. The Models Are Evaluated Using Multiple Performance Metrics, Including Accuracy, Sensitivity, Specificity, Precision, F1-Score, Mathew Correlation Coefficient (MCC), And Area Under The Curve (AUC). Experimental Results Indicate That The Random Forest Model Outperforms Other Algorithms, Achieving The Highest Accuracy, Sensitivity, Precision, MCC, And AUC Scores. The Proposed System Demonstrates The Potential To Assist Medical Practitioners In Early CKD Detection, Enabling Timely Intervention And Improving Patient Outcomes.

Keywords