Performance Analysis of Machine Learning Algorithms in Chronic Kidney Disease Prediction

Analyzed eight machine learning models, including Random Forest, SVM, and Logistic Regression, for Chronic
Kidney Disease (CKD) diagnosis.
◦ Addressed missing data in the UCL CKD dataset using “mean/mode” and “Random sampling” techniques for
improved model performance.
◦ Achieved 99% accuracy with Random Forest and Logistic Regression, outperforming other models such as
AdaBoost, XGBoost, and KNN (73%).