Because there are no symptoms, it might be challenging to detect chronic kidney disease (CKD) in its early stages. The development and validation of a predictive model for the prognosis of chronic renal disease is the aim of the proposed study. In order to diagnose and categorize diseases, machine learning algorithms are frequently utilized in medicine. Medical records are frequently inaccurate. Using a dataset on chronic kidney disease from the UCI Machine Learning Repository, we applied four machine learning classifiers for analysis: Logistic Regression (LR), Decision Tree (DT), Histogram Boosting Gradient (SHGB), and Support Vector Machine (SVM), using a total of 25 features. The machine learning classifiers were trained using the clusters of the dataset for chronic renal disease. The Kidney Disease Collection is then compiled using non-linear features and categories. The SHGB produces the best results, with an accuracy of 91%.

Chronic Kidney Disease, Support Vector Machine, Histogram boosting Gradient, Logistic Regression and Decision Tree