A Machine Learning Approach to Early Detection and Classification of Kidney Disease

Kidney disease is additionally as CKD, also called chronic kidney failure (CKF), that is marked by the little deterioration of functionality of the organ which is kidney. This organ engages a major role in purifying waste and over derived from blood to produce urine. In the later stages of CKD, harmful stages of fluids, electrolytes combined with toxins may accumulate in the physique. The term “chronic” signifies the progressive nature of organ damage. The occurrence of this illness is rising sharply in various regions around the world. A person is limited to only exist without functioning kidneys for an average of about 432 hours, creating an urgent demand for kidney transplants and dialysis treatments. For those suffering from severe renal failure, this short survival window emphasizes how vital and life-saving medical measures are. This study presents a methodology which applies different of clinical information to predict the status of CKD. This work implements four ML Models namely Decision Tree which is DT, SVM, XGBoost and Logistic Regression LR. The experimental results show that the Decision Tree (DT) model outperforms with score rate of 98.75%.