Predicting Chronic Kidney Disease using RF Algorithm for Big Data

Abstract

Chronic Kidney Disease (CKD) involves a slow loss of kidney function. Kidneys remove wastes and fluids from your blood, which are later eliminated in urine, covering over a period of months to years, signs and symptoms of kidney disease are usually indistinct, and are a serious disease. It is enlightened in six stages congenial to the severity level. It is categorized into various stages based on the Glomerular Filtration Rate (GFR), which in turn utilizes several attributes, like age, sex, race and Serum Creatinine. Among multiple available models for estimating GFR value, Chronic Kidney Disease Epidemiology Collaboration (CKD-EPI), which is a linear model, has been found to be quite efficient because it allows detecting all CKD stages. Random Forest had 99.24% truthfulness. The model's best result is created by considering the 10 most reelected features. When compared to previous studies, our results are amid the good for assessment metrics and the ranking accuracy.