Kidney disease prediction using different classification techniques of machine learning

Based on the rise in chronic kidney disease (CKD) incidence in recent years, a more accurate early prediction model is required to identify high-risk individuals before they develop end-stage renal failure. To date, it has been determined that diabetes mellitus6, obesity5, and female sex4 are all significant risk factors for chronic renal disease. Recently, several biomarkers connected to CKD have been identified. Treatment for renal failure and chronic kidney disease is both expensive and inefficient. Only around 5% of those with early CKD are aware of their illness, though20. Once CKD is detected, glomerular damage has typically reached over 50% and is irreversible. An accurate chronic renal illness prediction can be very helpful in this regard. This study aims to forecast renal failure using different classification techniques to predict the accuracy result of the algorithms and gives the result as whether a person has chronic kidney disease or not can be predicted.