Chronic Kidney Diseases Detection Using machine Learning

Abstract

Chronic kidney disease (CKD) and chronic renal disease (CRD) (CKD). Chronic renal disease refers to illnesses that affect your kidneys and reduce their ability to keep you healthy. Consequences include nerve damage, high blood pressure, anaemia, weak bones, and a lack of nourishment. Early detection and treatment can frequently stop chronic renal disease from getting worse. Data mining is the technique of obtaining knowledge from huge datasets. Utilizing previous data to find trends and guide decisions going forward is the aim of data mining. This task is the result of the convergence of a number of recent trends, including the declining cost of large data storage devices, the increasing simplicity of data collection over networks, the expansion of dependable and efficient machine learning algorithms, and the declining cost of computational power, which enables the use of computationally intensive techniques for decision-making. Machine learning has already produced useful applications in fields like assessing results from medical research, spotting fraud, spotting bogus users, etc.For the purpose of predicting chronic diseases, various data mining categorization methodologies and machine learning algorithms are used. The goal of this study is to develop a new decision-support system for forecasting chronic renal disease. This study compares the accuracy, precision, and execution time of Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) classifiers for the prediction of CKD.