Comparative Study of Classifier for Chronic Kidney Disease prediction using Naive Bayes, KNN and Random Forest

Abstract

Chronic kidney disease (CKD), is also known as chronic nephritic sickness. It defines constrains which affects your kidneys and reduces your potential to stay healthy. There will be various complication concerns like increased levels in your blood, anemia (low blood count), weak bones, and nerve injury. Detection and treatment should be done prior so it will typically keep chronic uropathy from obtaining a worse condition. Data processing is the term used for information discovery from big databases. The task of knowledge mining is to generate regular patterns from historical data and emphasize future conclusions , follows from the convergence of many recent trends: the decreased value of huge knowledge storage devices and therefore the tremendous ease of aggregation knowledge over networks; the development of robust and economical machine learning algorithms to method this data; and therefore the decrease value of machine power, enabling use of computationally intensive strategies for knowledge analysis. Machine learning is an important task as it benefits many applications such as analyzing life science outcomes, sleuthing fraud, sleuthing faux users etc. varied knowledge mining classification approaches and machine learning algorithms are applied for prediction of chronic diseases. Therefore, this paper examines the performance of Naive Bayes, K-Nearest Neighbour (KNN) and Random Forest classifier on the basis of its accuracy, preciseness and execution time for CKD prediction. Finally, the outcome after conducted research is that the performance of Random Forest classifier is finest than Naive Bayes and KNN