Comparative Analysis of Machine Learning Methods to Detect Chronic Kidney Disease

Abstract

Chronic Kidney disease (CKD) is a lifelong health hazard that can cause the failure of kidneys. Symptoms of this develop slowly and are not obvious. Early detection of Chronic Kidney Disease can lead to significant progress in finding the cure for this disease. Through this study, we aim to employ ML techniques for the prediction and diagnosis of Chronic Kidney Disease. The findings obtained from our predictive analysis combined with the expertise of healthcare professionals can help in making an accurate prognosis. For this, we have used a dataset containing data from 400 individuals acquired from the University of California Irvine (UCI) repository. Various feature selection techniques have been used to optimize the number of features affecting Chronic Kidney Disease. Subsequently, these desirable features are chosen and used in different ML models and their accuracy, sensitivity is compared. Multiple Machine learning algorithms have been explored such as Logistic Regression, Naïve Bayes, KNN, SVM, Decision Trees, Random Forest Classifier, and Extra Trees Classifier. It was concluded that Decision Trees using information gain gave six optimal features and the Extra Trees Classifier model gives the best accuracy of 99.36 % with Extra Trees Classifier having one of the least execution times.