A Survey on Various Machine Learning Classifiers for the Diagnosis of Chronic Kidney Disease

Chronic Kidney Diseases (CKD) are among one the significant health emergencies around the world that are causing the death of many individuals consistently every year. Major causes of CKD are diabetes, hypertension, and stroke. The need for quick and precise techniques for the identification of CKD has created a demand for machine learning strategies in the healthcare sector. This survey helps in investigating preventive measures for CKD through early analysis utilizing techniques of machine learning. This paper surveys various studies that have been previously performed for the early identification of CKD using various machine learning classifiers. This paper surveys the comparison of various machine learning classifiers presented based on sensitivity, accuracy rate, and specificity used to identify suitable classifiers for the early diagnosis of CKD in patients suffering from it. In this paper, there is a comparative analysis of previous studies performed on Decision Tree, Logistic Regression (LR), K-Nearest Neighbour (K-NN), Random Forest (RF), Support Vector Machine (SVM), Gradient boosting, Artificial Neural Network (ANN), and Radial Basis Function (RBF) for the diagnosis of CKD.