Machine Learning based Exploratory Data Analysis (EDA) and Diagnosis of Chronic Kidney Disease (CKD)

Abstract

INTRODUCTION: This research paper presents an exploratory data analysis (EDA) approach to diagnose Chronic Kidney Disease (CKD) using machine learning algorithms.
 OBJECTIVES: This paper focuses on early and accurate detection of CKD using a comprehensive dataset of clinical and laboratory parameters to minimize the risk of patients’ health complications with timely intervention through appropriate medications.
 METHODS: Machine Learning based prediction models including Naive Bayes, KNN, Logistic regression, decision tree, ensemble modelling, Random Forest and Ada Boost.
 RESULTS: The results indicate that the Naive Bayes algorithm achieved highest accuracy and sensitivity in detecting CKD.
 CONCLUSION: For reduced features and for binary class classification, Naive Bayes classifier gives best performance in terms of accuracy and computational cost. Other algorithms are good for multi-class classification but for binary class, they are little expensive than Naive Bayes.