Computational Intelligence Approaches for Prediction of Chronic Kidney Disease

Abstract

Over the past few decades, it has been observed that there is a growing interest in the area of intelligence systems, such as Machine Learning. Machine learning has been extensively used in order to support medical specialists and clinicians in the help of forecast and diagnosis of various diseases. The aim of this study is to compare the performance of six supervision-based Machine Learning techniques, which are used in the prediction and detection of the chronic kidney disease outbreak. Machine learning techniques are used to solve clinical problems and medical diagnosis’ which have recently been developed. Hence, it is essential to have a framework that can instantly recognize the prevalence of kidney disease in thousands of samples. This research uses the chronic kidney disease dataset that contains 400 Kidney patient’s data including 25 parameters. Moreover, we evaluated the performance of six supervision-based machine learning classification techniques, which are: KNN, Support Vector Machine, Decision Tree, Random Forest, Naïve Bayes and Logistics Regression. The performance of the supervised machine learning classification techniques was validated with sensitivity, specificity, f1 measure and accuracy. In this experiment, NB and RF outperformed, they were found to be at 100% accuracy, whereas the DT achieved 98% accuracy. Moreover, the KNN, SVM, LR classification techniques achieved 96% accuracy. Our findings showed that both the Random Forest and Naïve Bayes classification techniques outperformed as compared to other classification techniques used to predict kidney disease of the patients tested. In summary, our study has emphasized the research trends and scope in relation to Chronic Kidney Disease and as well as clinical research areas by machine learning techniques, which have had an effective impact in biomedical fields.