A Comparison of Data Classification Efficiency in Chronic Kidney Disease Patients Dataset Using Data Mining Techniques

Abstract

The objectives of this research are: 1) to study the data classification for patients with chronic kidney disease using data mining techniques, and 2) to compare the efficiency of two data classifications, namely the k nearest neighbor and decision tree. The experimental results show that the decision tree technique provides the best performance with 93% accuracy, 92% precision, and 92% recall while the k nearest neighbor gives 65% accuracy, 58% precision, and 44% recall respectively.