Comparison of Support Vector Machine and Naïve Bayes Classifiers for Predicting Diabetes

Abstract

Several chronic diseases have affected the human health in the recent times. Many diseases are widespread and caused severe damage on the mankind. The technological advances have proved most of the diseases can be cured in this medical era, but certain diseases can only be prevented but not cured, one among them is diabetes. In this paper, we report a medical case by considering electronic health records of diabetic patients from various sources. The analyses are carried out using two data mining classification algorithms such as Naive Bayes and Support Vector Machine. The aim of the analysis is to predict diabetes using health record and compare the accuracy of these two algorithms to find a better algorithm for predicting diabetes.