Comparison of Data Mining Algorithms in the Diagnosis of Type Ii Diabetes

Diabetes is one of the most prevalent diseases in the world today with high mortality and morbidity rate, thus one of the biggest health problems in the world. There are many ways to diagnose the disease; one of these methods is data mining algorithms. The use of data mining on medical data has brought about important, valuable, and effective achievements, which can enhance the medical knowledge to make necessary decisions. In this paper, the diagnosis of type II diabetes is done through data mining algorithms. The dataset used for the diagnosis of type II diabetes includes 768 samples from diabetic patients taken from Pima Indians Dataset. In this article, Naive Bayes, RBF Network, and J48 are the data mining algorithms used to diagnose type II diabetes. The so-called algorithms perform diagnosis using Weka. Finally, the algorithms were compared to determine which one was more accurate in diagnosis of type II diabetes. The results revealed that Naive Bayes, having accuracy rate of 76.95%, enjoyed the highest accuracy for diagnosis of type II diabetes.