Abstract
Diabetes mellitus (DM) is a chronic disease. It has been rising more rapidly in middle- and low-income countries. World Health Organization (WHO) [1] estimates that diabetes was the seventh leading cause of death in 2016. In this paper a database concerning this disease where discussed and implemented by data mining techniques. Data mining techniques used to help the prediction of DM. It makes the prediction process faster, cheaper and more accurate for the benefit of both physicians and patients. In this paper, well-known data mining algorithms explored to achieve DM prediction. The performance of these algorithms was evaluated and discussed using Orange Data Mining tool. The performance evaluation executed using two metrics: the recall and the precision; applied to each discussed classification algorithm. The studied classification algorithms are Naive Bayes, K-Nearest Neighbours, Artificial Neural Network, Decision Tree, Random Forest, Support Vector Machine and Logistic Regression.