Diagnosis of diabetes using bee colony algorithm and fuzzy decision tree

Today, in medical knowledge, collecting a lot of data about different diseases is very important. Medical centers collect this data for various purposes. One of the goals of using this data is to research these data and obtain useful results and patterns in relation to diseases. The large volume of this data and the confusion used to overcome this problem to obtain useful relationships between risk factors in diseases. In this study, due to the importance of diabetes in medicine, the aim is to present a hybrid model using fuzzy decision tree and bee cloning algorithm to increase the accuracy of diagnosis. The proposed method is called ABC-FDT. In ABC-FDT, the number of optimal fuzzy sets for each feature is considered so that the best segmentation for the features is provided with the two goals of accuracy and reduction of complexity. PID diabetes data set and classification methods based on ID3, C4.5 and CART rules were used for evaluation. The results indicate the superiority of ABC-FDT algorithm in terms of rules of number, accuracy, sensitivity and specificity. ABC-FDT also outperformed the recently introduced GAANN, QFAM-GA, and SM-RuleMiner algorithms by 10.1, 5.4, and 7.8 percent, respectively.