Abstract
Diabetes Mellitus is fast becoming an endemic in the world, especially in developing countries. An efficient prediction methodology is needed to diagnose the diabetes disease, which can be helpful for health care professionals. Data mining techniques have been widely used in healthcare to mine knowledgeable information from medical data. Data mining is the process of analyzing data based on different perspectives and summarizing it into useful information. Data mining techniques are proven forearly prediction of several diseases with higher accuracy and lower error rate and cost. Classification is one of the generally used techniques in medical data mining. In this paper, we intend to explore various data mining techniques to show the comparison of different classification algorithms using Waikato Environment for Knowledge Analysis (WEKA) and analyze the results in order to find the best suitable classification algorithm for prediction of diabetes diseases. Various performance measures metrics such as sensitivity, specificity, accuracy and error rate are used for finding the accuracy of the classifier.