Analysis of Diabetics Data by Data Mining Techniques

Medical dataset is a vital ingredient used in predicting patient's health condition. In other to have the best Prediction, there calls for a technique with high degree of accuracy. With the computerization in hospitals, a huge amount of data is collected. Although human decision-making is often optimal, it is poor when there are huge amounts of data to be classified. Medical data mining has great potential for exploring hidden patterns in the data sets of medical domain. These patterns can be used for clinical diagnosis. In this paper, we modeled data from diabetes patients and used it to predict the diabetes probability of any patient. In this paper a method for constructing fuzzy membership functions from data collected from Hospitals and diagnoses in the medical application area of diabetics is being presented. Fuzzy membership functions are generated to represent linguistic medical concepts for the data to symbol conversion unit of the medical knowledge based system. This data consists of six variables collected from private hospital in kanyakumari district. The variables chosen are low, medium and high. Based on the variables the risk of diabetics can be diagnosed. The aim of this paper is analyze the Diabetics data and Mamdani's fuzzy inference system is used. The reasonable results verify the validity of our method. This method tries to use the data mining technique effectively than other models available. Moreover the variables taken are linguistic variables which focuses on accuracy of the results.