Prediction of Prediabetes using Fuzzy Logic based Association Classification

Diabetes is one of the world's most common chronic disease. Prediabetes is the pre-phase of diabetes, which slowly lead to type-2 diabetes. Early detection of diabetes prevents hazardous health and saves a life. Pima Indian Diabetes dataset found to have a group of data with prediabetes conditions among the patient who have been classified as “diabetes=No”. Few data in this class found to have a deviated characteristic among the group it belongs to and can be mentioned as outliers for that group. To identify the hazard boundary values of the risk factors which lead to prediabetes, one requires expert's advice. An alternate method is to make use of a system which can handle the uncertain hazard boundary value. Such uncertainty can be handled by fuzzy logic in a better way than the conventional crisp method like discretization. Hence, the proposed system identifies the risk factors of prediabetes using fuzzy logic based associative classification technique. The proposed method found to identify a more accurate set of outlying prediabetes condition (outliers) among the data which belongs to the negative result of diabetes.