ANFIS based Diabetes Mellitus Prediction

Diabetes mellitus is a global problem. As a result of diabetes, the pancreas cannot produce adequate amounts of insulin, or the human cells cannot use enough insulin, that it produces. Blood glucose rises in the body of a diabetic patient. It is a common, chronic disease. Diabetes can lead to heart attack, brain stroke, kidney disease, myopia, early death, etc. Early detection of diabetes can lead to advanced treatment.We present a study on the detection of diabetes disease through the ANFIS based Subtractive Clustering Method. The PIMA Indian Diabetes (PID) dataset has been used from Kaggle. The network is trained using data from 768 diabetes patients aged 21 to 81 years. The accuracy of the results depends on different clustering radius. The proposed system uses 8 input attributes and provides a minimum percentage of accuracy of 79.1304 % and a maximum accuracy of 99.1304 % accurate results by estimating the presence and absence of diabetes disease during testing.