Performance analysis of diabetic prediction by using machine learning algorithm

Diabetes is a common, chronic disease. Prediction of diabetes at an early stage can lead to improved treatment. Data mining techniques are widely used for prediction of disease at an early stage. In this research paper, diabetes is predicted using significant attributes, and the relationship of the differing attributes is also characterized. Various tools are used to determine significant attribute selection, and for clustering, prediction, and association rule mining for diabetes. Significant attributes selection was done via the principal component analysis method. I am finding to indicate a strong association of diabetes with body mass index (BMI), Blood pressure, Skin thickness, Insulin, diabetic prediction, and with glucose level, which is extracted via the A priori method. K-means clustering techniques were implemented for the prediction of diabetes. The KNN technique provided a best accuracy of 73%, and may be useful to assist medical professionals with treatment decisions.