In 2050, the world's diabetic patients will arrive at 642 million, which implies that one of the ten grown-ups later on is experiencing diabetes. Diabetes mellitus (DM) is characterized as a gathering of metabolic issues applying critical tension on human wellbeing around the world. DM is a persistent sickness portrayed by hyperglycemia and it might cause numerous inconveniences. To forestall this issue, to break down the given medical clinic dataset by directed AI technique(SMLT) with catch a few data resembles, variable ID, uni-variate examination, bi-variate and multi-variate investigation, missing worth therapies and dissect the information approval, information cleaning/getting ready and information perception will be done on the whole given dataset. Our analysis provides a comprehensive guide to sensitivity analysis of model parameters with regard to performance in prediction of diabetic patients by given attributes of dataset with evaluation of GUI based user interface diabetes attribute prediction. Additionally, it observes to lead an increase the highest accuracy in diabetic prediction of attributes by a significantly better classification report, identify the confusion matrix and to categorizing data from priority and the result shows that the effectiveness of the proposed machine learning algorithm technique can be compared with best accuracy with precision, Recall and F1 Score.