Diabetes mellitus forecast using different data mining techniques

In this paper with the improvements in expert systems and ML tools, the effects of these innovations are entering to more application domains day-by-day and medical field is one of them. Decision-making in medical field can sometimes be a trouble. Classification systems that are used in medical decision-making provide medical data to be examined in shorter time and in a more detailed manner. In this particular work four different approaches have been proposed for the classification of subjects into two classes namely: Diabetic & Non-diabetic. The techniques undertaken are ANFIS, PCA + ANFIS, Neural Networks & PCA + Neural Networks. The results obtained are very interesting and show improvement from the previous works. There is enough scope for improvement in this field and with the advent of faster and more accurate learning techniques the results can surely be improved considerably. Again the application on live subjects rather than relying on stored datasets can lead to breakthrough research in the field of diabetes.