A Survey on Data Mining Approaches to Diabetes Disease Diagnosis and Prognosis

Abstract: Data Mining plays an important role in the field of healthcare, because disease diagnosis and analysis have huge size of data. These circumstances create huge number of data handling issues, and that to be handled effectively. The health dataset�s are uncertain and dynamic in nature and it is very tedious to maintain and to manipulate. To overcome the above issues, several studies introduced numerous Machine learning approaches for various disease diagnosis and prognosis. This paper a different data mining and machine learning techniques used in diabetes are analyzed and compared. The task of disease diagnosis and prognosis is a part of classification and prediction. The recent and popular data mining techniques used in clinical data includes Bayesian, Random forest algorithms, Artificial Neural network, SVM and Decision Tree etc. This paper gives the problems and findings about those techniques with various factors.

Keywords: Data Mining, Clinical data, Diabetes Mellitus, classification, Regression.