Abstract: Diabetes is one of the most significant health issues which are faced by maximum number of human being now a day. Diabetes is a chronic, metabolic disease characterized by elevated levels of blood glucose (or blood sugar), which leads over time to serious damage to the heart, blood vessels, eyes, kidneys and nerves.There are three main types of diabetes: Type 1 diabetes is caused by an autoimmune reaction in which the body’s immune system attacks the insulin-producing beta cells of the pancreas. As a result, the body produces very little or no insulin. Type 2 diabetes is the most common type of diabetes. Initially, hyperglycaemia (high blood glucose levels) is the result of the inability of the body’s cells to respond fully to insulin, a situation termed ‘insulin resistance’. Gestational diabetes (GDM) is characterised by high blood glucose levels during pregnancy. It may occur at any time during pregnancy (although most likely after week 24) and usually disappears after the pregnancy. But the present study is conducted for diabetes mellitus of Type I and Type II and its prediction and detection using data mining and data warehousing techniques. The study uses various data mining and warehousing techniques to predict and detect the diabetes mellitus. So that a multidimensional diabetes data warehouse has been built to store and access the general as well as medical records of diabetes patients. Along with that a data mining model has also been proposed and implemented with this diabetes data warehouse to predict the diabetes mellitus among patients and the risk factor for a particular type i.e., Type I and Type II diabetes and also the exact method to diagnose it.In this study,OLAP operations are performed to segregate the data based on several attributes like gender, type of diabetes, localities, etc.The k-means clustering algorithm is used for partitioning the data into diabetes and non-diabetes clusters.Weighted Average Method (WAM) is used to improve the accuracy of analytic predictive performance models for diabetes prevention systems with more number of new patients.

Keywords: Architectural Data Warehouse, Diabetes Mellitus, Data Mining and Warehousing Techniques, Multidimensional Diabetes Data Warehouse, MultidimensionalStar Schema, k- means Algorithm, OLAP Operations, Types of Diabetes- Type-I & Type-II,WAM.