Development of Data Mining Framework Cardiovascular Disease Prediction

One of the highest shares of data-driven technology of health sector happens for private insurance stakeholders. It is therefore clear that private insurance companies can only survive being competitive in covering different medical stages such as surgery, intervention and other clinical trials in a high-risk environment. Estimation of expected costs and coverage is also important for both patient and insurer. In this case study we as a Data Mining and Artificial Business consultant want to explore different techniques of data mining to find out business risks for patients. We have asked the insurer to provide us a sizable medical history to watch those features. We would like to predict if given biographical profile of the patient along with exam results can predict CVD so he can cover his costs with this Insurer. On the other hand, in case of higher error of misclassified CVD what kind of decision should be taken by risk holder and insurer. Which one of these attributes causing this cost and what other stakeholders like target group of patients can be suffered from the loss? The ultimate goal is to develop a model that can predict the gap between those patients' perception of their disease and their real disease. This can further help stakeholders to develop specific insurance policy.