Determining the probability of occurrence of diabetic cardiovascular disorder using machine learning algorithms.

Diabetes is one of the leading global health emergencies of the 21^st century. The threatening side effects proves it to be a dangerous epidemic. This paper proposes a model to solve the problem in the existing system by comparing various data mining techniques in order to cluster and classify them. The paper studies a huge sample of diabetic patients common to diabetes and cardiovascular disorders. The method adopted is to cluster the data into three prior categories of high, medium and low clusters. Once clustered, optimum algorithmic technique is implemented to classify the data into mild and severe fragments in order to determine the chances of occurrence of a heart disorder due to the impact of diabetes. The aim is to implement an algorithm that can classify the data collected in order to infer whether or not a diabetic patient is prone to a heart disorder or not. [ABSTRACT FROM AUTHOR]