Diagnosis of Heart Disease Using K-means Clustering and Bell Curve Fitting

Abstract

Due to changes in way lots of urban population experiences pathology and different heart related diseases. Many heart issues are because of irregular way and different factors like high cholesterol diets and lack of exercise. If on basis of medical records we are able to confirm patterns of heart issues we tend to scale back viscous connected cases within the health care system. Multiple factors impacting viscous health will be incorporated into the information set for locating different geographical, temporal and spatial correlations. The analysis proposes a strategy exploitation information mining to analyze patterns in tending significantly cardio-vascular diseases. The projected formula uses clustering for feature extraction within the vital organ ( ex. Heart rate, sterol levels). It'll cluster the data and tell what per cent of individuals are healthy and how many are sick. The clusters are mapped with the given price information which can facilitate in finding out the insurance cover of the patients. Cleveland information set is employed for mapping of illness teams to price teams, other than Cleveland information sets 2 different information sets are used for comparative calculation of performance of K clusters on the information set.