Machine Learning Models for Heart Disease Prediction
In the earlier couple of years, there has been a critical advancement in how machine learning can be utilized in different businesses and research. Social insurance is one of the quickest developing divisions today and is right now in the centre of a total worldwide update and change. With this quick development in costs, various moves must be made to guarantee the expenses of human services don't further leave control. Because of the enormous measure of information development in biomedical and human services field the requirement for giving precise examination of medicinal information that has advantages like prime location, persistent consideration and network administrations. Statistical data display the lethalness of cardiovascular or heart diseases by revealing the percentage of deaths worldwide caused due to heart attacks. In this paper, we will be designing a model which will take already existing medical data from a hospital and medical communities to develop and improve the system for an estimate the possibility of a patient being diagnosed with heart disease. The proposed model takes the factors which affect the health of a person, thus providing accurate results as the occurrence of a heart disease considering all possibilities.
We show an accuracy level of 90% through the prediction model for heart disease with the Naïve Bayes classifier.