Early Prediction of Coronary Artery Disease (CAD) by Machine Learning Method - A Comparative Study

Abstract

Coronary Artery Disease (CAD) prediction is a very hard and challenging task in the medical field. The early prediction in the medical field especially the cardiovascular sector is one of the virtuosi. The prior studies about the construction of the early prediction model developed an understanding of the recent techniques to find the variation in medical imaging. The prevention of cardiovascular can be fulfilled through a diet chart prepared by the concerned physician after early prediction. Our research paper consists of the prediction of CAD by the proposed algorithm by constructing of pooled area curve (PUC) in the machine learning method. This knowledge-based identification is an important factor for accurate prediction. This significant approach provides a good impact to determine variation in medical images although weak pixels surrounding it. This pooled area construction in our machine learning algorithm is bagging shrinking veins and tissues with the help of clogging and plaque of blood vessels. Besides, the noisy type database is used in this article for better clarity about identifying the classifier. This research article provides the recent adaptive image-based classification techniques and it comparing existing classification methods to predict CAD earlier for a higher accurate value. This proposed method is taking as evidence to diagnosis any heart disease earlier. The decision-making of classified output provides better accurate results in our proposed algorithm.