Cardiovascular Disease Prediction Using Machine Learning Approaches

Abstract

Cardiovascular disease is a prominent con tributor to global mortality. The timely identification and  prognostication of cardiovascular disease can mitigate its  incidence and diminish fatality ratios. The use of machine  learning has emerged as a promising methodology for fore casting the likelihood of heart disease. The present study  delves into the application of machine learning algorithms in  the prediction of heart disease. In this study, a publicly ac cessible dataset on heart disease is utilized to assess the effi cacy of various machine learning algorithms and determine  the optimal models. The study involves a comparative analy sis of various algorithms, namely Logistic Regression, Ran dom Forest, Support Vector Machines, and Artificial Neural  Networks, with respect to their accuracy and other perfor mance metrics. The findings indicate that the Artificial Neu ral Network model yielded the highest level of performance,  exhibiting an accuracy rate of 87.5%. The aforementioned  showcases the prospective employment of machine learning  in the domain of heart disease prognosis, thereby highlight ing the exigency for additional inquiry in this field.