Predicting Heart Disease Using Machine Learning in Healthcare Based on Several Data Sources

In this paper, cardiovascular illnesses have been the leading cause of mortality across all socioeconomic groups in the globe over the last few decades. The mortality rate from heart disorders may be lowered with early identification and close clinical monitoring. However, it is not feasible to precisely monitor patients every day, and 24-hour medical consultation is not accessible due to the increased sagacity, time, and experience required. For this project, we used Machine Learning methods such as backward elimination algorithm, logistic regression, and REFCV to analyse a publicly available dataset on the Kaggle website in order to predict the onset of heart disease in patients. The results were evaluated by means of a confusion matrix and cross validation. It would be a huge step forward in medicine if doctors could accurately predict the course of cardiovascular disease in order to let high-risk patients make choices about lifestyle adjustments that would lower the likelihood of serious problems.