Identification of Cardiovascular Disease using Machine Learning and Ensemble Learning

Cardiovascular disease is a very dangerous disease among humans and can be fatal. It describes a condition where blood arteries get constricted or clogged, which can cause a heart attack, chest symptoms, or a stroke. One of the significant challenges faced in research is accurately diagnosing heart disease using health data. Existing techniques have poor performance, potential to bias and limited interpretability. In the proposed study, a system has been developed to identify the presence of cardiovascular disease in a person by applying machine learning algorithms to a heart disease dataset containing information about clinical parameters. The model algorithms used are Random Forest, k Nearest Neighbours, Decision Trees, Logistic Regression, Naive Bayes and Ensemble Learning. For comparison, Principal Component Analysis has been applied for dimensionality reduction on the dataset and then the classification algorithms are applied and the results are compared based on various model performance metrics. The authors of this paper aim to propose system can identify the presence of cardiovascular disease among people efficiently and accurately in a way that is easy to use for all.