A Machine Learning Model for the Early Prediction of Cardiovascular Disease in Patients
Abhishek, Hutashan Vishal Bhagat, Manminder Singh
Abstract
Cardiovascular disease is a major health concern worldwide, with an estimated 17.9 million deaths each year. It encompasses a range of conditions affecting the heart and blood vessels, including coronary heart disease, stroke, and heart failure. These diseases are often associated with a range of modifiable and non-modifiable risk factors, including high blood pressure, high cholesterol, smoking, physical inactivity, obesity, diabetes, and genetic predisposition. Data analysis and machine learning have emerged as powerful tools for predicting and preventing cardiovascular disease. By analysing large and complex datasets of medical records, researchers can identify patterns and risk factors associated with cardiovascular disease. Machine learning models can help identify important features in the data that are predictive of heart disease outcomes, and can be used to develop accurate and reliable predictive models. Moreover, data analysis can help identify disparities and biases in cardiovascular disease outcomes across different populations and regions. This research aims to develop a machine-learning model for predicting cardiovascular disease risk using benchmark datasets. Various imputation techniques, including Mean, Median, Most Frequent, KNNI, and the proposed risk prediction model, are compared in terms of accuracy and efficiency. The CatBoost classification algorithm is used for developing the proposed model, achieving an accuracy of 91% for the Hungarian dataset. This research provides valuable insights into the use of machine learning and data analysis for predicting cardiovascular disease and improving healthcare outcomes.