An Efficient Prediction of Cardiovascular Diseases using Machine Learning Models

Cardiovascular diseases, including Heart Failure, ST-Elevation Myocardial Infarction (STEMI), and Pulmonary Embolism, are leading causes of morbidity and mortality worldwide. Early diagnosis and accurate prediction of mortality in these conditions are crucial for improved patient outcomes. The study used a machine learning approach using Gradient Boosting and XGBoost classifiers for efficient prediction of Cardiovascular diseases (Heart Failure, STEMI, and Pulmonary Embolism) and in-hospital mortality on a comprehensive dataset. The study achieved high accuracy (mean accuracy: in-hospital mortality – 0.968, Heart Failure – 0.816, STEMI – 0.868, Pulmonary Embolism – 0.985) and discrimination ability (mean AUC: in-hospital mortality – 0.987, Heart Failure – 0.884, STEMI – 0.833, Pulmonary Embolism – 0.807) over existing studies. Additionally, feature importance analysis identified key factors contributing to these diseases. These findings provide a reliable tool for risk assessment and early intervention in patients with cardiovascular diseases, with significant implications for clinical practice and improved patient outcomes.