Exploring the Path: Machine Learning Approaches to Cardiovascular Risk Assessment

Cardiovascular disease, refers to a variety of circumstances affecting the cardiovascular and blood vessels, such as cardiovascular failure and coronary artery illness. Cardiovascular disease, a major global health concern, is frequently caused by atherosclerosis, a condition in which plaque builds up and obstructs blood flow. This study introduces a predictive modeling methodology utilizing various machine learning (ML) algorithms. Additionally, hybrid models including Random Forest-Gradient Boosting, Genetic Algorithm-Support Vector Machine (GA-SVM), AdaBoostSupport Vector Machine (AdaBoost-SVM), Logistic Regression-Principal Component Analysis (LR-PCA), and Gradient Boosting Machines-Decision Tree (GBMDT) have been integrated into the analysis. Using two distinct datasets, our study focuses on proactive heart disease management, addressing a significant health challenge. Notably, the Random Forest-Gradient Boosting Machines (RF-GBM) hybrid model exhibited exceptional performance, achieving an impressive 93.5% accuracy for both datasets in predicting heart disease. These results highlight the effectiveness of our integrated approach in advancing predictive modeling for improved cardiovascular health management.