Predictive modeling of cardiovascular disease using exercise-based electrocardiography

Cardiovascular disease is the leading cause of death globally, highlighting the need for research focused on early detection and risk management to enhance patient outcomes. This study investigated the association between eleven cardiovascular risk factors and the presence of heart disease, hypothesizing a significant relationship between these factors and heart disease. The goal of this study was to create a model that could predict cardiovascular disease outcomes using exercise-based electrocardiography. We hypothesized that there would be significant associations between various risk factors and the presence of heart disease. Specifically, we aimed to investigate the relationships between demographic factors (age and sex), clinical symptoms (chest pain type), and physiological measurements (resting blood pressure, cholesterol level, fasting blood sugar, resting ECG results, maximum heart rate achieved, exercise-induced angina, oldpeak, and ST slope) with the presence or absence of heart disease. This approach allowed us to examine predictors across different categories that may affect cardiovascular health. We identified seven significant predictors of heart disease presence from the initial eleven risk factors, utilizing non-parametric data and multivariate analysis. Our findings were compared with contemporary research to evaluate the changes in heart disease risk factors over time. The results indicate that advancements in imaging, three-dimensional electrocardiography during exercise, and automated reporting systems are improving the diagnostic capabilities of traditional exercise-based electrocardiography. This research contributes to the ongoing efforts to improve early detection of cardiovascular disease.