Data-Driven Approach for Identifying Hidden Cardiac Risks through Multivariate Clinical Analysis

Heart disease is among the leading causes of death globally, impacting millions due to modern lifestyle challenges such as unhealthy diets, lack of physical activity, and chronic stress. This widespread condition necessitates accurate and early diagnosis. There are two main diagnostic pathways: invasive techniques like coronary angiography, and non-invasive methods utilizing physiological data, clinical symptoms, and imaging. This paper presents three machine learning (ML) frameworks tailored to each data category. The first uses basic clinical parameters and prioritizes feature selection, while the other two employ advanced signal and image processing techniques. By integrating supervised ML algorithms, this study highlights how large hospital datasets can facilitate early identification of cardiovascular risks, ultimately supporting healthcare professionals in timely interventions.