Identifying the early signs of cardiovascular disease remains a significant challenge for medical professionals. Each year, millions of deaths are attributed to heart-related conditions, highlighting the need for prompt diagnosis and intervention. The complexity of diagnosing heart disease arises from the interplay of several health factors, including hypertension, high cholesterol, and abnormal heart rhythms. In this scenario, artificial intelligence (AI) emerges as a critical tool to assist with early detection and management. This study introduces an ensemble-driven methodology that integrates machine learning (ML) and deep learning (DL) models to estimate an individual's risk of heart disease. Six different classification techniques are utilized for prediction, and a publicly accessible cardiovascular dataset is employed for training. Furthermore, Random Forest (RF) is used to determine the most influential features related to cardiovascular health.