Published Paper Details:

Cardiovascular diseases (CVDs) are the foremost cause of death worldwide, covering conditions such as coronary artery disease, arrhythmias, heart failure, congenital defects, and stroke. Their development is influenced by risk factors including hypertension, diabetes, obesity, smoking, high cholesterol, sedentary lifestyle, and genetics. Traditional diagnostic tools like ECG, echocardiography, angiography, and stress testing remain common but are often costly, labor-intensive, and may not detect disease at early stages. Advances in artificial intelligence have introduced machine learning and deep learning methods as efficient alternatives for disease prediction. These models are capable of handling diverse datasets, ranging from clinical records to medical images, and can identify patterns that aid in accurate and timely diagnosis. This paper reviews CVD types, major risk factors, diagnostic methods, and previously applied ML and DL approaches, highlighting their strengths, limitations, and challenges such as data imbalance, lack of interpretability, and limited generalizability. Future research directions emphasize multi-modal data fusion, explainable AI frameworks, and improved neural network designs to build robust and clinically reliable diagnostic tools for cardiovascular diseases.