<![CDATA[Objective: Cardiovascular diseases (CVDs) continue to be a primary cause of early death globally, with both their prevalence and the costs associated with healthcare consistently increasing. Epidemiological Researches has pinpointed a range of risk factors, including high cholesterol levels, elevated blood pressure, diabetes, obesity, smoking, and lack of physical activity, which together account for more than 90% of the risk linked to CVDs. The integration of artificial intelligence (AI) into healthcare has revolutionized medical diagnosis and treatment, particularly in the field of cardiology. Natural Language Processing (NLP) algorithms further enhance this by converting unstructured clinical notes into structured data, thus supporting clinical decision-making processes. This study explores the implementation of both traditional machine learning methods—such as Decision Trees (DT), Multilayer Perceptron (MLP)and advanced deep learning techniques in conjunction with NLP to diagnose heart conditions requiring catheter intervention. Method: This study explores the implementation of both traditional machine learning methods—such as Decision Trees (DT), Multilayer Perceptron (MLP)and advanced deep learning techniques in conjunction with NLP to diagnose heart conditions requiring catheter intervention. Results: Our findings suggest that the hybrid model employing deep learning methods outperforms traditional models, demonstrating the potential of AI in advancing cardiovascular healthcare. Novelty: Our findings suggest that the hybrid model employing deep learning methods outperforms traditional models, demonstrating the potential of AI in advancing cardiovascular healthcare.]]>
