Cardiovascular diseases (CVDs) remain the leading cause of mortality globally, contributing to approximately 18 million deaths every year, according to the World Health Organization (WHO). Despite advancements in healthcare technologies, the early diagnosis and accurate prediction of heart diseases continue to pose significant challenges due to the multifactorial nature and complexity of the disease. Traditional diagnostic methods such as clinical assessments, invasive procedures, and physician expertise are often limited by resource constraints, especially in underdeveloped regions. With the rise of artificial intelligence and machine learning in healthcare, data-driven models have shown great potential to assist in the early detection of heart disease by analyzing clinical and physiological data. Machine learning models, especially classification algorithms, can uncover complex patterns within medical datasets that traditional statistical methods might miss. This motivates the development of robust and intelligent predictive systems capable of supporting healthcare professionals in clinical decision-making.

In this study, an automated system for cardiovascular disease classification is proposed, leveraging Support Vector Machine (SVM) as the primary classifier. To enhance the feature selection process and improve the prediction accuracy, the Artificial Flora Algorithm (AFA) is utilized. AFA is a powerful optimization technique inspired by the natural propagation behavior of plants, which enables the selection of the most relevant features from patient data, reducing noise and improving model efficiency. Further improvements are achieved through the incorporation of ensemble methods such as the Stacking Classifier, Adaboost, combining Random Forest models tuned with Particle Swarm Optimization (PSO), to enhance robustness and generalization.

Keyword: Cardiovascular Disease Classification, Heart Disease Prediction, Artificial Flora Algorithm, Support Vector Machine, Feature Selection, Ensemble Learning, Random Forest, Particle Swarm Optimization, Stacking Classifier, Clinical Data Analysis.