Utilizing Optimization Techniques in Feature Selection for Effective Cardiovascular Disease Prediction

Cardiovascular disease (CVD) is considered one of the significant global health challenges, affecting individuals and societies worldwide. This paper aims to address the challenge of predicting CVD by developing a prediction model based on optimal feature selection. The process begins with data preprocessing of the Z-Alizadeh Sani dataset. Three optimization algorithms were utilized: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Arithmetic Optimization Algorithm (AOA) to find the most important and relevant features to improve the heart disease prediction accuracy of some selected popular machine learning classifiers. Simulation results showed that the proposed work achieves 98.59 % of accuracy.