Florentina Yuni Arini, Fathur Rahman Nur Saputra, Liafathra, Raditya Diyandra Rido Artama, Supailin Pichai
Heart disease is one of the leading causes of death worldwide, and accurate risk identification is essential for early intervention. This study explores the application of Support Vector Regression (SVR) optimized with Grey Wolf Optimization (GWO), namely SVR-GWO, predicting the risk of heart disease. SVR, as an effective machine learning algorithm, can model the relationships between various risk factors; however, its sensitivity to optimal parameter selection presents a challenge. To address this issue, GWO is employed as an optimization method, inspired by the efficient hunting behavior of grey wolves in exploring the search space and avoiding local solution traps. In this study, the process of optimizing SVR-GWO is evaluated and compared with other methods. Experimental results show that the SVR-GWO achieved an accuracy of 85.5%, indicating the potential of GWO to enhance predictive performance compared to previous approaches. Thus, this research presents a promising contribution to the development of more accurate and efficient heart disease prediction models, which can support early detection and better medical decision-making. © 2025 IEEE.
Department of Informatics Engineering, Faculty of Mathematics and Natural Sciences, Universitas Negeri Semarang, Semarang, Indonesia; Department of Applied Science, Faculty of Science and Technology, Loei Rajabhat University, Loei, Thailand
