International Journal of Electrical and Computer Engineering (IJECE) Vol. 12, No. 2, April 2022, pp. 1831~1838 ISSN: 2088-8708, DOI: 10.11591/ijece.v12i2.pp1831-1838  1831 Journal homepage: http://ijece.iaescore.com A hybrid approach to medical decision-making: diagnosis of heart disease with machine-learning model Tamilarasi Suresh 1 , Tsehay Admassu Assegie 2 , Subhashni Rajkumar 3 , Napa Komal Kumar 4 1 Department of Information Technology, St. Peter’s Institute of Higher Education and Research, Chennai, India 2 Department of Computer Science, College of Natural and Computational Science, Injibara University, Injibara, Ethiopia 3 Department of Computer Science and Applications, St. Peter’s Institut e of Higher Education and Research, Chennai, India 4 Department of Computer Science and Engineering, St. Peter’s Institute of Higher Education and Research, Chennai, India Article Info ABSTRACT Article history: Received Mar 16, 2021 Revised Sep 10, 2021 Accepted Oct 4, 2021 Heart disease is one of the most widely spreading and deadliest diseases across the world. In this study, we have proposed hybrid model for heart disease prediction by employing random forest and support vector machine. With random forest, iterative feature elimination is carried out to select heart disease features that improves predictive outcome of support vector machine for heart disease prediction. Experiment is conducted on the proposed model using test set and the experimental result evidently appears to prove that the performance of the proposed hybrid model is better as compared to an individual random forest and support vector machine. Overall, we have developed more accurate and computationally efficient model for heart disease prediction with accuracy of 98.3%. Moreover, experiment is conducted to analyze the effect of regularization parameter (C) and gamma on the performance of support vector machine. The experimental result evidently reveals that support vector machine is very sensitive to C and gamma. Keywords: Heart disease Hybrid approach Medical decision making Random forest Support vector machine This is an open access article under the CC BY-SA license. Corresponding Author: Tsehay Admassu Assegie Department of Computer Science, Injibara University P.O.B, 40, Injibara, Amhara, Ethiopia Email: tsehayadmassu2006@gmail.com 1. INTRODUCTION In recent years, heart disease have become one of the foremost reason of chronic disease related deaths thought the world population [1]–[5]. Moreover, heart disease is among the most frequently occurring diseases in the world affecting 26 million of the world population [1], [2]. Heart disease cases are widely spreading and the number of cases of heart disease patient is annually growing at a rate of 2%. Thus, identification and diagnosis of heart disease is crucial to save human life and reduce the wide mortality rate caused by heart disease through automated intelligent model to assist medical practitioner on clinical decision making during the diagnosis of heart disease patient [3]. In addition, automated or intelligent model provides more accurate and timely result overcoming the problems caused due to human error [4]. Hence, in order for the survival chance of heart disease patient to be increased, an accurate and timely identification of heart disease through intelligent model is critical for better decision making when diagnosing heart disease patient. Heart disease prediction involves precise classification of a given sample as heart disease positive or heart disease negative class based on the symptoms or features of a given sample or instance. Many researchers have developed intelligent model with focus on improving the performance of heart disease prediction model and there exist model for heart disease prediction in literature. However, there is still larger scope for improving the performance of the existing model for heart disease prediction [5]. Thus, in this study an effort has been made in designing and implementing an effective and more accurate model that classifies a given sample in