Home > Published Issues > 2022 > Volume 13, No. 1, February 2022 >

An Optimized Neural Network Using Genetic Algorithm for Cardiovascular Disease Prediction

Jan Carlo T. Arroyo 1 and Allemar Jhone P. Delima 2
1. College of Computing Education, University of Mindanao, Davao City, Philippines
2. Graduate School, Cebu Technological University-Barili Campus, Cagay, Barili, Cebu, Philippines

Abstract—Cardiovascular disease prediction has gained the spotlight in research for the past years. Data-driven techniques for prediction through machine learning techniques have paved the way for an increased prediction accuracy in detecting the disease to people. In this paper, the cardiovascular disease dataset comprising 70,000 instances with 12 variables was used for training and testing using Artificial Neural Networks (ANN). However, the drawback of ANN when determining layers and neurons to be used persist. This paper aims to optimize the performance of ANN, leading to an increase in prediction accuracy. To realize, the use of the Genetic Algorithm (GA) was observed. Simulation results revealed that the use of GA had improved the performance of ANN by 5.08 percentage points against the prediction accuracy of the lone ANN. Further, the GA-ANN prediction model outperformed the other machine learning algorithms in the prediction of cardiovascular disease.
 
Index Terms—artificial neural network, cardiovascular disease prediction, genetic algorithm, hybrid algorithm, parameter tuning

Cite: Jan Carlo T. Arroyo and Allemar Jhone P. Delima, "An Optimized Neural Network Using Genetic Algorithm for Cardiovascular Disease Prediction," Journal of Advances in Information Technology, Vol. 13, No. 1, pp. 95-99, February 2022. doi: 10.12720/jait.13.1.95-99

Copyright © 2022 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.