Exploring the Potential of Analytical Models in Heart Disease Prediction

  • Hanan Saleh Al-Messabi
  • Fatma Mohamed Al-Ali
  • Feras Al-Obeidat

Abstract

In 2021, the annual death toll due to various heart diseases reached a staggering 18 million individuals. This excessive mortality rate has become a pressing concern for scientists and medical professionals alike. Fortunately, the emergence of artificial intelligence has provided a valuable tool for decision-makers to tackle the challenges posed by heart disease. Consequently, numerous algorithms have been proposed to develop diverse models tailored to specific applications. By utilizing different analytical models, including logistic regression, decision trees, random forests, neural networks, and deep learning models, it has been determined that the logistic regression model achieves the highest and most favorable metric scores. With an impressive accuracy rate of 83%, a precision rate of 88%, and a recall rate of 86%, this model proves to be the most effective in predicting heart disease. Therefore, this study will significantly contribute to the advancement of healthcare practices by harnessing the power of big data and advanced analytical models. These insights will provide valuable guidance in addressing critical health issues in society in the future.
Published
May 10, 2024
How to Cite
AL-MESSABI, Hanan Saleh; AL-ALI, Fatma Mohamed; AL-OBEIDAT, Feras. Exploring the Potential of Analytical Models in Heart Disease Prediction. International Journal of Information Science and Technology, [S.l.], v. 8, n. 1, p. 17 - 34, may 2024. ISSN 2550-5114. Available at: <https://innove.org/ijist/index.php/ijist/article/view/254>. Date accessed: 29 may 2024. doi: http://dx.doi.org/10.57675/IMIST.PRSM/ijist-v8i1.254.
Section
Articles