Real-time smart system for heart disease prediction

Abstract

Heart diseases are one of the leading causes of death worldwide. Despite this, predicting these diseases remains challenging for doctors due to their complexity and the high associated costs. This is why, in recent years, many researchers have turned to modern technologies such as artificial intelligence and machine learning to anticipate these diseases before they occur. The objectif of this study is to propose a real-time smart system for predicting heart diseases using supervised learning algorithms and the data available in the UCI Cleveland database. Algorithms such as Support Vector Machines (SVM), Random Forest (RF), Decision Tree (DT), and k-Nearest Neighbors (k-NN) are employed. Subsequently, we identified the algorithm that showed the highest accuracy rate and selected the most important features using the genetic algorithm to improve performance and reduce the detrimental effects of irrelevant and redundant features.