Risk Factor Prediction of Heart Disease using Machine Learning Approaches

• Main Authors: Dkhil, Mejdi Ben, Rabbouch, Bochra, Saadaoui, Foued
• Format: Conference Proceeding
• Language: English
• Subjects: ElasticNet; heart dataset; Heart diseases; KNN; machine learning algorithms; Random Forest; risk prediction; SVR; XG Boost
• ISSN: 2642-3596
• DOI: 10.1109/CW58918.2023.00053

Heart disease is a widespread condition that impacts a significant number of individuals and continues to be the leading cause of death globally. It encompasses a range of conditions that affect the heart. There are numerous risk factors associated with heart disease, making it crucial to develop accurate, reliable, and practical methods for early diagnosis and effective management. Artificial intelligence techniques and machine learning algorithms have become widely used in healthcare and offer a means to process vast amounts of medical data. Researchers employ those techniques to analyze complex medical data, assisting healthcare professionals in predicting the likelihood of heart disease. In this research paper, regression techniques are investigated to predict risk factors of heart disease by focusing on different attributes related to this disease. For this aim we pretrained some machine learning approaches such as ElasticNet, K-Nearest Neighbor, XG Boost, Support Vector Regression and Random Forest. The study utilizes an existing dataset from the American Centers for Disease Control and Prevention that contains 319795 lignes and 18 attributes. The objective of this research paper is to estimate risk factors encountred on developing heart disease in patients in order to delay this disease as much as possible.