Heart Disease Prediction Support System using Machine Learning Approaches
- Author Alpha Alimamy Kamara
- Co-Author Abdul Joseph Fofanah
- DOI http://wwj
- Country : Sierra Leone
- Subject :
Keywords : Cardiovascular Disease, Decision Tree, Machine Learning, Random Forest, Neural Network, XGBoost, Heart Disease
Abstract
Heart disease (cardiovascular disease) is a common source of death in the world and a major health threat. According to WHO research, a cardiovascular disease caused 17.9 million deaths worldwide in 2017. Unfortunately, the mortality and morbidity of cardiovascular disease (heart disease) are increasing year by year, especially in developing countries. According to reports, almost 80% of heat-related deaths occur in middle-income and low-income countries. In addition, in low-income countries, the age of these deaths is younger than in high-income countries. The poor economic transition in developing countries has led to environmental changes and unhealthy lifestyles; in addition, the aging of the population may increase the risk factors of cardiovascular disease and the incidence of cardiovascular disease (heart disease). The patients and the whole society were hit hard by heart disease. Therefore, strategies for improving the diagnosis and treatment of heart disease are needed in the future.
Machine learning may now solve this problem. This study used four different machine learning algorithms to develop and implement a predictive model for heart (cardiovascular) disease detection. The findings of this study show that all developed models, including random forests, decision trees, neural networks, and XGBoost, have high classification accuracy and are similar in predicting heart disease cases. However, the comparison based on the true positive rate shows that the random forest model performs slightly better in predicting heart disease, with a classification accuracy rate of 94.96 %.
Comments
No have any comment !