Meta-Learning Based Classification Model for Cardiovascular Disease

Abstract

Cardiovascular disease is a major global health concern and is the leading cause of death and disability worldwide. According to the World Health Organization, cardiovascular disease is responsible for 17.9 million deaths each year, which accounts for 31% of all global deaths. Heart disease is a major cause of mortality worldwide. Machine learning algorithms have shown promise in predicting the risk of heart attacks. Meta-learning is a type of machine-learning method which enables a system to learn how to learn. It involves a set of techniques that allow a system to improve its own learning process. In this paper, we propose a Meta-learning based classification model for Cardiovascular diseases. We consider the dataset (for heart attack classification), which contains 76 attributes with the predicted attribute being the presence of heart disease. We evaluate traditional classification models and Meta-Learning approach for heart attack classification. Additionally, we compared the results using SMOTE and without SMOTE to balance the target classes. The Meta-learning approach outperforms traditional models, providing a more accurate prediction of heart attack risk. These results suggest that the meta-learning approach can be used to improve accuracy.