Accurate Detection of Heart Disease Using the CardioFusion Ensemble Algorithm

The purpose of this study is to use Artificial Intelligence approaches to create an effective and precise diagnostic tool to detect heart disease problem. Heart disease is one of the leading causes of death worldwide. We compared AI techniques to diagnose heart disease, such as Deep Learning, Multi-layer Perceptron, Random Forest, Decision Tree, Gradient Boosting, Radial SVM, Linear SVM, AdaBoost, Linear SVM, Logistic Regression, and K-Nearest Neighbor. By identifying important predictors feature selection techniques like sigmoid and Rectified Linear Unit, were used to improve model accuracy. Our algorithm showed better accuracy, sensitivity, and specificity: mostly, Random Forest classifiers superior performance metrics is evidenced by their 98% accuracy rate. This underscores the significance of incorporating these technologies into healthcare systems to improve patient outcomes and lower the prevalence of heart disease. Our research shows the MLP-GA algorithm can increase diagnostic accuracy.