<![CDATA[Heart disease is a serious health issue that leads to high mortality risk worldwide. Contributing factors include high cholesterol, diabetes, and high blood pressure. Therefore, early prediction of heart disease is a crucial initial step to reduce mortality risk. This paper proposes a new heart disease classification model based on the Support Vector Machine (SVM) algorithm to enhance disease detection performance. To improve diagnostic accuracy, we apply feature selection techniques and grid search. The performance of the enhanced model is validated by comparing it with a simple model using a confusion matrix. The enhanced model achieves an accuracy of 96.56%, showing an improvement of 8.91% over the previous model, which had an accuracy rate of only 87.65%. Additionally, the number of features used is reduced from 14 to 8, decreasing the computational load from 100% to about 32%. These results indicate that the enhanced SVM provides better and more efficient performance compared to other methods in heart disease classification]]>
Copyrights © 2024
