<![CDATA[Cardiovascular diseases (CVDs) remain a significant global health concern, necessitating effective preventive measures and early diagnosis to reduce mortality rates. Leveraging machine learning models to identify risk factors holds great promise, especially in cardiology. This study introduces a robust methodology for prognosing cardiac illnesses based on patient-specific factors. By integrating five publicly available datasets from the UCI Repository and employing Feature Importance techniques for optimal risk factor selection, the proposed approach enhances prediction accuracy. Furthermore, the inclusion of the density-based spatial clustering of applications with noise (DBSCAN) algorithm assists in noise detection and removal, thereby improving model precision. The proposed Cardio MetaStack model, coupled with a stacking classifier ensemble, achieved an accuracy of 94.91%, surpassing that of traditional algorithms such as XGBoost 90.45%, demonstrating its efficacy in heart disease prediction.]]>
Copyrights © 2025
