Abstract:
This study focuses on the application of machine learning methods for predicting cardiac
diseases, aiming to develop accurate and interpretable diagnostic models. The primary objective is to
enhance prediction accuracy and identify key risk factors. Various classification algorithms, including
Random Forest, Gradient Boosting, Support Vector Machines (SVM), and Neural Networks, are
utilized. A dataset containing clinical attributes of patients is processed and analyzed to build
predictive models. The model performance is evaluated using accuracy metrics, confusion matrices,
and ROC-AUC scores. The results indicate that the Random Forest algorithm achieves the highest
predictive accuracy. Furthermore, feature importance analysis highlights the most significant factors
contributing to the development of cardiac diseases. This research provides valuable insights for
medical professionals and researchers, offering effective tools for early disease detection.
