<![CDATA[Heart disease is one of the leading causes of death in Indonesia and often develops without clear early symptoms, making early detection difficult. This study aims to predict the risk of heart attacks using the C4.5 algorithm based on RapidMiner by utilizing Indonesian public health data. The research method applies a data mining approach using the CRISP-DM framework, which includes business understanding, data understanding, data preparation, modeling, and evaluation stages. The dataset was obtained from Kaggle, consisting of 158,355 records and 28 attributes. Data preparation involved removing redundant attributes, data transformation and encoding, and dataset balancing. The evaluation results show that the C4.5 model achieved an accuracy of 90.89% with a recall value of 95.07% for the heart attack class. These results indicate that the C4.5 algorithm is effective in detecting individuals at risk of heart attacks and can be used as a basis for developing decision support systems in the healthcare sector.]]>
Copyrights © 2026
