<![CDATA[Stroke is one of the leading causes of death and disability worldwide. Early detection of the risk of stroke is crucial to reducing its impact and improving the effectiveness of treatment. This study aims to predict the probability of a person being at risk of stroke using the C4.5 Algorithm, known as a decision tree-based method. The dataset used includes variables such as age, blood pressure, blood sugar levels, medical history, smoking habits, and physical activity. After data preprocessing, including handling missing data and normalization, a predictive model was built using the C4.5 Algorithm. The results show that the model achieved an accuracy of 95.01%, a precision of 33.33%, a recall of 2.04%, and an F1-score of 3.81%. Additionally, the Negative Predictive Value (NPV) of 95.10% and specificity of 99.79% demonstrate the model's ability to detect risks effectively in negative cases. The model also generates decision rules that are easily interpretable by medical professionals, making it a potential tool to support medical decision-making in the early identification of stroke risks.]]>
Copyrights © 2025
