<![CDATA[Stroke is a non-communicable disease and one of the leading causes of death and long-term disability worldwide, making early detection essential through intelligent computational systems that can assist healthcare professionals in clinical decision-making. The main challenge addressed in this study is the complexity of multifactorial stroke risk factors and the imbalance of medical record datasets, which may affect the performance of classification models. This study implements the Gaussian Naive Bayes algorithm as the classification method, supported by comprehensive data preprocessing stages, including mean value imputation for missing data, label encoding to transform categorical variables into numerical values, Min-Max Scaling normalization, and classification modeling using RapidMiner. The objective of this research is to accurately predict the level of stroke risk based on patients' medical records in order to support clinical decision support systems for preventive healthcare and early intervention. The experimental results demonstrate that the proposed model achieved an overall accuracy of 90.70%, a precision of 72.08%, a recall of 78.89%, and an F1-score of 75.33%. Furthermore, the model successfully classified posterior probabilities into hierarchical risk categories, providing more interpretable information for identifying high-risk patients and supporting more effective and efficient clinical decision-making processes in preventive stroke management.]]>
Copyrights © 2026
