<![CDATA[Dengue Hemorrhagic Fever (DHF) remains a significant public health problem in Indonesia, particularly in regions with environmental conditions that support the growth of Aedes aegypti mosquitoes. This study aims to implement the Naive Bayes algorithm to predict the distribution of DHF cases in the working area of Wates Public Health Center, Pringsewu Regency, Lampung. The research employs a quantitative approach using data mining techniques, including data collection, preprocessing, modeling, and evaluation stages. The dataset consists of 260 DHF cases in 204-2025 categorized into acute, subacute, and non-acute conditions. The results indicate that the Naive Bayes algorithm achieved an accuracy of 65.8%, with a recall value of 0.658 and an F1-score of 0.556. The analysis also shows that most cases fall into the acute category, and there is no significant relationship between gender and disease severity. Although the AUC and MCC values are relatively low, the model provides an initial insight into the distribution pattern of DHF. Therefore, the Naive Bayes algorithm can be utilized as a decision support system to determine priority areas for intervention and as an early warning system to improve the effectiveness of DHF control.]]>
Copyrights © 2026
