<![CDATA[Dengue Hemorrhagic Fever (DHF) is an infectious disease caused by the dengue virus and transmitted through the bite of the Aedes aegypti mosquito. This disease remains a serious health problem in Indonesia because it can cause severe complications and even death if not treated immediately. This study aims to classify the severity of DHF based on patient clinical data using three machine learning algorithms, namely Random Forest, XGBoost, and Support Vector Machine (SVM). The dataset used consists of 5,000 patient data that includes various vital parameters and laboratory test results such as age, gender, hemoglobin level, white blood cell count (WBC), leukocyte count (Differential Count), red blood cell parameters (RBC Panel), platelet count, and Platelet Distribution Width (PDW). The research stages include data cleaning, handling missing values, coding categorical variables, data normalization, and dividing the dataset into 80% training data and 20% test data. Evaluation is carried out using accuracy, precision, sensitivity (recall), and F1 score metrics. The results showed that the XGBoost algorithm performed best with an accuracy of 87.72%, followed by Random Forest (86.21%) and SVM (84.78%). Based on these findings, XGBoost was deemed most effective in classifying dengue fever. Further research is recommended to use a larger dataset and perform hyperparameter optimization to improve the accuracy and reliability of the resulting model.]]>
Copyrights © 2025
