Summary
Diagnosing dengue early is hard because its symptoms are like other illnesses. The authors use machine learning models to analyze patient symptoms and blood test data from hospitals in Bangladesh to guess who has dengue. They tested different models and found adding more blood test details helped prediction in one year’s data. However, the models worked much better on the following year's data, perhaps due to better data quality. The authors say more tests with other data sets are needed to confirm the findings.
What this means in practice
- •For hospital data teams: Use machine learning models enhanced with blood parameter RDW-CV to better predict dengue from clinical and lab data in Bangladesh hospital settings.
- •For public health monitoring teams: Integrate machine learning predictions from routine blood tests to improve early dengue case identification in areas with similar symptoms from other illnesses.
Abstract
Dengue is a viral infection caused by the dengue virus (DENV) and a major public health concern in Bangladesh, where symptom overlap with other febrile illnesses complicates early diagnosis. This study compares Logistic Regression, Random Forest and XGBoost to predict dengue from clinical and hematological data using two Bangladeshi hospital datasets (2024, n=1,511; 2025, n=1,283) with SMOTE. Extended models outperformed benchmarks within 2024 (Random Forest ROC-AUC 0.640 to 0.661), with RDW-CV the most consistently influential added predictor. 2025 benchmark performance was higher (ROC-AUC 0.904), unexplained by class imbalance and possibly reflecting data quality. External validation is needed.