Machine Learning-Based Prediction of Dengue Infection Using Clinical and Hematological Data from Bangladesh: A Comparative Analysis of Benchmark and Extended Prediction Models
The study compared three machine learning models (Logistic Regression, Random Forest, XGBoost) to predict dengue using clinical and blood test data from two Bangladeshi hospital datasets (2024 and 2025). It found that while performance varied by year, Platelet Count was the most important predictor. Adding specific morphology predictors improved results in 2024, suggesting ML can aid early diagnosis but highlights data quality issues between years.