Related Experiment Video
Updated: Apr 24, 2026
04:23
A Murine Model of Dengue Virus-induced Acute Viral Encephalitis-like Disease
Published on: April 28, 2019
6.4K
Data-Driven Machine Learning-Based Forecasting of Dengue in Bangladesh: Supporting Digital Health Approaches for
1Department of Statistics Begum Rokeya University Rangpur Bangladesh.
Health Science Reports
|April 23, 2026
Summary
Forecasting dengue cases in Bangladesh using machine learning shows a potential rise in future outbreaks. Digital health tools and enhanced surveillance are crucial for early warning systems and effective disease management.
Area of Science:
- Epidemiology
- Public Health
- Digital Health
Background:
- Dengue poses a significant public health challenge in Bangladesh.
- Effective surveillance and prevention are crucial for managing dengue.
- Digital health tools are increasingly important for disease monitoring.
Purpose of the Study:
- To model dengue case trends in Bangladesh.
- To forecast dengue cases for the next five years.
- To identify the optimal model for dengue prediction to support digital health early warnings.
Main Methods:
- Utilized monthly dengue case data from January 2000 to December 2023.
- Employed Autoregressive Integrated Moving Average (ARIMA) and eXtreme Gradient Boosting (XGBoost) models.
- Evaluated model performance using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Scaled Error (MASE).
Main Results:
- Bangladesh reported 565,890 dengue cases between 2000-2023, with a sharp peak in 2023.
- XGBoost demonstrated superior performance over ARIMA in predicting dengue cases.
- Recent dengue incidence (lag 1) was the most significant predictor, alongside seasonal patterns.
Conclusions:
- Findings highlight the need for robust early warning systems and digital health integration.
- Machine learning models can enhance predictive accuracy for dengue.
- Future research should incorporate climate and urbanization data for refined dengue projections.
