<![CDATA[Dengue fever remains a pressing public health issue, especially in tropical and subtropical regions where urbanization, climate change, and ineffective vector control contribute to frequent outbreaks. Traditional surveillance methods often fall short in providing timely and accurate insights, necessitating data-driven approaches for improved monitoring and intervention. This review explores various computational methodologies, including Geographic Information Systems (GIS), machine learning, and predictive modeling, to enhance dengue outbreak mapping and risk assessment. Studies from Bangladesh, Thailand, Malaysia, and Reunion Island demonstrate how integrating epidemiological data with environmental and socio-economic factors improves outbreak prediction and control efforts. Advanced techniques, such as dynamic mapping of the basic reproduction number (R0) and deep learning models like Long Short-Term Memory (LSTM) networks, further enhance forecasting accuracy. Additionally, innovative control strategies, such as Wolbachia-infected mosquito releases, show promise in reducing dengue transmission. By synthesizing recent research, this review underscores the critical role of data science in strengthening dengue surveillance, prediction, and intervention strategies.]]>
Copyrights © 2025
