Spatiotemporal patterns of climate-sensitive vector-borne diseases in Bangladesh: leveraging machine learning and spatial regression for intervention strategies

Bangladesh has a noticeable rise in vector-borne diseases (VBD) attributed to climate change. Accurately mapping, predicting, and identifying the risk factors of VBD is essential for prevention and control strategies. Therefore, this study aimed to investigate the spatiotemporal pattern and associated meteorological factors of VBD in Bangladesh. This study used district-level reported cases of VBD (dengue, chikungunya, malaria, filariasis, and yellow fever) obtained from the Bangladesh Bureau of Statistics. Simultaneously, meteorological data (temperature, relative humidity, wind speed, and precipitation) were sourced from NASA from 2017 to 2020. A combination of exploratory spatial analysis, spatial regression, and advanced tree-based machine learning models was utilized for prediction, risk factor identification, and correlation analysis. Dengue was the most prevalent vector-borne disease during the study period, peaking in 2019, while malaria and filariasis showed variable incidence across districts. Dhaka, Pirojpur, Jessore, Bandarban, Rangamati, and Narail districts exhibited higher incidence rates of VBD. The spatial regression model identified mean temperature as a major risk factor for VBD (β = 16.64, s.e. = 6.39). Additionally, the optimal XGBoost model also highlighted mean temperature as the primary determinant, alongside other climatic and socioeconomic factors such as GDP, population size, and healthcare infrastructure, underscoring the complex interplay between health infrastructure and socioeconomic drivers for Bangladesh’s VBD from 2017 to 2020. The study’s findings, incorporating the One Health perspective, provide insights for planning early-warning, prevention, and control strategies using machine learning to combat infectious diseases in Bangladesh and similar endemic countries. Precautionary measures and intensified surveillance must be implemented in certain high-risk districts nationwide.