{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T23:08:04Z","timestamp":1793747284532,"version":"4.6.1"},"reference-count":60,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T00:00:00Z","timestamp":1772668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["TropicalMed"],"abstract":"<jats:p>Dengue is a mosquito-borne viral disease which is predominantly endemic in tropical and subtropical countries. In Bangladesh, 321,179 dengue cases were reported in 2023, followed by 101,214 cases in 2024, which highlights a severe and ongoing public health challenge. Dengue transmission risks are shaped by climatic variability, rapid urbanization, socio-economic vulnerability, and healthcare strain. But existing dengue surveillance models remain limited in their ability to capture district-level disparities in Bangladesh. This study aimed to develop a district-level dengue early warning system that integrates climatic, socio-demographic, economic, healthcare, and environmental determinants to generate accurate and interpretable predictions. We examined dengue cases across all 64 districts in Bangladesh from 2017 to 2024, integrating Directorate General of Health Services (DGHS) case records with climate, socio-demographic, economic, and healthcare indicators. Machine learning and deep learning approaches, including Multi-Layer Perceptron (MLP) and Convolutional Long Short-Term Memory (ConvLSTM), were combined with SHAP (Shapley Additive Explanations)-based explainable artificial intelligence. We also used Bayesian spatio-temporal models to capture spatial clustering, temporal dependence, and the lagged transmission effects of dengue. Dengue outbreaks peaked in September 2023, with Dhaka recording 113,233 cases. DENV-4 (Dengue Virus type 4) emerged in 2022, accounting for 27% of infections in 2023. Climate was the strongest predictor of dengue transmission (humidity SHAP = 0.314; minimum temperature SHAP = 0.146; rainfall RR = 1.303). Poverty (SHAP = 0.193) and healthcare capacity (nursing\/midwifery density SHAP = 0.073) mostly contributed to dengue prediction. The MLP model achieved the best yearly performance (accuracy = 0.93; ROC-AUC = 0.99), ConvLSTM was the best model in monthly prediction (recall = 0.88; ROC-AUC = 0.81), and Bayesian BYM2_RW2 with lagged effects improved predictive fit (DIC = 3671.055). Our integrated framework delivers transparent, interpretable predictions and district-level early warnings, supporting adaptive dengue outbreak preparedness and resource allocation in Bangladesh.<\/jats:p>","DOI":"10.3390\/tropicalmed11030073","type":"journal-article","created":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:29:53Z","timestamp":1772724593000},"page":"73","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["District-Level Dengue Early Warning Prediction System in Bangladesh Using Hybrid Explainable AI and Bayesian Deep Learning"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0424-446X","authenticated-orcid":false,"given":"Md. Abu Bokkor","family":"Shiddik","sequence":"first","affiliation":[{"name":"Department of Statistics, Begum Rokeya University, Rangpur 5404, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farzana Zannat","family":"Toshi","sequence":"additional","affiliation":[{"name":"Department of Statistics, Begum Rokeya University, Rangpur 5404, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sadia","family":"Yesmin","sequence":"additional","affiliation":[{"name":"Department of Statistics, Begum Rokeya University, Rangpur 5404, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8925-6544","authenticated-orcid":false,"given":"Md. Siddikur","family":"Rahman","sequence":"additional","affiliation":[{"name":"Department of Statistics, Begum Rokeya University, Rangpur 5404, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"100555","DOI":"10.1016\/j.onehlt.2023.100555","article-title":"Aedes aegypti and Aedes albopictus (Diptera: Culicidae) ecology, biology, behaviour, and implications on arbovirus transmission in Thailand: Review","volume":"16","author":"Ahebwa","year":"2023","journal-title":"One Health"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1016\/S0140-6736(24)01542-3","article-title":"Dengue: The threat to health now and in the future","volume":"404","author":"Lancet","year":"2024","journal-title":"Lancet"},{"key":"ref_3","unstructured":"WHO (2025, November 25). Dengue\u2014Bangladesh. Available online: https:\/\/www.who.int\/emergencies\/disease-outbreak-news\/item\/2023-DON481."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s40794-025-00251-6","article-title":"Dengue fever in Bangladesh: Rising trends, contributing factors, and public health implications","volume":"11","author":"Ogieuhi","year":"2025","journal-title":"Trop. Dis. Travel Med. Vaccines"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Poltep, K., Phadungsombat, J., Nakayama, E.E., Kosoltanapiwat, N., Hanboonkunupakarn, B., Wiriyarat, W., Shioda, T., and Leaungwutiwong, P. (2021). Genetic Diversity of Dengue Virus in Clinical Specimens from Bangkok, Thailand, during 2018\u20132020: Co-Circulation of All Four Serotypes with Multiple Genotypes and\/or Clades. Trop. Med. Infect. Dis., 6.","DOI":"10.3390\/tropicalmed6030162"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"100654","DOI":"10.1016\/j.jher.2025.100654","article-title":"Impacts of climate change on the South Asian monsoon: A comprehensive review of its variability and future projections","volume":"59","author":"Fiaz","year":"2025","journal-title":"J. Hydro-Environ. Res."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Sylvestre, E., Joachim, C., C\u00e9cilia-Joseph, E., Bouzill\u00e9, G., Campillo-Gimenez, B., Cuggia, M., and Cabi\u00e9, A. (2022). Data-driven methods for dengue prediction and surveillance using real-world and Big Data: A systematic review. PLoS Negl. Trop. Dis., 16.","DOI":"10.1371\/journal.pntd.0010056"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1186\/s41182-025-00723-7","article-title":"Assessing dengue forecasting methods: A comparative study of statistical models and machine learning techniques in Rio de Janeiro, Brazil","volume":"53","author":"Chen","year":"2025","journal-title":"Trop. Med. Health"},{"key":"ref_9","unstructured":"UNDRR (2025, November 25). Early Warning Systems Reach New Heights, but Gaps Remain. Available online: https:\/\/www.undrr.org\/news\/early-warning-systems-reach-new-heights-critical-gaps-jeopardize-global-progress."},{"key":"ref_10","unstructured":"UNESCO (2025, November 25). Early Warning Systems. Available online: https:\/\/www.unesco.org\/en\/disaster-risk-reduction\/ews."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100210","DOI":"10.1016\/j.gloepi.2025.100210","article-title":"Explainable artificial intelligence for predicting dengue outbreaks in Bangladesh using eco-climatic triggers","volume":"10","author":"Rahman","year":"2025","journal-title":"Glob. Epidemiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1186\/s12942-025-00433-7","article-title":"Leveraging explainable artificial intelligence and spatial analysis for communicable diseases in Asia (2000\u20132022) based on health, climate, and socioeconomic factors","volume":"24","author":"Rahman","year":"2025","journal-title":"Int. J. Health Geogr."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"100230","DOI":"10.1016\/j.gloepi.2025.100230","article-title":"Reflections on explainable artificial intelligence for predicting dengue outbreaks in Bangladesh","volume":"10","author":"Rahman","year":"2025","journal-title":"Glob. Epidemiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"100879","DOI":"10.1016\/j.epidem.2025.100879","article-title":"Bayesian spatio-temporal modelling for infectious disease outbreak detection","volume":"54","author":"Adeoye","year":"2026","journal-title":"Epidemics"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Coly, S., Garrido, M., Abrial, D., and Yao, A.-F. (2021). Bayesian hierarchical models for disease mapping applied to contagious pathologies. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0222898"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e16053","DOI":"10.1016\/j.heliyon.2023.e16053","article-title":"Association of climate factors with dengue incidence in Bangladesh, Dhaka City: A count regression approach","volume":"9","author":"Hossain","year":"2023","journal-title":"Heliyon"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Alam, K.E., Ahmed, J., Chalise, R., Rahman, A., Mathin, T.T., Bhuiyan, I.H., Bhandari, P., and Hossain, D. (2025). Time series analysis of dengue incidence and its association with meteorological risk factors in Bangladesh. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0323238"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"113552","DOI":"10.1016\/j.knosys.2025.113552","article-title":"Optimal meso-granularity selection for classification based on Bayesian optimization","volume":"318","author":"Chen","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100108","DOI":"10.1016\/j.joclim.2021.100108","article-title":"Climate change adaptation in Bangladesh: Current practices, challenges and the way forward","volume":"6","author":"Chowdhury","year":"2022","journal-title":"J. Clim. Change Health"},{"key":"ref_20","unstructured":"DGHS (2025, November 25). Dengue Press Releases. Directorate General of Health Services, Available online: https:\/\/old.dghs.gov.bd\/index.php\/bd\/home\/5200-daily-dengue-status-report."},{"key":"ref_21","unstructured":"DGHS (2025, November 25). Bangladesh National Dengue Prevention and Control Strategy (2024\u20132030). Directorate General of Health Services, Available online: https:\/\/dashboard.dghs.gov.bd\/pages\/index.php."},{"key":"ref_22","unstructured":"NASA (2025, November 25). Earthdata Search, Available online: https:\/\/search.earthdata.nasa.gov\/search."},{"key":"ref_23","unstructured":"WorldBank (2025, November 25). World Bank Group\u2014International Development, Poverty and Sustainability. Available online: https:\/\/www.worldbank.org\/ext\/en\/home."},{"key":"ref_24","unstructured":"BBS (2025, November 25). Bangladesh Bureau of Statistics, Available online: http:\/\/nsds.bbs.gov.bd\/en."},{"key":"ref_25","unstructured":"WHO (2025, November 25). Indicators Index. Available online: https:\/\/www.who.int\/data\/gho\/data\/indicators\/indicators-index."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"E70726","DOI":"10.1002\/hsr2.70726","article-title":"Dengue Early Warning System and Outbreak Prediction Tool in Bangladesh Using Interpretable Tree-Based Machine Learning Model","volume":"8","author":"Rahman","year":"2025","journal-title":"Health Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"101","DOI":"10.3329\/ijss.v25i2.85772","article-title":"Data-Driven Dengue Prevention Strategies in Bangladesh using Explainable Artificial Intelligence and Causal Inference","volume":"25","author":"Rahman","year":"2025","journal-title":"Int. J. Stat. Sci."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1007\/s10113-020-01650-5","article-title":"Dynamics and drivers of land use and land cover changes in Bangladesh","volume":"20","author":"Xu","year":"2020","journal-title":"Reg. Environ. Change"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"e19991","DOI":"10.1016\/j.heliyon.2023.e19991","article-title":"Spatiotemporal characterization of relative humidity trends and influence of climatic factors in Bangladesh","volume":"9","author":"Fattah","year":"2023","journal-title":"Heliyon"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1002\/mpr.329","article-title":"Multiple imputation by chained equations: What is it and how does it work?","volume":"20","author":"Azur","year":"2011","journal-title":"Int. J. Methods Psychiatr Res."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Olaniran, O.R., and Alzahrani, A.R.R. (2025). Bayesian Random Forest with Multiple Imputation by Chain Equations for High-Dimensional Missing Data: A Simulation Study. Mathematics, 13.","DOI":"10.3390\/math13060956"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"106901","DOI":"10.1016\/j.csda.2019.106901","article-title":"Borrowing strength and borrowing index for Bayesian hierarchical models","volume":"144","author":"Xu","year":"2020","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"100157","DOI":"10.1016\/j.metip.2024.100157","article-title":"A method to simulate multivariate outliers with known mahalanobis distances for normal and non-normal data","volume":"11","year":"2024","journal-title":"Methods Psychol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"e2154","DOI":"10.1002\/hsr2.2154","article-title":"Dengue fever mapping in Bangladesh: A spatial modeling approach","volume":"7","author":"Sarker","year":"2024","journal-title":"Health Sci. Rep."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"19296","DOI":"10.1038\/s41598-023-45947-x","article-title":"Spatial autocorrelation equation based on Moran\u2019s index","volume":"13","author":"Chen","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"100452","DOI":"10.1016\/j.onehlt.2022.100452","article-title":"The association between dengue case and climate: A systematic review and meta-analysis","volume":"15","author":"Abdullah","year":"2022","journal-title":"One Health"},{"key":"ref_37","unstructured":"Posit Team RStudio (2025). Integrated Development Environment for, R (v.4.5.1) Posit Software, PBC, Posit Team RStudio. Available online: http:\/\/www.posit.co\/."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"28334","DOI":"10.1038\/s41598-025-12872-0","article-title":"Unraveling global malaria incidence and mortality using machine learning and artificial intelligence\u2013driven spatial analysis","volume":"15","author":"Rahman","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_39","unstructured":"Kluyver, T., Ragan-Kelley, B., P\u00e9rez, F., Granger, B., Bussonnier, M., Frederic, J., Kelley, K., Hamrick, J., Grout, J., and Corlay, S. (2016). Jupyter Notebooks\u2014A Publishing Format for Reproducible Computational Workflows, IOS Press."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.1093\/ije\/dyaa049","article-title":"Reflection on modern methods: Generalized linear models for prognosis and intervention\u2014theory, practice and implications for machine learning","volume":"49","author":"Arnold","year":"2020","journal-title":"Int. J. Epidemiol."},{"key":"ref_41","first-page":"e77169","article-title":"Support Vector Machines: A Literature Review on Their Application in Analyzing Mass Data for Public Health","volume":"17","author":"Khyathi","year":"2025","journal-title":"Cureus"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"e70172","DOI":"10.1111\/cts.70172","article-title":"A Tutorial and Use Case Example of the eXtreme Gradient Boosting (XGBoost) Artificial Intelligence Algorithm for Drug Development Applications","volume":"18","author":"Wiens","year":"2025","journal-title":"Clin. Transl. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.neunet.2004.07.001","article-title":"Functional multi-layer perceptron: A non-linear tool for functional data analysis","volume":"18","author":"Rossi","year":"2005","journal-title":"Neural. Netw."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Krichen, M., and Mihoub, A. (2025). Long Short-Term Memory Networks: A Comprehensive Survey. AI, 6.","DOI":"10.3390\/ai6090215"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/s41597-025-05032-6","article-title":"Convolutional Long Short-Term Memory network for generating 100 m daily near-surface air temperature","volume":"12","author":"Sun","year":"2025","journal-title":"Sci. Data"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"102068","DOI":"10.1016\/j.jksuci.2024.102068","article-title":"RNN-LSTM: From applications to modeling techniques and beyond\u2014Systematic review","volume":"36","author":"Hassan","year":"2024","journal-title":"J. King Saud. Univ.-Comput. Inf. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.envint.2014.06.018","article-title":"Impact of meteorological factors on the spatiotemporal patterns of dengue fever incidence","volume":"73","author":"Chien","year":"2014","journal-title":"Environ. Int."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"103153","DOI":"10.1016\/j.futures.2023.103153","article-title":"Types of scenario planning and their effectiveness: A review of reviews","volume":"149","author":"Rouwette","year":"2023","journal-title":"Futures"},{"key":"ref_49","first-page":"100370","article-title":"Artificial intelligence to predict West Nile virus outbreaks with eco-climatic drivers","volume":"17","author":"Farooq","year":"2022","journal-title":"Lancet Reg. Health\u2014Eur."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"106532","DOI":"10.1016\/j.envsoft.2025.106532","article-title":"A two-stage trained hybrid Unet-ConvLSTM2D for enhanced precipitation nowcasting","volume":"192","author":"Naz","year":"2025","journal-title":"Environ. Model. Softw."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1080\/02664763.2021.2023116","article-title":"The integrated nested Laplace approximation applied to spatial log-Gaussian Cox process models","volume":"50","author":"Flagg","year":"2023","journal-title":"J. Appl. Stat."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1919","DOI":"10.1038\/s41467-025-56573-8","article-title":"Artificial intelligence for modeling and understanding extreme weather and climate events","volume":"16","author":"Cohrs","year":"2025","journal-title":"Nat. Commun."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"16092","DOI":"10.1038\/s41598-024-83431-2","article-title":"Impact of dual climatic and socioeconomic factors on global trends in infectious disease outbreaks","volume":"15","author":"Qu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_54","unstructured":"WHO (2025, November 26). Climate Change. Available online: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/climate-change-and-health."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"2046","DOI":"10.1016\/j.jiph.2023.10.014","article-title":"Changing pattern of circulating dengue serotypes in the endemic region: An alarming risk to the healthcare system during the pandemic","volume":"16","author":"Verma","year":"2023","journal-title":"J. Infect. Public Health"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"100301","DOI":"10.1016\/j.sste.2019.100301","article-title":"Bayesian hierarchical spatial models: Implementing the Besag York Molli\u00e9 model in stan","volume":"31","author":"Morris","year":"2019","journal-title":"Spat. Spatio-Temporal. Epidemiol."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1038\/s43247-023-01009-8","article-title":"Bayesian weighting of climate models based on climate sensitivity","volume":"4","author":"Massoud","year":"2023","journal-title":"Commun. Earth Environ."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"100807","DOI":"10.1016\/j.ijmmb.2025.100807","article-title":"Serotype and genotype shift detection over two consecutive periods of dengue virus infection in a tertiary care hospital","volume":"54","author":"Bhat","year":"2025","journal-title":"Indian J. Med. Microbiol."},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"100310","DOI":"10.1016\/j.pdisas.2023.100310","article-title":"An integrated risk-based early warning system to increase community resilience against disaster","volume":"21","author":"Haque","year":"2024","journal-title":"Prog. Disaster Sci."},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"30164","DOI":"10.1109\/ACCESS.2024.3368377","article-title":"Explainable AI for Intrusion Detection Systems: LIME and SHAP Applicability on Multi-Layer Perceptron","volume":"12","author":"Gaspar","year":"2024","journal-title":"IEEE Access"}],"container-title":["Tropical Medicine and Infectious Disease"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2414-6366\/11\/3\/73\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:57:07Z","timestamp":1772726227000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2414-6366\/11\/3\/73"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,5]]},"references-count":60,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["tropicalmed11030073"],"URL":"https:\/\/doi.org\/10.3390\/tropicalmed11030073","relation":{},"ISSN":["2414-6366"],"issn-type":[{"value":"2414-6366","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,5]]}}}