Forecasting dengue severity using machine learning and environmental predictors in Chanthaburi, Thailand
Article Sidebar
Main Article Content
Abstract
Dengue fever is a vector-borne disease whose dynamics are substantially driven by climate change and environmental variability. To this end, this study proposed the establishment and assessment of machine learning models for predicting the severity of dengue incidents in Chanthaburi province, Thailand, based on climatic and environmental variables from 2018–2022. Both classification accuracy and confusion matrix analyses were used to compare the implementation of four machine learning algorithms: Random Forest, Gradient Boosting, Extra Trees, and CatBoost. The highest-performing model was able to predict a sum score of 0.50 correctly 86.70% of the time, which suggests that the developed system has good predictive ability, especially in homing in on low-severity dengue cases. Still, challenges associated with recognizing high-severity cases persist. Shapley Additive Explanations (SHAP) sensitivity analysis revealed that specific air pollutant levels (PM10, PM2.5), time-lag parameters, and indicators such as temperature and humidity, particularly during certain periods, were significant predictors of dengue severity. Our results reveal the intricate relationships between environmental variables and the pattern of dengue transmission, arguing for a judicious use of machine learning tools as evidence-based support to inform disease control policies. Future studies that consider other variables, longer time series data, and advanced modeling techniques are needed to increase the accuracy of predictions, especially with respect to improving sensitivity for high-severity dengue outbreaks.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
World Health Organization. Vector-borne diseases [Internet]. 2024 [cited 2025 Apr 17]. Available from: https://www.who.int/
news-room/fact-sheets/detail/vector-borne-diseases.
World Bank Group, Asian Development Bank. Climate risk country profile: Thailand. Thailand: World Bank Group and Asian Development Bank: 2021. Report No. TCS210314-2.
Alied M, Nguyen D, Aziz JMA, Vinh DP, Huy NT. Dengue fever on the rise in Southeast Asia. Pathog Global Health. 2023;117(1):1-2. DOI: https://doi.org/10.1080/20477724.2022.2116550
IQAir. Interactive global map of 2024 PM2.5 concentrations by city [Internet]. 2024 [cited 2025 Apr 17]. Available from: https://www.iqair.com/th-en/world-air-quality-report.
Ratanawong P, Nunthaitaweekul P, Huynh PT, Weesakul U. Impact of climate change on human health in Thailand: a literature review. J. Disaster Res. 2025;20(4):423-44. DOI: https://doi.org/10.20965/jdr.2025.p0423
Centers for Disease Control and Prevention. Thailand: CDC Yellow Book 2024 [Internet]. 2024 [cited 2024 Apr 17]. Available from: https://wwwnc.cdc.gov/travel/yellowbook/2024/itineraries/thailand#infectious.
Rahman MS, Pientong C, Zafar S, Ekalaksananan T, Paul RE, Haque U, et al. Mapping the spatial distribution of the dengue vector Aedes aegypti and predicting its abundance in northeastern Thailand using machine-learning approach. One Health. 2021;13:100358. DOI: https://doi.org/10.1016/j.onehlt.2021.100358
Chumpu R, Khamsemanan N, Nattee C. The association between dengue incidences and provincial-level weather variables in Thailand from 2001 to 2014. PLoS One. 2019;14(12):e0226945. DOI: https://doi.org/10.1371/journal.pone.0226945
Cheng Y, Cheng R, Xu T, Tan X, Bai Y, Yang J. Integrating meteorological data and hybrid intelligent models for dengue fever prediction. BMC Public Health. 2025;25:1516. DOI: https://doi.org/10.1186/s12889-025-22375-2
Hii YL, Rocklöv J, Ng N, Tang CS, Pang FY, Sauerborn R. Climate variability and increase in intensity and magnitude of dengue incidence in Singapore. Glob Health Action. 2009;2(1):2036. DOI: https://doi.org/10.3402/gha.v2i0.2036
Chakraborty S, Zigmond E, Shah S, Dayal D, Sylla M, Akorli J, et al. Thermal tolerance of Aedes aegypti mosquito eggs is associated with urban adaptation and human interactions. J Therm Biol. 2025;131:104167. DOI: https://doi.org/10.1016/j.jtherbio.2025.104167
Sharma G, Khan Z, Das D, Singh S, Singh S, Kumar M, et al. Thermal influence on development and morphological traits of Aedes aegypti in central India and its relevance to climate change. Parasites Vectors. 2025;18:279. DOI: https://doi.org/10.1186/s13071-025-06924-7
Puengpreeda A, Yhusumrarn S, Sirikulvadhana S. Weekly forecasting model for dengue hemorrhagic fever outbreak in Thailand. Eng J. 2020;24(3):71-87. DOI: https://doi.org/10.4186/ej.2020.24.3.71
Kesorn K, Ongruk P, Chompoosri J, Phumee A, Thavara U, Tawatsin A, et al. Morbidity rate prediction of dengue hemorrhagic fever (DHF) using the support vector machine and the Aedes aegypti infection rate in similar climates and geographical areas. PLoS ONE. 2015;10(5):e0125049. DOI: https://doi.org/10.1371/journal.pone.0125049
Jain R, Sontisirikit S, Iamsirithaworn S, Prendinger H. Prediction of dengue outbreaks based on disease surveillance, meteorological and socio-economic data. BMC Infect Dis. 2019;19:272. DOI: https://doi.org/10.1186/s12879-019-3874-x
Thompson MC, Palmer T, Morse AP, Cresswell M, Connor SJ. Forecasting disease risk with seasonal climate predictions. Lancet. 2000;355(9214):1559-60. DOI: https://doi.org/10.1016/S0140-6736(05)74616-X
Kaur I, Kumar Y, Sandhu AK, Ijaz MF. Predictive modeling of epidemic diseases based on vector-borne diseases using artificial intelligence techniques. In: Tamrakar S, Choubey SB, Choubey A, editors. Computational intelligence in medical decision making and diagnosis. Boca Raton: CRC Press; 2023. p. 81-100. DOI: https://doi.org/10.1201/9781003309451-5
Leung XY, Islam RM, Adhami M, Ilic D, McDonald L, Palawaththa S, et al. A systematic review of dengue outbreak prediction models: current scenario and future directions. PLoS Negl Trop Dis. 2023;17(2):e0010631. DOI: https://doi.org/10.1371/journal.pntd.0010631
Molina-Guzmán LP, Gutiérrez-Builes LA, Ríos-Osorio LA. Models of spatial analysis for vector-borne diseases studies: a systematic review. Vet World. 2022;15(8):1975-89. DOI: https://doi.org/10.14202/vetworld.2022.1975-1989
Zhao N, Charland K, Carabali M, Nsoesie EO, Maheu-Giroux M, Rees E, et al. Machine learning and dengue forecasting: comparing random forests and artificial neural networks for predicting dengue burden at national and sub-national scales in Colombia. PLoS Negl Trop Dis. 2020;14(9):e0008056. DOI: https://doi.org/10.1371/journal.pntd.0008056
Kerdprasop N, Kerdprasop K, Chuaybamroong P. Computational intelligence and statistical learning performances on predicting dengue incidence using remote sensing data. Adv Sci Technol Eng Syst J. 2020;5(4):344-50. DOI: https://doi.org/10.25046/aj050440
Abdulsalam FI, Antunez P, Yimthiang S, Jawjit W. Influence of climate variables on dengue fever occurrence in the southern region of Thailand. PLOS Glob Public Health. 2022;2(4):e0000188. DOI: https://doi.org/10.1371/journal.pgph.0000188
Kerdprasop K, Kerdprasop N, Chuaybamroong P. Forecasting dengue incidence with the chi-squared automatic interaction detection technique. 2019 2nd Artificial Intelligence and Cloud Computing Conference, AICCC 2019; 2019 Dec 21-23; Kobe Japan. USA: ACM; 2019. p. 37-42. DOI: https://doi.org/10.1145/3375959.3375971
Dhaked DK, Sharma O, Gopal Y, Gopal R. Prediction of dengue patients using deep learning methods amid complex weather conditions in Jaipur, India. Discov Public Health. 2025;22:58. DOI: https://doi.org/10.1186/s12982-025-00448-2
Tuan D. Leveraging climate data for dengue forecasting in Ba Ria Vung Tau Province, Vietnam: an advanced machine learning approach. Trop Med Infect Dis. 2024;9(10):250. DOI: https://doi.org/10.3390/tropicalmed9100250
Mazhar B, Ali NM, Manzoor F, Khan MK, Nasir M, Ramzan M. Development of data-driven machine learning models and their potential role in predicting dengue outbreak. J Vector Borne Dis. 2024;61(4):503-14. DOI: https://doi.org/10.4103/0972-9062.393976
Francisco ME, Carvajal TM, Watanabe K. Hybrid machine learning approach to zero-inflated data improves accuracy of dengue prediction. PLoS Negl Trop Dis. 2024;18(10):e0012599. DOI: https://doi.org/10.1371/journal.pntd.0012599
Al Mobin M. Forecasting dengue in Bangladesh using meteorological variables with a novel feature selection approach. Sci Rep. 2024;14:32073. DOI: https://doi.org/10.1038/s41598-024-83770-0
Sebastianelli A, Spiller D, Carmo R, Wheeler J, Nowakowski A, Jacobson LV, et al. A reproducible ensemble machine learning approach to forecast dengue outbreaks. Sci Rep. 2024;14:3807. DOI: https://doi.org/10.1038/s41598-024-52796-9
Chowdhury AH. Comparison of deep learning and gradient boosting: ANN versus XGBoost for climate‐based dengue prediction in Bangladesh. Health Sci Rep. 2025;8:e70714. DOI: https://doi.org/10.1002/hsr2.70714
Sutriyawan A, Rahardjo M, Martini M, Sutiningsih D, Rattanapan C, Kassim NFA. Global forecasting models for dengue outbreaks in endemic regions: a systematic review. Zh Mikrobiol Epidemiol Immunobiol. 2025;102(2):331-42. DOI: https://doi.org/10.36233/0372-9311-694
Rocklöv J, Dubrow R. Climate change: an enduring challenge for vector-borne disease prevention and control. Nat Immunol. 2020;21:479-83. DOI: https://doi.org/10.1038/s41590-020-0648-y
The Health Aisle Team. How does climate change affect diseases like Malaria, Dengue and Chikungunya? [Internet]. n.d. [cited 2025 Apr 17]. Available from: https://www.prudential.co.th/corp/prudential-th/en/we-do-pulse/health-wellness/how-does-climate-change-affect-diseases-like-malaria-dengue-and-chikungunya/.
Tewari P, Guo P, Dickens B, Ma P, Bansal S, Lim JT. Associations between dengue incidence, ecological factors, and anthropogenic factors in Singapore. Viruses. 2023;15(9):1917. DOI: https://doi.org/10.3390/v15091917
Narvaez F, Gutierrez G, Pérez MA, Elizondo D, Nuñez A, Balmaseda A, et al. Evaluation of the traditional and revised WHO classifications of dengue disease severity. PLoS Negl Trop Dis. 2011;5(11):e1397. DOI: https://doi.org/10.1371/journal.pntd.0001397
Ajlan BA, Alafif MM, Alawi MM, Akbar NA, Aldigs EK, Madani TA. Assessment of the new World Health Organization’s dengue classification for predicting severity of illness and level of healthcare required. PLoS Negl Trop Dis. 2019;13(8):e0007144. DOI: https://doi.org/10.1371/journal.pntd.0007144
Friedman JH. Greedy function approximation: a gradient boosting machine. Ann Stat. 2001;29(5):1189-232. DOI: https://doi.org/10.1214/aos/1013203451
Ditthakit P, Pinthong S, Salaeh N, Binnui F, Khwanchum L, Pham QB. Using machine learning methods for supporting GR2M model in runoff estimation in an ungauged basin. Sci Rep. 2021;11:19955. DOI: https://doi.org/10.1038/s41598-021-99164-5
Dou J, Yunus AP, Tien Bui D, Merghadi A, Sahana M, Zhu Z, et al. Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan. Sci Total Environ. 2019;662:332-46. DOI: https://doi.org/10.1016/j.scitotenv.2019.01.221
Zhu L, Qiu D, Ergu D, Ying C, Liu K. A study on predicting loan default based on the random forest algorithm. Procedia Comput Sci. 2019;162:503-13. DOI: https://doi.org/10.1016/j.procs.2019.12.017
Safari MJS. Hybridization of multivariate adaptive regression splines and random forest models with an empirical equation for sediment deposition prediction in open channel flow. J Hydrol. 2020;590:125392. DOI: https://doi.org/10.1016/j.jhydrol.2020.125392
Schoppa L, Disse M, Bachmair S. Evaluating the performance of random forest for large-scale flood discharge simulation. J Hydrol. 2020;590:125531. DOI: https://doi.org/10.1016/j.jhydrol.2020.125531
Ali M, Prasad R, Xiang Y, Yaseen ZM. Complete ensemble empirical mode decomposition hybridized with random forest and kernel ridge regression model for monthly rainfall forecasts. J Hydrol. 2020;584:124647. DOI: https://doi.org/10.1016/j.jhydrol.2020.124647
Otchere DA, Ganat TOA, Ojero JO, Tackie-Otoo BN, Taki MY. Application of gradient boosting regression model for the evaluation of feature selection techniques in improving reservoir characterisation predictions. J Pet Sci Eng. 2022;208:109244. DOI: https://doi.org/10.1016/j.petrol.2021.109244
Rao H, Shi X, Rodrigue AK, Feng J, Xia Y, Elhoseny M, et al. Feature selection based on artificial bee colony and gradient boosting decision tree. Appl Soft Comput. 2019;74:634-42. DOI: https://doi.org/10.1016/j.asoc.2018.10.036
Alexopoulos MJ, Müller-Thomy H, Nistahl P, Šraj M, Bezak N. Validation of precipitation reanalysis products for rainfall-runoff modelling in Slovenia. Hydrol Earth Syst Sci. 2023;27(13):2559-78. DOI: https://doi.org/10.5194/hess-27-2559-2023
Bagalkot N, Keprate A, Orderløkken R. Combining computational fluid dynamics and gradient boosting regressor for predicting force distribution on horizontal axis wind turbine. Vibration. 2021;4(1):248-62. DOI: https://doi.org/10.3390/vibration4010017
Geurts P, Ernst D, Wehenkel L. Extremely randomized trees. Mach Learn. 2006;63:3-42. DOI: https://doi.org/10.1007/s10994-006-6226-1
Ahmad MW, Reynolds J, Rezgui Y. Predictive modelling for solar thermal energy systems: a comparison of support vector regression, random forest, extra trees and regression trees. J Cleaner Prod. 2018;203:810-21. DOI: https://doi.org/10.1016/j.jclepro.2018.08.207
John V, Liu Z, Guo C, Mita S, Kidono K. Real-time Lane estimation using deep features and extra trees regression. 7th Pacific-Rim Symposium, Image and Video Technology 2015, PSIVT 2015; 2015 Nov 25-27; Auckland, New Zealand. Cham: Springer; 2016. p. 721-33. DOI: https://doi.org/10.1007/978-3-319-29451-3_57
Ahmad MW, Mourshed M, Rezgui Y. Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression. Energy. 2018;164:465-74. DOI: https://doi.org/10.1016/j.energy.2018.08.207
Prokhorenkova L, Gusev G, Vorobev A, Dorogush AV, Gulin A. CatBoost: unbiased boosting with categorical features. 32nd International Conference on Neural Information Processing Systems; 2018 Dec 2-8; Montréal, Canada. USA: NeurIPS; 2018. p. 6838-48.
Jia X, Wang Y, Wang Z, Ji X. New insights into the main meteorological factors affecting mosquito densities: time lags, interaction effects, and species specificity. Environ Ecol Stat. 2025;32:1091-113. DOI: https://doi.org/10.1007/s10651-025-00669-3
Ardiansyah Akbar K, Kumala Fatma R, Elamouri F, Rockstroh JK. Climate change and dengue fever: a 14-year study of mortality trends during 2010–2023 in Indonesia. Travel Med. Infect. Dis. 2025;67:102893. DOI: https://doi.org/10.1016/j.tmaid.2025.102893
Sy AK, Biggs J, Chowdhury SK, Quinones MA, Jones-Warner W, Ashall J, et al. The impact of altitude and population density on dengue incidence and force of infection across the Philippines: implications for climate-adapted surveillance [Internet]. SSRN [Preprint]. 2025 [cited 2025 Apr 17]. Available from: https://doi.org/10.2139/ssrn.5400338. DOI: https://doi.org/10.2139/ssrn.5400338
Hancock JT, Khoshgoftaar TM. CatBoost for big data: an interdisciplinary review. J Big Data. 2020;7:94. DOI: https://doi.org/10.1186/s40537-020-00369-8
Dunias ZS, Van Calster B, Timmerman D, Boulesteix AL, Van Smeden M. A comparison of hyperparameter tuning procedures for clinical prediction models: a simulation study. Stat Med. 2024;43(6):1119-34. DOI: https://doi.org/10.1002/sim.9932
Nishio M, Nishizawa M, Sugiyama O, Kojima R, Yakami M, Kuroda T, et al. Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization. PLoS ONE. 2018;13(4):e0195875. DOI: https://doi.org/10.1371/journal.pone.0195875
Zafar S, Rocklöv J, Paul RE, Shipin O, Rahman MS, Pientong C, et al. Landscape and climatic drivers of dengue fever in Lao People’s Democratic Republic and Thailand: a retrospective analysis during 2002–2019. Landsc Ecol. 2025;40:102. DOI: https://doi.org/10.1007/s10980-025-02102-3
Sang S, Wang Y, Liu Q, Chen P, Li C, Zhang A. Predicting dengue incidence in high-risk areas of China through the integration of Southeast Asian and local meteorological factors. Ecotoxicol Environ Saf. 2025;290:117751. DOI: https://doi.org/10.1016/j.ecoenv.2025.117751
Kaewhan S, Junpha J, Pimpeach W. The regional distribution of dengue fever in Thailand and other emerging countries in Southeast Asia: a literature review. Toxicol Environ Health Sci. 2025;17:327-34. DOI: https://doi.org/10.1007/s13530-025-00251-1
Liu M, Zhang Y. Impact of climate change on dengue fever: a bibliometric analysis. Geospat Health. 2025;20:1301. DOI: https://doi.org/10.4081/gh.2025.1301
Sapbamrer P, Chaichanan P, Chiablam S, Pimonsree S, Thongtip S. Association of meteorology and air quality with dengue fever incidence in Upper Northern Thailand. EnvironmentAsia. 2025;18(1):164-73.
Mailepessov D, Ong J, Aik J. Influence of air pollution and climate variability on dengue in Singapore: a time-series analysis. Sci Rep. 2025;15:13467. DOI: https://doi.org/10.1038/s41598-025-97068-2
Lu HC, Lin FY, Huang YH, Kao YT, Loh EW. Role of air pollutants in dengue fever incidence: evidence from two southern cities in Taiwan. Pathog Global Health. 2023;117(6):596-604. DOI: https://doi.org/10.1080/20477724.2022.2135711
Kuo CY, Yang WW, Su ECY. Improving dengue fever predictions in Taiwan based on feature selection and random forests. BMC Infect Dis. 2024;24:334. DOI: https://doi.org/10.1186/s12879-024-09220-4
Ju X, Zhang W, Yimaer W, Lu J, Xiao J, Qu Y, et al. How air pollution altered the association of meteorological exposures and the incidence of dengue fever. Environ Res Lett. 2022;17:124041. DOI: https://doi.org/10.1088/1748-9326/aca59f
Massad E, Coutinho FAB, Ma S, Burattini MN. A hypothesis for the 2007 dengue outbreak in Singapore. Epidemiol Infect. 2010;138:951-7. DOI: https://doi.org/10.1017/S0950268809990501
Cano-Granda DV, Ramírez-Ramírez M, Gómez DM, Hernandez JC. Effects of particulate matter on endothelial, epithelial and immune system cells. Rev Bionatura. 2022;7(1):4. DOI: https://doi.org/10.21931/RB/2022.07.01.4
Andrade AC, Falcão LAD, Borges MAZ, Leite ME, Espírito Santo MMD. Are land use and cover changes and socioeconomic factors associated with the occurrence of dengue fever? a case study in Minas Gerais State, Brazil. Resources. 2024;13(3):38. DOI: https://doi.org/10.3390/resources13030038
