The results imply that the GWRF is more effective in modeling dengue fever outbreaks and can inform the development of region-specific public health interventions.
Abstract
Dengue hemorrhagic fever continues to pose a significant public health challenge, particularly in West Java Province, Indonesia, which consistently reports the highest incidence rates in the country. This study examined the factors influencing dengue fever incidence using Random Forest Regression (RFR) and Geographically Weighted Random Forest (GWRF) methodologies. Utilizing secondary data from 2022 to 2024 across 27 districts/cities, the data from 2022 to 2023 served as training data, while the 2024 data were used for testing. The findings revealed that the optimal RFR model, with ntree = 1000 and mtry = 1, achieved an RMSE of 1796.409, a MAPE of 0.482, and an of 0.685. Conversely, the GWRF model, which employed an adaptive kernel and an optimal bandwidth of 45 nearest neighbors, exhibited superior performance, with an RMSE of 1,756.713, MAPE of 0.466, and of 0.700. This enhancement in the model performance suggests that spatial weighting improves the model's capacity to capture spatial heterogeneity. In addition, variations in local feature importance indicate spatial non-stationarity across regions. These results imply that the GWRF is more effective in modeling dengue fever outbreaks and can inform the development of region-specific public health interventions.
The development and assessment of a machine learning-driven early warning system for infectious disease prediction using geospatial big data from South-Western Nigeria, at the level of Local Government Area outperform conventional surveillance systems in developing countries.
I. Adewumi, N. Bakare, W. Ajayi et al.· London Journal of Physics· 0 citations
Beyond predictive accuracy, qualitative criteria including explain-ability, transparency, and adaptability were evaluated, further highlighting the superiority of CBR 2 over conventional black-box models.
Konan N’gatta Aimé Kouassi, Koffi Kouakou Ive Arsene, Goore Bi Tra· International Journal of Adv...· 0 citations
The feasibility of predicting dengue outbreaks using weekly multivariate time-series data from San Juan, Puerto Rico and Iquitos, Peru is examined, demonstrating that advanced machine learning models can serve as reliable early warning systems for vector-borne diseases.
Pratik S. Machchar, Purvi N. Ramanuj, R. Patel et al.· International Journal of Inf...· 0 citations
Dengue is an arboviral disease of high public health relevance, characterized by pronounced temporal variability, nonlinearity, and recurrent outbreaks, which pose challenges to epidemiological surveillance and decision-making. This study evaluated the performance of machine learning methods for short-term forecasting of the weekly dengue morbidity rate in the 27 Brazilian capital cities, comprising the 26 state capitals and Brasília, Federal District, with horizons up to 4 weeks. Epidemiological, climatic, and socioeconomic data were compiled for these capital cities and used to compare a Gated Recurrent Unit (GRU) neural network, formulated as a Multi-Input Multi-Output (MIMO) model, and a Gradient Boosting model (CatBoost), implemented using a Direct forecasting strategy with horizon-specific models. Validation was conducted using a walk-forward approach, with evaluation based on absolute error metrics and the coefficient of determination. The results indicated that the GRU architecture presented recurring limitations, including underfitting, temporal lag, and low capacity to anticipate epidemic peaks. In contrast, the CatBoost model demonstrated greater robustness and better adaptation to the variability of epidemiological time series, showing superior performance in most of the analyzed capitals. The findings reinforce that greater architectural complexity does not necessarily imply better operational performance and highlight the potential of ensemble-based methods for short-term epidemiological surveillance applications. These findings contribute to dengue forecasting by showing that, under a common validation framework, ensemble-based strategies may provide greater operational robustness than recurrent MIMO architectures for short-term prediction in heterogeneous epidemiological settings.
D. C. da Cunha e Silva, L. M. Nery, Nícholas de Paula Nicomedes et al.· International journal of bio...· 0 citations
This study employed geospatial approaches to assess the risk and spatial distribution of Dengue Fever (DF) and Dengue Hemorrhagic Fever (DHF) in Phayao Province, Thailand. Epidemiological data from 2016 to 2024, comprising 3,600 reported cases, were analysed alongside demographic and climatic variables. Temporal analysis revealed a major epidemic in 2023 lasting 20 weeks, coinciding with peak rainfall, with adolescents and young adults (13-24 years old) being the most affected group. Spatial autocorrelation (Moran's I) indicated significant clustering of dengue morbidity rates, with hotspots concentrated in urbanised districts such as Mueang Phayao, Dok Khamtai and Chiang Kham, while Kernel Density Estimation (KDE) highlighted shifts of hotspots toward eastern districts in later years. Local Indicators of Spatial Association (LISA) identified 24 high-high clusters in 2019, predominantly in Mae Chai District. Case-control analysis further revealed that socio-economic conditions, housing environments and inconsistent preventive behaviours influenced dengue incidence, with strong community participation linked to more effective prevention. These findings underscore the spatial heterogeneity of dengue transmission and provide geospatial evidence to guide targeted vector control, strengthen community-based interventions, and support evidence-based public health strategies in northern Thailand.
Phaisarn Jeefoo, Watcharaporn Preedapirom Jeefoo, S. Mekruksavanich et al.· Geospatial Health· 0 citations
A machine learning-based model for predicting outbreaks, explainability, and spatial risk propagation, validated through a multiyear data set of an epidemiological nature from 12 cities in the Eastern Province of Saudi Arabia (2021–2025).
N. F. Saleem ALAnsary, Mahmood Berekaa, Raghad Alhotheyfa et al.· Frontiers in Public Health· 0 citations