AI-based prediction of dengue incidence using climatic, environmental, and socio-demographic factors: an ensemble random forest approach with agile system development
Abstract
Background : Dengue transmission in Indonesia is shaped by interacting climatic, environmental, and socio-demographic factors, yet most forecasting systems remain static and vulnerable to data shifts. There is a critical need for adaptive, data-driven early-warning frameworks that integrate multiple predictor domains while preventing methodological biases such as information leakage. This study aimed to develop a Random Forest (RF)–based predictive model embedded within an Agile System Development workflow to forecast monthly dengue case counts in Yogyakarta. Methods : Monthly dengue case counts from five districts (2017–2022) were modeled using multi-domain predictors. All preprocessing steps—including imputation, standardization, correlation screening, VIF diagnostics, and Negative Binomial GLM–based feature screening—were performed exclusively on the 2017–2021 training subset, with parameters applied unchanged to the 2022 test set. The GLM served solely as a leakage-free exploratory screening tool. A Random Forest model was trained using optimized hyperparameters (500 trees, max depth 10) and evaluated through temporal testing. Model reliability was assessed using calibration curves, prediction-interval metrics, and a one-month early-warning classification evaluated with sensitivity, specificity, PPV, and NPV. Results : The RF model achieved strong predictive performance (R² = 0.86; RMSE = 5.72), exceeding the GLM benchmark (R² = 0.64). Rainfall lag-1, temperature, and humidity emerged as dominant predictors, complemented by built-up area and population density. Calibration indicated good agreement across routine transmission ranges, with reduced reliability during outbreak peaks. The early-warning component demonstrated high sensitivity (0.82) and strong negative predictive value (0.86), supporting its use as a decision-support indicator of elevated transmission risk. Conclusion : The proposed Agile–AI framework demonstrates the potential to deliver accurate dengue risk predictions with interpretable uncertainty estimates within a flexible, multi-domain early-warning architecture. While external validation and further refinement are required, the framework offers a scalable foundation for adaptive dengue surveillance and targeted vector-control decision support in dynamic tropical settings.
Related
- Socio-Demographic Inequalities in the Burden of Low Back Pain Across Development Strata: Sex-Specific, Age-Standardized Trends in Prevalence, Incidence and Disability from the Global Burden of Disease Study 2023, 2003-2023.
- Demographic and environmental factors associated with canine cutaneous squamous cell carcinoma development in Australia: a retrospective matched case-control analysis.
- Hospital-Based Incidence Trends of Thyroid Cancer in Poland: Temporal Trends, Regional Disparities and Demographic Characteristics Based on a Nationwide Hospital Discharge Database (2012-2024).
- Impact of environmental determinants on malaria incidence: a systematic review
- Global and Regional Trends in Multiple Sclerosis Incidence with Projections to 2030: A Joinpoint Regression Analysis of the GBD Data 2021 by Socio‑Demographic Index and WHO Regions
BibTeX
@article{satoto2026aibased,
title = {{AI-based prediction of dengue incidence using climatic, environmental, and socio-demographic factors: an ensemble random forest approach with agile system development}},
author = {Tri Baskoro Tunggul Satoto and Nur Alvira Pascawati and Roger Frutos and Erizal Erizal and Triwibowo Ambar Garjito and Marko Ferdian Salim},
journal = {BMC Infectious Diseases},
year = {2026},
month = oct,
doi = {10.1186/s12879-026-13270-1},
url = {https://hal.science/hal-05785297v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - AI-based prediction of dengue incidence using climatic, environmental, and socio-demographic factors: an ensemble random forest approach with agile system development
AU - Tri Baskoro Tunggul Satoto
AU - Nur Alvira Pascawati
AU - Roger Frutos
AU - Erizal Erizal
AU - Triwibowo Ambar Garjito
AU - Marko Ferdian Salim
PY - 2026
DA - 2026/10/08
JO - BMC Infectious Diseases
DO - 10.1186/s12879-026-13270-1
UR - https://hal.science/hal-05785297v1
AB - Background : Dengue transmission in Indonesia is shaped by interacting climatic, environmental, and socio-demographic factors, yet most forecasting systems remain static and vulnerable to data shifts. There is a critical need for adaptive, data-driven early-warning frameworks that integrate multiple predictor domains while preventing methodological biases such as information leakage. This study aimed to develop a Random Forest (RF)–based predictive model embedded within an Agile System Development workflow to forecast monthly dengue case counts in Yogyakarta. Methods : Monthly dengue case counts from five districts (2017–2022) were modeled using multi-domain predictors. All preprocessing steps—including imputation, standardization, correlation screening, VIF diagnostics, and Negative Binomial GLM–based feature screening—were performed exclusively on the 2017–2021 training subset, with parameters applied unchanged to the 2022 test set. The GLM served solely as a leakage-free exploratory screening tool. A Random Forest model was trained using optimized hyperparameters (500 trees, max depth 10) and evaluated through temporal testing. Model reliability was assessed using calibration curves, prediction-interval metrics, and a one-month early-warning classification evaluated with sensitivity, specificity, PPV, and NPV. Results : The RF model achieved strong predictive performance (R² = 0.86; RMSE = 5.72), exceeding the GLM benchmark (R² = 0.64). Rainfall lag-1, temperature, and humidity emerged as dominant predictors, complemented by built-up area and population density. Calibration indicated good agreement across routine transmission ranges, with reduced reliability during outbreak peaks. The early-warning component demonstrated high sensitivity (0.82) and strong negative predictive value (0.86), supporting its use as a decision-support indicator of elevated transmission risk. Conclusion : The proposed Agile–AI framework demonstrates the potential to deliver accurate dengue risk predictions with interpretable uncertainty estimates within a flexible, multi-domain early-warning architecture. While external validation and further refinement are required, the framework offers a scalable foundation for adaptive dengue surveillance and targeted vector-control decision support in dynamic tropical settings.
SN - 1471-2334
ER -