A Dataset of Dengue Hospitalizations in Brazil (1999 to 2021) with Weekly Disaggregation from Monthly Counts
Lucas M. Morello, Matheus Lima Castro, Pedro Cesar M. G. Camargo, Liliane Moreira Nery, Darllan Collins da Cunha e Silva, Leopoldo Lusquino Filho
TL;DR
This work addresses the limited temporal granularity of monthly dengue hospitalization data in Brazil by generating weekly (epiweek) series for 1999–2021 through temporal disaggregation. It systematically evaluates three interpolation strategies—linear, jittering, and cubic spline—against a high-resolution São Paulo reference (CVE-SP 2024) and selects cubic spline as the default due to superior distributional fidelity and temporal alignment, while acknowledging limitations in sparse municipalities. The authors publicly release a versioned dataset (v1.0.0) containing weekly dengue hospitalization rates and harmonized covariates across 5,028 municipalities, enabling multivariate forecasting and epidemiological modeling with consistent provenance and licensing (CC BY 4.0). They also document rigorous quality metrics (MAE, RMSE, $R^2$, $D_{KL}$, $\mathrm{JSD}$, DTW, KS) and provide guidance for responsible use, including sensitivity analyses and calendar-alignment considerations. Overall, the dataset offers a reproducible resource to improve outbreak forecasting and spatiotemporal studies, while transparently outlining limitations related to derived weekly scales and regional variability.
Abstract
This data paper describes and publicly releases this dataset (v1.0.0), published on Zenodo under DOI 10.5281/zenodo.18189192. Motivated by the need to increase the temporal granularity of originally monthly data to enable more effective training of AI models for epidemiological forecasting, the dataset harmonizes municipal-level dengue hospitalization time series across Brazil and disaggregates them to weekly resolution (epidemiological weeks) through an interpolation protocol with a correction step that preserves monthly totals. The statistical and temporal validity of this disaggregation was assessed using a high-resolution reference dataset from the state of Sao Paulo (2024), which simultaneously provides monthly and epidemiological-week counts, enabling a direct comparison of three strategies: linear interpolation, jittering, and cubic spline. Results indicated that cubic spline interpolation achieved the highest adherence to the reference data, and this strategy was therefore adopted to generate weekly series for the 1999 to 2021 period. In addition to hospitalization time series, the dataset includes a comprehensive set of explanatory variables commonly used in epidemiological and environmental modeling, such as demographic density, CH4, CO2, and NO2 emissions, poverty and urbanization indices, maximum temperature, mean monthly precipitation, minimum relative humidity, and municipal latitude and longitude, following the same temporal disaggregation scheme to ensure multivariate compatibility. The paper documents the datasets provenance, structure, formats, licenses, limitations, and quality metrics (MAE, RMSE, R2, KL, JSD, DTW, and the KS test), and provides usage recommendations for multivariate time-series analysis, environmental health studies, and the development of machine learning and deep learning models for outbreak forecasting.