Files and links (1)
A District-level Ensemble Model to Enhance Dengue Prediction and Control for the Mekong Delta Region of Vietnam
Preprint (Author's original)CC BY V4.0, Open
Preprint
A District-level Ensemble Model to Enhance Dengue Prediction and Control for the Mekong Delta Region of Vietnam
20/12/2024
Metrics
1 Record Views
Abstract
The Mekong Delta Region of Vietnam faces increasing dengue risks driven by urbanization, globalization, and climate change. This study introduces a probabilistic forecasting model for predicting dengue incidence and outbreaks with one to three month lead times, integrating meteorological, sociodemographic, preventive, and epidemiological data. Seventy-two models were evaluated, and an ensemble combining top-performing spatiotemporal, supervised PCA, and semi-mechanistic hhh4 frameworks was developed. Using data from 2004-2022 for training, validation, and evaluation, the ensemble model demonstrated 69% accuracy at a 3-month horizon, outperforming a baseline model. While effective, its performance declined in years with atypical seasonality, such as 2019 and 2022. The model provides critical lead time for targeted dengue prevention and control measures, addressing a growing public health need in the region.
Details
- Title
- A District-level Ensemble Model to Enhance Dengue Prediction and Control for the Mekong Delta Region of Vietnam
- Creators
- Wala Draidi Areed - The University of QueenslandThi Thanh Thao Nguyen - The University of QueenslandKien Quoc Do - The University of QueenslandThinh Nguyen - National Institute Of Hygiene And EpidemiologyVinh Bui - Southern Cross UniversityElisabeth Nelson - Yale UniversityJoshua L Warren - Yale UniversityQuang-Van Doan - University of TsukubaNam Vu Sinh - National Institute Of Hygiene And EpidemiologyNicholas Osborne - The University of QueenslandRussell Richards - The University of QueenslandNu Quy Linh Tran - The University of QueenslandHong Le - The University of QueenslandTuan Pham - Griffith UniversityTrinh Manh Hung - The University of QueenslandSon Nghiem - Australian National UniversityHai Phung - Griffith UniversityCordia Chu - Griffith UniversityRobert Dubrow - Yale UniversityDaniel M Weinberger - Yale UniversityDung Phung - The University of Queensland
- Grant note
- This research was fully funded by the Wellcome Trust [Grant number 226474/Z/22/Z].
- Identifiers
- 991013245450702368
- Academic Unit
- Information Technology; Faculty of Science and Engineering
- Language
- English
- Resource Type
- Preprint