Machine learning for predicting severe dengue in Puerto Rico
ML models, especially gradient boosting algorithms, outperformed traditional warning signs in predicting severe dengue. Integrating these models into clinical decision-support tools could help clinicians better identify high-risk patients, guiding timely interventions like hospitalization, closer monitoring, or the administration of intravenous fluids. The subanalysis excluding hemoconcentration confirmed the models' applicability in resource-limited settings, where access to laboratory data may be limited.
Authors
- Joshua M. Wong (ORCID: https://orcid.org/0000-0002-1062-0049)
- Maile T. Phillips (ORCID: https://orcid.org/0000-0001-6952-0440)
- Gabriela Paz‐Bailey (ORCID: https://orcid.org/0000-0001-8478-4911)
- Vanessa Rivera‐Amill (ORCID: https://orcid.org/0000-0003-4810-0871)
- Zachary J. Madewell (ORCID: https://orcid.org/0000-0002-5667-9660)
- Laura E. Adams (ORCID: https://orcid.org/0000-0003-4698-7720)
- Dania M. Rodríguez (ORCID: https://orcid.org/0000-0003-2837-3629)
Institutions
- Centers for Disease Control and Prevention (US)
- Ponce Health Sciences University (PR)
- Puerto Rico Department of Health (PR)
Publication Details
- Journal
- Infectious Diseases of Poverty
- Published
- 2025-02-04
- DOI
- https://doi.org/10.1186/s40249-025-01273-0
- Citations
- 10
- Primary Topic
- Mosquito-borne diseases and control
- Type
- article
- Field-Weighted Citation Impact
- 18.79
Funders
- Centers for Disease Control and Prevention