Background: Distinguishing between non-severe and severe dengue is crucial for timely intervention and reducing morbidity and mortality. Traditional warning signs recommended by the World Health Organization (WHO) offer a practical approach for clinicians but have limitations in sensitivity and specificity. This study evaluates the performance of machine learning (ML) models compared to WHO-recommended warning signs in predicting severe dengue among laboratory-confirmed cases in Puerto Rico. Methods: We analyzed data from Puerto Rico's Sentinel Enhanced Dengue Surveillance System (May 2012-August 2024), using 40 clinical, demographic, and laboratory variables. Nine ML models, including Decision Trees, K-Nearest Neighbors, Naive Bayes, Support Vector Machines, Artificial Neural Networks, AdaBoost, CatBoost, LightGBM, and XGBoost, were trained using 5-fold cross-validation and evaluated with area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). A subanalysis excluded hemoconcentration and leukopenia to assess performance in resource-limited settings. An AUC-ROC value of 0.5 indicates no discriminative power, while a value closer to 1.0 reflects better performance. Results: Among the 1,708 laboratory-confirmed dengue cases, 24.3% were classified as severe. Gradient boosting algorithms achieved the highest predictive performance, with AUC-ROC values exceeding 94% for CatBoost, LightGBM, and XGBoost. Feature importance analysis identified hemoconcentration (≥20% increase during illness or ≥20% above baseline for age and sex), leukopenia (white blood cell count <4,000/mm3), and timing of presentation to a healthcare facility at 4-6 days post-symptom onset as key predictors. Excluding hemoconcentration and leukopenia did not significantly affect model performance. Individual warning signs like abdominal pain and restlessness had sensitivities of 79.0% and 64.6%, but lower specificities of 48.4% and 59.1%, respectively. Combining ≥3 warning signs improved specificity (80.9%) while maintaining moderate sensitivity (78.6%), resulting in an AUC-ROC of 74.0%. Conclusions: 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.

The authors have declared no competing interest.

This research was funded by Centers for Disease Control and Prevention, grant numbers U01CK000473 and U01CK000580 (VRA).

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

The Institutional Review Boards at the Centers for Disease Control and Prevention (CDC), Auxilio Mutuo, and Ponce Medical School Foundation approved the SEDSS study protocols 6214, and 120308-VR/2311173707, respectively. Written consent to participate was obtained from all adult participants and emancipated minors. For minors aged 14 to 20 years, written consent was obtained, and for those aged 7 to 13 years, parental written consent and participant assent were obtained.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes

Data cannot be shared publicly because data cannot be deidentified at the granular level of analyses performed. Data are available from the CDC management team (contact: dengue@cdc.gov) for researchers who meet the criteria for access to confidential data.