Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Steps in Outbreak Investigation

Steps in Outbreak Investigation

In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Cross-sectional analysis of chikungunya vaccine acceptability among residents of Ponce, Puerto Rico, 2024-2025.

Vaccine·2026

Same author

Utility of sentinel surveillance as an early warning system for emerging pathogens in a low-resource setting: Correlations of dengue, chikungunya, Zika, and COVID-19 trends between sentinel and passive surveillance systems in Puerto Rico, 2012-2023.

PLOS global public health·2026

Same author

Leveraging Sentinel Enhanced Surveillance to Characterize the 2024-2025 Dengue Epidemic in Puerto Rico: Insights and Comparisons With Passive Surveillance.

Public health reports (Washington, D.C. : 1974)·2026

Same author

Increase in Travel-Associated and Locally Acquired Dengue Cases - United States, 2024.

MMWR. Morbidity and mortality weekly report·2026

Same author

Evaluation of Effectiveness of Autocidal Gravid Ovitraps for Preventing Zika Virus Infection, Puerto Rico, USA.

Emerging infectious diseases·2026

Same author

Deaths with preceding hospitalisations within 180 days in eight countries in sub-Saharan Africa and South Asia: A secondary descriptive analysis of the Child Health and Mortality Prevention Surveillance (CHAMPS) network.

BMJ open·2026

Search research articles

Related Experiment Video

Updated: May 29, 2025

A Murine Model of Dengue Virus-induced Acute Viral Encephalitis-like Disease

A Murine Model of Dengue Virus-induced Acute Viral Encephalitis-like Disease

Published on: April 28, 2019

Machine learning for predicting severe dengue in Puerto Rico.

Zachary J Madewell¹, Dania M Rodriguez², Maile B Thayer²

¹Division of Vector-Borne Diseases, Centers for Disease Control and Prevention, San Juan, Puerto Rico, USA. ock0@cdc.gov.

Infectious Diseases of Poverty

|February 5, 2025

Summary

Machine learning models accurately predict severe dengue, outperforming traditional warning signs. This technology can improve early detection and patient management in clinical settings.

Keywords:

Caribbean Clinical decision support Dengue Ensemble learning Feature importance Gradient boosting

More Related Videos

Visualizing Dengue Virus through Alexa Fluor Labeling

Visualizing Dengue Virus through Alexa Fluor Labeling

Published on: July 9, 2011

Multiplexed Isothermal Amplification Based Diagnostic Platform to Detect Zika, Chikungunya, and Dengue 1

Multiplexed Isothermal Amplification Based Diagnostic Platform to Detect Zika, Chikungunya, and Dengue 1

Published on: March 13, 2018

Related Experiment Videos

Last Updated: May 29, 2025

A Murine Model of Dengue Virus-induced Acute Viral Encephalitis-like Disease

A Murine Model of Dengue Virus-induced Acute Viral Encephalitis-like Disease

Published on: April 28, 2019

Visualizing Dengue Virus through Alexa Fluor Labeling

Visualizing Dengue Virus through Alexa Fluor Labeling

Published on: July 9, 2011

Multiplexed Isothermal Amplification Based Diagnostic Platform to Detect Zika, Chikungunya, and Dengue 1

Multiplexed Isothermal Amplification Based Diagnostic Platform to Detect Zika, Chikungunya, and Dengue 1

Published on: March 13, 2018

Area of Science:

Infectious Disease Epidemiology
Computational Biology
Clinical Decision Support

Background:

Accurate prediction of severe dengue is critical for reducing mortality.
World Health Organization (WHO) warning signs have limitations in sensitivity and specificity.
This study evaluated machine learning (ML) models against WHO warning signs for severe dengue prediction.

Purpose of the Study:

To compare the performance of various ML models with WHO-recommended warning signs in predicting severe dengue.
To identify key predictors of severe dengue in laboratory-confirmed cases.
To assess the applicability of ML models in resource-limited settings.

Main Methods:

Analysis of 40 clinical, demographic, and laboratory variables from Puerto Rico's Dengue Surveillance System (2012-2024).
Training and evaluation of nine ML models using fivefold cross-validation and AUC-ROC metrics.
Subanalysis excluding hemoconcentration and leukopenia to simulate resource-limited scenarios.

Main Results:

Gradient boosting algorithms (CatBoost) achieved the highest AUC-ROC of 97.1% for severe dengue prediction.
Key predictors included hemoconcentration, leukopenia, and symptom onset timing (4-6 days).
ML models showed minimal performance decrease (AUC-ROC 96.7%) when excluding lab parameters, outperforming combined WHO warning signs (AUC-ROC 74.0%).

Conclusions:

Machine learning models, particularly gradient boosting, significantly outperform traditional warning signs for severe dengue prediction.
Integration of ML into clinical decision support can enhance early identification of high-risk patients.
ML models demonstrate utility even in resource-limited settings, aiding timely interventions.