Identifying children without serious bacterial infections in the pediatric ICU

Predicting the Absence of Serious Bacterial Infection in the PICU

NIH-funded research University of Colorado Denver · NIH-10932411

This study is working on smart tools to help doctors figure out which kids in the pediatric intensive care unit don’t have serious bacterial infections, so they can avoid giving unnecessary antibiotics and keep them safer and healthier.

Quick facts

Grant typeNIH-funded research
Study typeNIH-funded research
Funding institutionUniversity of Colorado Denver NIH-funded
Lab location1 site (Aurora, UNITED STATES)
Project IDNIH-10932411 on NIH RePORTER

What this research studies

This research aims to develop and validate machine learning tools that can help healthcare providers identify children who do not have serious bacterial infections when they are admitted to the pediatric intensive care unit (PICU). By analyzing electronic health records, including vital signs and lab results, the study seeks to improve antibiotic decision-making and reduce unnecessary antibiotic use, which can lead to harmful side effects. The research will involve testing these predictive models in multiple centers to ensure their effectiveness across different patient populations. Ultimately, the goal is to enhance patient safety and treatment outcomes for critically ill children.

Who could benefit from this research

Good fit: Ideal candidates for this research are children aged 0-11 years who are admitted to the pediatric ICU and are suspected of having serious bacterial infections.

Not a fit: Patients who are older than 11 years or those who do not require admission to the pediatric ICU may not benefit from this research.

Why it matters

Potential benefit: If successful, this research could significantly reduce the unnecessary use of antibiotics in critically ill children, minimizing the risk of adverse effects and antibiotic resistance.

How similar studies have performed: Previous research has shown promise in using machine learning models for similar predictive tasks, indicating that this approach could be effective.

Where this research is happening

Aurora, UNITED STATES

Researchers

About this research

  1. This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
  2. Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
  3. For full project details, budget, and progress reports, visit the official NIH RePORTER page below.
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.