Pediatric eCART: an electronic tool to spot children at high risk of critical illness

A Rapid Diagnostic of Risk in Hospitalized Pediatric Patients to Improve Outcomes Using Machine Learning

Not applicable Interventional University of Wisconsin, Madison · NCT06771830

This project will test whether implementing pediatric eCART, an EHR-based risk alert system, helps identify hospitalized children at high risk of life-threatening deterioration and is acceptable to pediatric nurses.

Quick facts

PhaseNot applicable
Study typeInterventional
Enrollment30000 (estimated)
AgesN/A to 17 Years
SexAll
SponsorUniversity of Wisconsin, Madison Academic / other
Locations1 site (Madison, Wisconsin)
Trial IDNCT06771830 on ClinicalTrials.gov

What this trial studies

Researchers will compare three years of retrospective pediatric inpatient data before implementation to two years of prospective data after deploying pediatric eCART at American Family Children's Hospital, examining up to 30,000 encounters. Pediatric eCART applies a machine-learning model to routine electronic health record data and is delivered via the AgileMD clinical decision support engine to continuously quantify risk of clinical deterioration. The study will measure outcomes such as timing of ICU transfer, morbidity, mortality, and nurse acceptability of the intervention. Neonates and birth encounters are excluded and the focus is on UW Health inpatient locations.

Who should consider this trial

Good fit: Children under 18 admitted to inpatient units at UW Health who are eligible for pediatric eCART scoring (excluding neonates and birth encounters) are the target participants.

Not a fit: Newborns and birth encounters, patients not eligible for eCART scoring, and patients cared for only in outpatient settings are unlikely to benefit from this intervention.

Why it matters

Potential benefit: If successful, pediatric eCART could help clinicians detect deterioration earlier, enabling timelier ICU care and potentially reducing morbidity and mortality among hospitalized children.

How similar studies have performed: Preliminary implementation at the University of Chicago reported improved outcomes with pediatric eCART, but broader multisite validation is still limited.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria (pediatric patients):

* All pediatric patients scored on pediatric eCART (or eligible for scoring on either algorithm in the pre-implementation period) will be screened for study eligibility.
* Patients eligible for pediatric eCART scoring include pediatric (\<18 years of age) patients
* Inpatient locations

Exclusion Criteria (pediatric patients):

* Patients who are ineligible for pediatric eCART scoring
* Neonates and birth encounters will be excluded from the pediatric eCART study

Inclusion Criteria (nurse clinicians):

* UW Health nurses who interact with eCART during patient care

Exclusion Criteria (nurse clinician):

* UW Health nurses no longer employed at UW Health

Where this trial is running

Madison, Wisconsin

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Pediatric ALLSepsismachine learningartificial intelligenceclinical decision supporttriageelectronic medical records
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.