A Rapid Diagnostic of Risk in Hospitalized Pediatric Patients to Improve Outcomes Using Machine Learning
University of Wisconsin, Madison
Summary
This is a study comparing 3 years of retrospective data (pre-implementation) to 2 years of prospective data after the implementation of a pediatric version of Electronic Cardiac Arrest Risk Triage (pediatric eCART), a clinical decision support (CDS) tool that uses electronic health records (EHR) to identify patients with high risk for life threatening outcomes. Up to 30,000 encounters with pediatric patients will be assessed. Acceptability of the pediatric eCART intervention will also be measured from pediatric nurse clinicians.
Description
Pediatric eCART draws upon readily available EHR data and rapidly quantifies disease severity, predicting the likelihood of critical illness onset. Currently, no consistently available system continuously tracks the risk of critical illness in children admitted to UW Health. While AFCH has an implementation of Pediatric Early Warning Scores (PEWS) available for risk monitoring, internal reports indicate limited usage. Therefore, AFCH/UW Health clinicians or care providers do not have a reliable mechanism to risk-stratify patients for effective clinical decision-making. This proposal leverages…
Eligibility
- Age range
- Up to 17 years
- Sex
- All
- Healthy volunteers
- No
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…
Interventions
- DevicePediatric eCART
Integration of the pediatric version of electronic Cardiac Arrest Risk Triage as a clinical decision support tool within Epic for use by clinicians
Location
- American Family Children's HospitalMadison, Wisconsin