Validation of a pediatric AKI prediction tool in the ICU
Prospective Validation of AKI Prediction Algorithm
This project will test whether a machine-learning pediatric AKI risk score can accurately predict acute kidney injury within 72 hours for children admitted to the PICU or PCICU.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 800 (estimated) |
| Ages | 30 Days to 18 Years |
| Sex | All |
| Sponsor | University of Rochester Academic / other |
| Locations | 1 site (Rochester, New York) |
| Trial ID | NCT06804200 on ClinicalTrials.gov |
What this trial studies
This single-center prospective observational effort implements an existing Pediatric Early AKI Risk Score using a FHIR-based architecture and an asynchronous offline calculation pipeline. Model outputs are written back to the EHR but are not shown to the treating clinical team. Investigators will conduct daily chart reviews to establish a gold-standard list of patients meeting KDIGO AKI criteria by creatinine and urine output and compare that list to the automated predictions. Primary outcomes include sensitivity, positive predictive value, and number needed to alert, with timeliness of detection also characterized.
Who should consider this trial
Good fit: Children older than 30 days and younger than 18 years who are admitted to the pediatric ICU or pediatric cardiac ICU, not discharged within 12 hours and without AKI at 12 hours of admission.
Not a fit: Patients already meeting AKI criteria within 12 hours of admission, those discharged very quickly, or children cared for outside the participating ICUs would not be expected to benefit from this deployment.
Why it matters
Potential benefit: If successful, the tool could detect AKI earlier in critically ill children, allowing faster treatment that may reduce kidney damage.
How similar studies have performed: Prior retrospective pediatric AKI risk scores have shown promise, but prospective, blinded FHIR-based deployments like this remain relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patients admitted to the Pediatric Intensive Care Unit or Pediatric Cardiac Intensive Care Unit * Age \> 30 days and \< 18 years Exclusion Criteria: * Discharged less than 12 hours after admission * AKI at 12 hours of admission by KDIGO Serum Criteria
Where this trial is running
Rochester, New York
- Golisano Children's Hospital at Strong — Rochester, New York, United States (Recruiting)
Study contacts
- Study coordinator: Adam C Dziorny, MD, PhD
- Email: adam_dziorny@urmc.rochester.edu
- Phone: 585-276-3014
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.