Prospective Validation of AKI Prediction

Prospective Validation of AKI Prediction Algorithm

The purpose of this prospective observational study is to implement, deploy, and quantify accuracy of an existing Pediatric Early AKI Risk Score algorithm. The implementation will be facilitated using a Health Level 7 (HL7) Fast Healthcare Interoperability Resource (FHIR)-based architecture. Investigators will deploy this model and store results in a manner not viewable to the clinical team caring for the patient. To determine the accuracy of the implemented prediction model, Investigators will prospectively identify patients with AKI at 72 hours following ICU admission. Investigators hypothesize that this model will prospectively detect AKI with a sensitivity >70% and a positive predictive value >20%, both chosen a priori as 10% improvement over the initial Pediatric AKI Risk Score tool.

Study Overview

• Status: Recruiting
• Conditions: Acute Kidney Injury

Detailed Description

This is a single-center prospective observational study validating an AKI predictive model. Each model feature will be mapped to an appropriate FHIR-based resource. To mitigate the latency issues seen in other distributed CDS systems, Investigators have developed an asynchronous design where algorithm calculations are performed offline (e.g., not within the EHR) and risk scores are subsequently written back to the EHR. Importantly, in this deployment, model output and resulting clinical risk score will not be communicated to the treating clinicians.

During the study period, Investigators will review charts daily for all patients admitted to the Golisano Children's Hospital PICU, a 12-bed facility adjacent to our 15-bed Pediatric Cardiac Intensive Care Unit (PCICU). Using a standard protocol to screen and identify patients by chart review, Investigators will generate a list of patients who meet AKI KDIGO criteria by SCr and urine output, along with recorded clinical information about these patients. At the conclusion of the study period, this list will be used as the "gold standard" and compared to the automated screening tool to determine the tool's test characteristics.

Model assessment outcomes include sensitivity, positive predictive value (PPV), and number needed to alert (NNA) to prospectively identify AKI in a population of critically ill children. Additional outcomes include timeliness of identification based on model implementation (e.g., measured timestamps of algorithm prediction compared to manual, prospectively identified AKI development). Additionally, Investigators will report interventions and clinical outcomes of the prospectively identified patients with AKI, stratified by those predicted early by the model (within 24 hours of admission) versus not.

• Study Type: Observational
• Enrollment (Estimated): 800

Contacts and Locations

• Study Contact: Name: Adam C Dziorny, MD, PhD; Phone Number: 585-276-3014; Email: adam_dziorny@urmc.rochester.edu

Study Locations

• United States
  • New York
    • Rochester, New York, United States, 14642
      • Recruiting
      • Golisano Children's Hospital at Strong

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

All medical and surgical patients admitted to the pediatric intensive care unit and pediatric cardiac intensive care unit.

Description

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

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Pediatric ICU Admissions; The study subjects are all patients admitted to the pediatric intensive care unit and the pediatric cardiac care unit at Golisano Children's Hospital at Strong. By virtue of admission to a pediatric hospital bed, all subjects will be children. The rationale for focusing on this population is that the developed algorithm focuses on identifying acute kidney injury among critically ill pediatric patients. The gender and age of subjects will not influence enrollment. To accurately determine algorithm test characteristics (sensitivity, PPV, NNA) pragmatically, Investigators must include all admitted patients. Missing patients may bias our results and invalidate the study.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Acute Kidney Injury (AKI) within the first 72 hours of ICU admission	Acute Kidney Injury (AKI) defined by KDIGO stages 1, 2, or 3, based on changes in serum creatinine levels or urine output (UOP), assessed within the first 72 hours of ICU admission. Stage 1 is defined by a 1.5 to 1.9 times baseline serum creatinine or an increase of ≥0.3 mg/dL. Stage 2 is a 2.0 to 2.9 times baseline increase, and Stage 3 is a 3.0 times baseline increase or a serum creatinine ≥4.0 mg/dL.	Within 72 hours following ICU Admission

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Prediction Accuracy and Timeliness of AKI Risk using a Predictive Model	Predictive model results generated prospectively (at 12 hours following admission) will be used to generate a 2x2 confusion matrix with prospectively identified AKI by serum creatinine or urine output changes based on KDIGO criteria. Investigators will calculate sensitivity, PPV, and NNA for the prospective identification of AKI. Investigators will report the time of AKI prediction compared to admission date and the onset date of AKI.	Within 12 hours of ICU Admission
Risk of Mortality in Patients with Acute Kidney Injury (AKI)	Investigators will assess for AKI independent risk of mortality at 28 days after adjusting for confounders.	28 Days following ICU admission

Collaborators and Investigators

• Sponsor: Adam C Dziorny
• Collaborators: National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK)

Study record dates

Study Major Dates

• Study Start (Actual): June 25, 2025
• Primary Completion (Estimated): June 1, 2026
• Study Completion (Estimated): June 1, 2026

Study Registration Dates

• First Submitted: January 27, 2025
• First Submitted That Met QC Criteria: January 27, 2025
• First Posted (Actual): February 3, 2025

Study Record Updates

• Last Update Posted (Actual): April 8, 2026
• Last Update Submitted That Met QC Criteria: April 7, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: Pediatrics; Critical Care; Machine Learning
• Additional Relevant MeSH Terms: Urogenital Diseases; Male Urogenital Diseases; Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Renal Insufficiency; Acute Kidney Injury
• Other Study ID Numbers: STUDY00008612; K23DK138299 (U.S. NIH Grant/Contract)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: Non-PHI data elements may be made available by request, per data sharing plan.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No