Effectiveness-Implementation Evaluation of Acute Kidney Injury Decision Support

NCT06840210 | Recruiting

• 2 other identifiers: IRB00367884R01HS027793
• Study Type: observational
• Target: 200,000
• Locations: 1 country
• Sites: 1

Brief Summary

Study Purpose: This study is testing an artificial intelligence (AI)-powered clinical decision support (CDS) system designed to help emergency department (ED) doctors detect and manage acute kidney injury (AKI) earlier. The goal is to see whether the tool improves patient care, clinician decision-making, and hospital outcomes when used in real-world ED settings. Study Design: The AI tool will be gradually introduced at three hospital EDs: Johns Hopkins Hospital (JHH) Bayview Medical Center (BMC) Howard County General Hospital (HCGH) Before the tool is activated, it will run in the background to collect baseline data without influencing care. Once implemented, doctors will receive training, and researchers will track how often the tool is used and whether it improves AKI care. What the Study Measures: Process Outcomes: Does the tool help doctors identify AKI sooner, avoid harmful medications, and improve decision-making about hospitalization? Clinical Outcomes: Does the tool reduce the number and severity of AKI cases and improve kidney-related health outcomes? Implementation Outcomes: Do ED doctors find the tool useful? Does it fit into the ED doctor's workflow without slowing the ED doctor's down? Expected Impact: If successful, the AI tool could be expanded to other hospitals and used to improve early detection and treatment of AKI, reducing kidney complications and improving patient care nationwide.

Conditions

Acute Kidney Injury

Keywords

Acute Kidney Injury; AKI; Prediction; Machine Learning; Emergency Department; Clinical Decision Support

Outcome Measures

Primary Outcomes (1)

• Number of Patients who receive Guideline-Concordant Kidney Care

  From time of decision support provision until departure from the ED, approximately 6 hours

Secondary Outcomes (2)

• New or Progressive Acute Kidney Injury

  Within 72 hours of first creatinine measurement in the ED

• Perceived usefulness and usability of AKIDS software as assessed by the System Usability Score

  Prior to AKIDS implementation, immediately after implementation, and post implementation 6 months

Study Arms (1)

All adult ED patients with creatinine concentration measured during the participant's ED stay

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Emergency Department

You may qualify if:

• Participants must meet all of the following conditions to be eligible for the study:
• Emergency Department Visit
• Patients presenting to one of the three study site emergency departments (EDs):
• Johns Hopkins Hospital (JHH) Bayview Medical Center (BMC) Howard County General Hospital (HCGH) Serum Creatinine Measurement
• At least one serum creatinine (sCr) test performed during the ED visit.
• Age: Adults (≥18 years old) at the time of ED visit.
• Follow-Up Data Available: To be included in analysis for the investigator's secondary effectiveness outcome (new or progressive AKI) patients must have repeat creatinine concentration measurement available within 72 hours

You may not qualify if:

• No ED Serum Creatinine Data: Patients who do not have a measured serum creatinine (sCr) value during the ED visit will not have decision support provided during the ED stay.
• Patients Discharged Without Follow-Up Data: Patients discharged from the ED who do not undergo a follow-up serum creatinine test within 72 hours will be excluded from analysis of new or progressive AKI outcome assessment.
• Age \<18 Years
• End-Stage Kidney Disease (ESKD) or Chronic Dialysis: Patients with a documented history of end-stage kidney disease (ESKD), (patients receiving chronic dialysis (hemodialysis or peritoneal dialysis) will will be excluded from analysis of new or progressive AKI outcome assessment).

Sponsors & Collaborators

• Johns Hopkins University: lead
• Agency For Healthcare Research & Quality: collaborator

Study Sites (1)

Johns Hopkins Hospital

Baltimore, Maryland, 21287, United States

RECRUITING

MeSH Terms

Conditions

Acute Kidney Injury; Emergencies

Condition Hierarchy (Ancestors)

Renal Insufficiency; Kidney Diseases; Urologic Diseases; Female Urogenital Diseases; Female Urogenital Diseases and Pregnancy Complications; Urogenital Diseases; Male Urogenital Diseases; Disease Attributes; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Officials

• Eili Klein, PhD

  Johns Hopkins University

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Eili Y Klein, PhD

CONTACT

732-266-7732; eklein@jhmi.edu

Michael Ehmann, MD

CONTACT

mehmann1@jhmi.edu

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 365 Days
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: February 17, 2025
• First Posted: February 21, 2025
• Study Start: March 10, 2026
• Primary Completion (Estimated): December 1, 2028
• Study Completion (Estimated): December 1, 2030
• Last Updated: April 20, 2026

Record last verified: 2026-04

Data Sharing

• IPD Sharing: Will not share

Locations

US (1)