Real-Time Acute Kidney Injury Perioperative Prediction Clinical Trial

Summary

This investigator-initiated, pragmatic trial evaluates whether displaying a machine learning (ML)- derived perioperative AKI risk score-alone or paired with an interruptive Best/Our Practice Advisory (BPA/OPA)-improves kidney-protective care and reduces kidney injury after non-obstetric surgery at UCSF. Approximately 75-100 attending anesthesiologists (clusters) are randomized 1:1:1 to: (a) Control (risk score hidden), (b) Score Only (visible preoperative AKI risk probability with passive KDIGO bundle recommendation), or (c) Score + BPA (visible risk plus interruptive KDIGO prompt for high-risk patients). CRNAs/residents follow their attending' s assignment. Adult inpatients (age ≥18) with expected overnight stay and eGFR ≥15 mL/min/1.73 m² are included; obstetrics, chronic dialysis, and kidney transplant patients are excluded. The underlying preoperative model was prospectively validated at UCSF and outperforms anesthesiologist risk estimation reported in the literature. The model was reviewed and approved by the AI Oversight Committee at UCSF. Primary endpoint is the continuous change in serum creatinine (mg/dL) from baseline to POD 1-2. Secondary outcomes include KDIGO-defined AKI, adherence to bundle elements (hemodynamics, balanced fluids, nephrotoxin avoidance, glycemic control), intraoperative hypotension time, fluid volumes, nephrotoxin exposure, perioperative hyperglycemia, length of stay, unplanned ICU transfer, readmission, dialysis, and in-hospital mortality. Data are obtained from the EHR; analysts are blinded. No direct subject interaction is planned; the investigators will request a waiver of patient consent. The study aims to demonstrate that ML-enabled, workflow-embedded decision support can safely and feasibly improve guideline concordant care and decrease early postoperative kidney injury.

Conditions

• Acute Kidney Injury
• Surgery Complications
• Anesthesia

Interventions

DEVICE

EHR-Embedded AKI Risk Score

A non-adaptive, machine learning-based clinical decision support tool integrated into the electronic health record that generates a preoperative probability of acute kidney injury (AKI) using routinely collected patient data. For patients identified as high risk, the tool displays the risk estimate to anesthesia providers without an accompanying Best Practice Advisory (BPA) recommending consideration of a KDIGO-based kidney-protective bundle. The intervention is advisory only, does not mandate clinical actions, and is designed to support provider decision-making within the existing clinical workflow.

DEVICE

EHR-Embedded AKI Risk Score with Best Practice Advisory

A non-adaptive, machine learning-based clinical decision support tool integrated into the electronic health record that generates a preoperative probability of acute kidney injury (AKI) using routinely collected patient data. For patients identified as high risk, the tool displays the risk estimate to anesthesia providers with an accompanying Best Practice Advisory (BPA) recommending consideration of a KDIGO-based kidney-protective bundle. The intervention is advisory only, does not mandate clinical actions, and is designed to support provider decision-making within the existing clinical workflow.

Sponsors & Collaborators

• National Institute of General Medical Sciences (NIGMS)

  collaborator NIH

• University of California, San Francisco

  lead OTHER

Principal Investigators

• Andrew Bishara, MD · University of California, San Francisco

Study Design

Allocation

RANDOMIZED

Purpose

SCREENING

Masking

NONE

Model

PARALLEL

Eligibility

Min Age

18 Years

Sex

ALL

Healthy Volunteers

Yes

Timeline & Regulatory

Start

2026-10-15

Primary Completion

2027-10-15

Completion

2027-12-15

FDA Device

Yes

Countries

• United States

Study Locations