Real-Time Acute Kidney Injury Perioperative Prediction Clinical Trial

Official title

Prediction of Acute Kidney Injury (AKI) After Surgery: A Pragmatic Three-Arm Cluster-Randomized Trial

Overview

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.

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 c
• 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 clin

Primary outcome measures

• Post-operative Change in Creatinine [Time frame: From pre-operative baseline to 1-2 days post-operative level]

Secondary outcome measures (12)

• Acute Kidney Injury [Time frame: Operation to Post-operative Day 7]
• KDIGO Bundle Adherence [Time frame: Intra-operative]
• Intra-Operative Time and Severity of Hypotension [Time frame: Intra-operative]
• Total intra-operative intravenous fluid volume administered (mL) [Time frame: Intra-operative]
• Length of Stay [Time frame: Operation to Post-operative Day 180]
• Intra-operative Hyperglycemic Events [Time frame: Intra-operative]
• Intra-operative Nephrotoxin Exposure [Time frame: Intra-operative]
• In-Hospital Mortality [Time frame: Operation to Post-operative Day 180]
• ICU Transfer and total time in the ICU [Time frame: Postoperative]
• Hospital Readmission [Time frame: Operation to Post-operative Day 180]
• Dialysis Requirement [Time frame: Operation to Post-operative Day 180]
• Dilution Corrected KDIGO AKI measurement (Stage 1 or higher) [Time frame: AKI is defined per KDIGO as corrected creatinine increase ≥0.3 mg/dL within 48 hours or ≥1.5× baseline within 7 days. This measure captures "hidden AKI" - kidney injury masked by fluid dilution that would be missed using standard uncorrected creatinine.]

Eligibility criteria

Inclusion criteria

• Adults ≥18 years undergoing non-obstetric surgery at UCSF.
• Inpatient cases with expected overnight stay.
• Baseline eGFR ≥15 mL/min/1.73 m².
• Managed by an attending anesthesiologist randomized to one of three arms (CRNAs/residents follow attending).
• Data available in the UCSF EHR for risk scoring and outcomes.

Exclusion criteria

• Obstetric procedures.
• Chronic dialysis patients.
• Kidney transplant recipients.
• Cases without baseline creatinine/eGFR or missing essential EHR elements needed for scoring/outcomes (operational exclusions).
• Outpatient procedures without expected overnight stay.

Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.

Healthy volunteers: Yes

Study design

Allocation

Randomized

Model

Parallel assignment

Masking

Open label

Primary purpose

Screening

Study locations

United States · 1 center

• University of California, San Francisco — San Francisco

Publications

• James MT, Dixon E, Tan Z, Mathura P, Datta I, Lall RN, Landry J, Minty EP, Samis GA, Winkelaar GB, Pannu N. Stepped-Wedge Trial of Decision Support for Acute Kidney Injury on Surgical Units. Kidney Int Rep. 2024 Jul 31;9(10):2996-3005. doi: 10.1016/j.ekir.2024.07.025. eCollection 2024 Oct. PMID 39430177
• Zarbock A, Kullmar M, Ostermann M, Lucchese G, Baig K, Cennamo A, Rajani R, McCorkell S, Arndt C, Wulf H, Irqsusi M, Monaco F, Di Prima AL, Garcia Alvarez M, Italiano S, Miralles Bagan J, Kunst G, Nair S, L'Acqua C, Hoste E, Vandenberghe W, Honore PM, Kellum JA, Forni LG, Grieshaber P, Massoth C, Weiss R, Gerss J, Wempe C, Meersch M. Prevention of Cardiac Surgery-Associated Acute Kidney Injury by PMID 33684086
• Khwaja A. KDIGO clinical practice guidelines for acute kidney injury. Nephron Clin Pract. 2012;120(4):c179-84. doi: 10.1159/000339789. Epub 2012 Aug 7. No abstract available. PMID 22890468
• Walsh M, Devereaux PJ, Garg AX, Kurz A, Turan A, Rodseth RN, Cywinski J, Thabane L, Sessler DI. Relationship between intraoperative mean arterial pressure and clinical outcomes after noncardiac surgery: toward an empirical definition of hypotension. Anesthesiology. 2013 Sep;119(3):507-15. doi: 10.1097/ALN.0b013e3182a10e26. PMID 23835589
• Sun LY, Wijeysundera DN, Tait GA, Beattie WS. Association of intraoperative hypotension with acute kidney injury after elective noncardiac surgery. Anesthesiology. 2015 Sep;123(3):515-23. doi: 10.1097/ALN.0000000000000765. PMID 26181335
• Kork F, Balzer F, Spies CD, Wernecke KD, Ginde AA, Jankowski J, Eltzschig HK. Minor Postoperative Increases of Creatinine Are Associated with Higher Mortality and Longer Hospital Length of Stay in Surgical Patients. Anesthesiology. 2015 Dec;123(6):1301-11. doi: 10.1097/ALN.0000000000000891. PMID 26492475
• Fujii T, Takakura M, Taniguchi T, Tamura T, Nishiwaki K. Intraoperative hypotension affects postoperative acute kidney injury depending on the invasiveness of abdominal surgery: A retrospective cohort study. Medicine (Baltimore). 2023 Dec 1;102(48):e36465. doi: 10.1097/MD.0000000000036465. PMID 38050260

Identifiers

NCT: NCT07604662 · 22-37005 · K23GM151611-03

Primary sources (government registries)

• ClinicalTrials.gov (US NIH)

View this study on ClinicalTrials.gov ↗