Machine learning prediction of acute kidney injury after non-cardiac surgery
A Machine Learning Prediction Model for Postoperative Acute Kidney Injury in Non-Cardiac Surgery Patients: Development, Validation, and the Incremental Value of Frailty Assessment
Zhongda Hospital · NCT07030166
This project will try a computer-based model to predict which adults are at risk of acute kidney injury after non-cardiac surgery.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 10000 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Zhongda Hospital (other) |
| Locations | 1 site (Nanjing) |
| Trial ID | NCT07030166 on ClinicalTrials.gov |
What this trial studies
This observational project develops and validates a machine-learning model to predict acute kidney injury (AKI) after non-cardiac surgery using hospital electronic medical records. Retrospective data from adult patients who had non-cardiac surgery between July 2015 and June 2025 will serve as the development set, and prospective data collected from July 2025 to February 2026 will provide temporal external validation. The model will include routine clinical variables and add a frailty assessment as a new predictor to measure its incremental value. No interventions are applied; inclusion requires pre- and postoperative serum creatinine measurements and several renal- and surgery-related exclusions are enforced.
Who should consider this trial
Good fit: Ideal candidates are adults (≥18) undergoing non-cardiac surgery at the participating hospital who have both pre- and postoperative serum creatinine measurements.
Not a fit: Patients with recent dialysis-dependent end-stage renal disease, baseline creatinine ≥4.5 mg/dL, preoperative AKI within 7 days, renal surgery, missing creatinine measurements, or operations under 2 hours are unlikely to benefit.
Why it matters
Potential benefit: If successful, the model could identify high-risk patients so clinicians can apply preventive measures to reduce the chance or severity of postoperative AKI.
How similar studies have performed: Previous machine-learning models for postoperative AKI have shown promising results in retrospective cohorts, but externally validated models—especially those incorporating frailty—are still limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * 18 years old or above * Undergo non-cardiac surgery Exclusion Criteria: * At least one measurement of serum creatinine (SCr) was not conducted before and after the operation * End-stage renal disease (ESRD) that has received dialysis within the past year * Baseline SCr ≥ 4.5 mg/dl (because the clinical criteria for AKI based on elevated SCr may not be applicable to these patients) * Acute kidney injury occurred within 7 days before the operation * The surgical procedure is renal surgery * The operation time is less than 2 hours
Where this trial is running
Nanjing
- Zhongda Hospital Southeast University — Nanjing, China (RECRUITING)
Study contacts
- Study coordinator: Yue Lan Zhu
- Email: zhulanyue1993@126.com
- Phone: +8618795969178
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.
Conditions: Kidney Injury, Acute