NCT07030166

A Machine Learning Prediction Model for Postoperative Acute Kidney Injury in Non-Cardiac Surgery Patients

A Machine Learning Prediction Model for Postoperative Acute Kidney Injury in Non-Cardiac Surgery Patients: Development, Validation, and the Incremental Value of Frailty Assessment

• Status: Recruiting
• Phase: —
• Study type: Observational
• Enrollment: 10,000 (estimated)
• Sponsor: Lanyue Zhu · Academic / Other
• Sex: All
• Age: 18 Years
• Healthy volunteers: Not accepted

Summary

Primary objectives of this study is to develop and validate a predictive model for acute kidney injury after non-cardiac surgery based on machine learning. Secondary objectives of this study is to incorporate frailty assessment as a new predictor into the model and measure its incremental value was measured.

Detailed description

The data in this study are divided into two parts: retrospective and prospective. The retrospective data served as the development set, sourced from the electronic medical records of adult patients who underwent non-cardiac surgery during hospitalization between July 2015 and June 2025. The prospective data constituted an external (temporal) validation set, with data collection commencing in July 2025 and expected to conclude in February 2026.

Conditions

• Kidney Injury, Acute

Interventions

Type	Name	Description
OTHER	No intervention measures were used.	The exposure factors were the perioperative related operations experienced by the patients and their individual conditions

Timeline

• Start date: 2025-07-01
• Primary completion: 2026-12-31
• Completion: 2026-12-31
• First posted: 2025-06-22
• Last updated: 2026-04-02

Locations

1 site across 1 country: China