Prediction of postoperative acute kidney injury in patients undergoing off-pump coronary artery bypass…

AI / informaticsJournal of anesthesia and translational medicine· Sep 2026

Prediction of postoperative acute kidney injury in patients undergoing off-pump coronary artery bypass grafting: A machine learning model.

Sen Wang, Wenli Wang, Yuchen Bu … Yuanyuan Wang

Adult Cardiac SurgeryAI / informaticsQ2IF 1.6

Machine learning model predicts acute kidney injury after off-pump coronary bypass surgery

Prediction of postoperative acute kidney injury in patients undergoing off-pump coronary artery bypass grafting: A machine learning model.

Sen Wang … Yuanyuan Wang

Journal of anesthesia and translational medicine · Sep 2026

Background

The incidence of cardiac surgery-associated acute kidney injury (cardiac surgery-associated acute kidney injury) is 26.0%-28.5%.

Methods

This retrospective study analyzed 938 patients who underwent off-pump coronary artery bypass grafting from June 2023 to January 2025.

n = 938 patients

0.982

Results

0.982

correctly ranks acute kidney injury risk almost perfectly, 1.0 would be flawless

n = 938 patients

More results

Of the 938 patients, 210 (22.39%) developed OPCABG-AKI.

SHAP analysis identified Cystatin C (Cystatin C) as the top predictor, with NT-proBNP levels ranking second.

“

Conclusion · 1 of 2

The XGBoost model showed outstanding performance in predicting OPCABG-AKI. Selecting features from preoperative data and integrating them with intraoperative data significantly improved prediction accuracy.

Conclusion · 2 of 2

This model enables clinicians to stratify patient risks and make informed decisions regarding OPCABG-AKI, promoting early patient recovery.

Prediction of postoperative acute kidney injury in patients undergoing off-pump coronary artery bypass grafting: A machine learning model.

Prediction of postoperative acute kidney injury in patients undergoing off-pump coronary artery bypass grafting: A machine learning model.

Related papers