Development and External Validation of a Machine Learning Model Based on Preoperative Nutritional Status for Predicting Acute Kidney Injury After Coronary Artery Bypass Grafting

This study shows that poor preoperative nutritional status—especially low PNI—is an independent predictor of acute kidney injury after CABG. A machine learning model (GBM) combining nutritional and clinical factors achieved high predictive accuracy and enables individualized risk assessment.