Development and Validation of a Machine Learning Model for Predicting Serum Creatinine-Defined Acute Kidney Injury in Older Adults After Cardiac Surgery - PubMed
6 hours ago
- #acute kidney injury
- #machine learning
- #cardiac surgery
- Machine learning model LightGBM developed to predict acute kidney injury after cardiac surgery in older adults, achieving an AUC of 0.784.
- The model was validated internally and externally using data from multiple centers, with key predictors including lactate, surgical duration, APTT, transfusion volume, and PT.
- SHAP analysis was used to interpret the model's predictions, highlighting influential features and non-linear effects on risk.
- The study involved 177 patients developing CSA-AKI, aiming to assist in early risk stratification and perioperative management optimization.