Objective To investigate the early diagnostic value of urinary neutrophil gelatinase-associated lipocalin (NGAL) for acute kidney injury (AKI) after acute Stanford type A aortic dissection. Methods From January 2018 to December 2018, the clinical data of 50 patients who underwent open surgery for acute Stanford type A aortic dissection were analyzed in Nanjing First Hospital. Urine specimens were collected before and 2 hours after the aortic dissection surgery. Patients were divided into an AKI group (n=27) and a non-AKI group (n=23) according to the Kidney Disease Improving Global Outcomes criteria. Receiver operating characteristic (ROC) curve was used to evaluate the diagnostic value of urine NGAL. ResultsThe incidence of postoperative AKI was 54.00% (27/50). There was a statistically significant difference between the two groups in serum creatinine concentration at 2 hours after surgery and urinary NGAL concentration before the surgery (P<0.05). The area under ROC curve of preoperative urinary NGAL concentration was 0.626. When cut-off value was 43 ng/mL, the sensitivity was 40.7%, specificity was 95.7%. The area under ROC curve of urinary NGAL concentration at 2 hours after surgery was 0.655, and when the cut-off value was 46.95 ng/mL, the sensitivity was 63.0%, specificity was 78.3%. Conclusion Urine NGAL can predict postoperative AKI in patients with acute Stanford type A aortic dissection, but its value is limited.
ObjectiveTo construct a machine learning (ML) model incorporating preoperative, intraoperative, and early postoperative variables to predict cardiac surgery-associated acute kidney injury (CSA-AKI), thereby providing decision support for early clinical warning and intervention. MethodsPatients who underwent cardiac surgery at Nanjing Medical University Affiliated Nanjing Hospital from 2020 to 2022 were included in this study. The cohort was randomly divided into a training set and a validation set at a ratio of 7:3. Five ML models were constructed, including random forest (RF), logistic regression (LR), gradient boosted decision tree (GBDT), extreme gradient boosting (XGBoost), and support vector machines (SVM). Model performance was evaluated using metrics such as the area under the receiver operating characteristic curve (AUC), and the SHapley Additive exPlanations (SHAP) method was applied for model interpretation. ResultsA total of 3 679 patients were included, comprising 2 217 males and 1 462 females, with a median age of 64 (56, 70) years. Fifteen feature variables were incorporated: history of heart failure, age, body mass index, smoking history, creatinine, cardiopulmonary bypass time, total blood transfusion volume, total urine output, uric acid, hemoglobin, Acute Physiology and Chronic Health Evaluation Ⅱ (APACHE Ⅱ) score, European System for Cardiac Operative Risk Evaluation (EuroSCORE), postoperative white blood cell count, postoperative lactate, and postoperative lymphocyte count. Among the five ML models, LR, RF, GBDT, and XGBoost showed no statistical differences in performance within the validation set; however, considering the dimensions of performance, model robustness, and clinical interpretability, the LR model was deemed superior. SHAP analysis quantified the predictive weights of each variable (indicating that a history of heart failure and advanced age were high-risk features) and visually demonstrated the underlying causes of personalized risk for individual patients. Based on the optimized LR model, an online web-based risk calculator was successfully developed to output personalized probability of CSA-AKI occurrence. ConclusionA clinical prediction model for CSA-AKI risk is constructed using ML techniques, demonstrating favorable predictive performance and interpretability. This risk assessment tool can provide early warnings for clinicians and assist in optimizing postoperative treatment strategies, thereby reducing the risk of CSA-AKI occurrence.