Search

Background: Acute kidney injury (AKI) is a complication that occurs for various reasons after surgery, especially cardiac surgery. This complication can lead to a prolonged treatment process, increased costs, and sometimes death. Prediction of postoperative AKI can help anesthesiologists to implement preventive and early treatment strategies to reduce the risk of AKI. Objectives: This study tries to predict postoperative AKI using interpretable machine learning models. Methods: For this study, the information of 1435 patients was collected from multiple centers. The gathered data are in six categories: demographic characteristics and type of surgery, past medical history (PMH), drug history (DH), laboratory information, anesthesia and surgery information, and postoperative variables. Machine learning methods, including support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), random forest (RF), logistic regression, XGBoost, and AdaBoost, were used to predict postoperative AKI. Local interpretable model-agnostic explanations (LIME) and the Shapley methods were then leveraged to check the interpretability of models. Results: Comparing the area under the curves (AUCs) obtained for different machine learning models show that the RF and XGBoost methods with values of 0.81 and 0.80 best predict postoperative AKI. The interpretations obtained for the machine learning models show that creatinine (Cr), cardiopulmonary bypass time (CPB time), blood sugar (BS), and albumin (Alb) have the most significant impact on predictions. Conclusions: The treatment team can be informed about the possibility of postoperative AKI before cardiac surgery using machine learning models such as RF and XGBoost and adjust the treatment procedure accordingly. Interpretability of predictions for each patient ensures the validity of obtained predictions.

Objective This study was conducted to compare propofol dose requirements between patients with and without sleep quality disorder (SQD) in order to achieve the same depth of anesthesia. Methods In this comparative study, adult patients who were candidates for elective cataract surgery under general anesthesia in American Society of Anesthesiologists (ASA) class I or II were included. Using a validated questionnaire, patients were divided into two groups with Pittsburgh Sleep Quality Index (PSQI) higher and lower than five. Pre-induction with midazolam 0.02 mg/kg and fentanyl 2 µg/kg was administered 3 min before induction. Induction and 1-hour maintenance doses of propofol to achieve and maintain bispectral index score (BIS) 40–60 were measured and compared in the two groups. Results Seventy patients, 47 of which (67.1%) were female, with the mean age of 63.83 ± 10.67 years were enrolled; 35 in SQD group and 35 in normal group. Baseline and demographic characteristics were not significantly different between the two groups. BIS score after pre-induction was significantly lower in SQD group compared with normal group (p = 0.002). Propofol dose at the time of induction and also 1 hour after induction was significantly lower in SQD group compared to normal group (p Conclusion In the current study, induction and maintenance doses of propofol for general anesthesia were significantly lower in patients with SQD, in comparison with normal patients.