Objective To develop and compare the predictive performance of five machine learning models for adverse postoperative outcomes in cardiac surgery patients, and to identify key decision factors through SHapley Additive exPlanations (SHAP) interpretability analysis. Methods A retrospective collection of perioperative data (including demographic information, preoperative, intraoperative, and postoperative indicators) with 88 variables was conducted from adult cardiac surgery patients at the First Affiliated Hospital of Xinjiang Medical University in 2023. Adverse postoperative outcomes were defined as the occurrence of acute kidney injury and/or in-hospital mortality during the postoperative hospitalization period following cardiac surgery. Patients were divided into an adverse outcome group and a favorable outcome group based on the presence of adverse postoperative outcomes. After screening feature variables using the least absolute shrinkage and selection operator (LASSO) regression method, five machine learning models were constructed: eXtreme gradient boosting (XGBoost), random forest (RF), gradient boosting machine (GBM), light gradient boosting machine (LightGBM), and generalized linear model (GLM). The dataset was randomly divided into a training set and a test set at a 7 : 3 ratio using stratified sampling, with postoperative outcome as the stratification factor. Model performance was evaluated using receiver operating characteristic curves, decision curve analysis, and F1 Score. The SHAP method was applied to analyze feature contribution. Results A total of 639 patients were included, comprising 395 males and 244 females, with a median age of 62 (55, 69) years. The adverse outcome group consisted of 191 patients, while the favorable outcome group included 448 patients, resulting in an adverse postoperative outcome incidence of 29.9%. Univariate analysis showed no significant differences between the two groups for any variables (P>0.05). Using LASSO regression, 16 feature variables were selected (including cardiopulmonary bypass support time, blood glucose on postoperative day 3, creatine kinase-MB isoenzyme, systemic inflammatory response index, etc.), and five machine learning models (GLM, RF, GBM, LightGBM, XGBoost) were constructed. Evaluation results demonstrated that the XGBoost model exhibited the best predictive performance on both the training set (n=447) and test set (n=192), with area under the curve values of 0.761 [95%CI (0.719, 0.800) ] and 0.759 [95%CI (0.692, 0.818) ], respectively. It also significantly outperformed other models in positive predictive value, and balanced accuracy in the test set. Decision curve analysis further confirmed its clinical utility across various risk thresholds. SHAP analysis indicated that variables such as cardiopulmonary bypass support time, blood glucose on postoperative day 3, creatine kinase-MB isoenzyme, and inflammatory markers (SIRI, NLR, CAR) had high contributions to the prediction. Conclusion The XGBoost model effectively predicts adverse postoperative outcomes in cardiac surgery patients. Clinically, attention should be focused on cardiopulmonary bypass support time, postoperative blood glucose control, and monitoring of inflammatory levels to improve patient prognosis.

Objective:To explore the effect of holistic nursing combined with heat preservation nursing in patients undergoing thoracoscopic lung wedge resection.Methods:From April 2020 to March 2021, convenience sampling was used to select 196 patients who underwent thoracoscopic wedge resection for lung cancer in the First Affiliated Hospital of Xinjiang Medical University as the research object. The patients were divided into the observation group and the control group by the order of admission, 98 cases in each group. The patients in the control group were given routine nursing, and the patients in the observation group were given holistic nursing combined with heat preservation nursing on the basis of the control group. The visual analogue scale (VAS) was used to evaluate the postoperative pain of the two groups of patients, and the transfer time to and from the Resuscitation Room, postoperative recovery time and hospital stay were compared between the two groups. The incidence of postoperative adverse reactions in the two groups was recorded and compared.Results:The VAS scores of the observation group at 1 and 12 hours after operation were (2.06±0.52) and (2.46±0.81) respectively, which were lower than those of the control group [ (3.72±1.10) and (4.06±0.78) ], and the differences were statistically significant ( P<0.05) . The postoperative recovery time, hospital stay, and transfer time to and from the Resuscitation Room of the observation group were (56.34±10.10) min, (7.12±1.17) d, (2.10±0.32) min, and (2.52±0.50) min, respectively, lower than those of the control group, and the differences were statistically significant ( P<0.05) . The incidence of adverse reactions in the observation group (4.08%) was lower than that in the control group (22.45%) , and the difference was statistically significant ( P<0.05) . Conclusions:Holistic nursing combined with heat preservation nursing can speed up the postoperative recovery, reduce the incidence of adverse reactions, relieve postoperative pain, and facilitate postoperative recovery of patients undergoing thoracoscopic lung wedge resection.

Objective To investigate the value of prothrombotic state (PTS) in prediction of perioperative cardiac events in elderly patients with coronary heart disease undergoing noncardiac surgery.Methods One-hundred and twenty-eight ASA physical status Ⅰ or Ⅱ elderly patients (NYHA class Ⅰ or Ⅱ) of both sexes,aged 6575 yr,undergoing elective abdominal surgery,were enrolled in the study.Total intravenous anesthesia was performed during surgery.Venous blood samples were collected for detection of the levels of D-dimer,thrombus precursor protein and P-selectin (molecular markers of PTS).Detection of PTS was based on the three indexes mentioned above.The patients were divided into 2 groups according to the cardiac events occurred during surgery and within 3 days after surgery:non-cardiac event group and cardiac event group.The general data of patients and each index during surgery were recorded.Logistic regression analysis was used to pick out the potential risk factors for cardiac events.Results Twenty-nine patients developed cardiac events.There was no significant difference in age,obesity,ratio of diabetes,duration of operation,and ratio of PTS between non-cardiac event and cardiac event groups (P ＜ 0.05 or 0.01).Logistic regression analysis showed that old age,diabetes,prolonged duration of operation,and PTS were independent risk factors for cardiac events (P ＜ 0.01).Conclusion PTS produces some value in prediction of perioperative cardiac events in elderly patients with coronary heart disease undergoing noncardiac surgery.