Objective Patients with chronic liver diseases often exhibit unique hemodynamic abnormalities and metabolic disorders.Postoperative fluid management presents numerous challenges,especially for critically ill patients admitted to the intensive care unit(ICU)after surgery.This study aimed at exploring the relationship between postoperative fluid therapy and prognosis.Methods Based on 2 414 patients with chronic liver diseases who underwent surgical treatment and were subsequently transferred to the ICU in the MIMIC-IV database,a retrospective cohort study was conducted on the final 2 143 patients after our inclusion and exclusion criteria.Multivariate adjusted logistic regression model was used to analyze the association between fluid therapeutic regimens on the first day after ICU admission and the risk of 7-day death after surgery.Restricted cubic spline(RCS)was applied to analyze the dose-response relationship.Results Multivariate analysis indicated that restrictive fluid resuscitation was an independent protective factor.Compared with the non-restrictive fluid resuscitation group,restrictive fluid resuscitation significantly reduced the 7-day postoperative mortality rate(6.4％vs 12.4％,OR=0.44,95％CI:0.22～0.88,P=0.021),decreased the use of mechanical ventilation(42.9％vs 72.3％,OR=0.29,95％CI:0.24～0.35,P<0.001),and shortened the ICU stay(1.86 vs 3.47 d,OR=0.81,95％CI:0.78～0.84,P<0.001).RCS curve showed that the fluid intake on the first postoperative day and the 7-day postoperative mortality risk presented a J-shaped curve relationship,with an inflection point at 1 850 mL.Beyond this threshold,the 7-day postoperative mortality risk was increased.Subgroup analysis results indicated that the protective effect of restrictive fluid resuscitation was consistent across different age and comorbidity groups.Conclusion For patients with chronic liver diseases,adopting a restrictive fluid therapy on the first day after surgery can effectively reduce the risk of short-term death.Moreover,there is a non-linear dose-effect relationship between the fluid intake and the 7-day mortality risk.When the fluid intake exceeds 1 850 mL,the risk of death significantly increases.

Objective To develop a personalized recommendation strategy for tranexamic acid administration during the perioperative period of orthopedic surgery based on machine learning,aiming to reduce perioperative bleeding and related complications and improving clinical outcomes.Methods A total of 11 727 patients undergoing orthopedic surgery from the INSPIRE database were subjected in this study.Missing data were handled using multiple imputation methods,and relevant feature variables were screened using Boruta analysis.We constructed various machine learning models,including Gradient Boosting Machine(GBM),Generalized Linear Model(GLM),eXtreme Gradient Boosting(XGBoost),K-Nearest Neighbors(KNN),Neural Network(NNET),Naive Bayes(NB),and Random Forest(RF),to evaluate their performance in predicting intraoperative bleeding and prolonged postoperative length of hospital stay.The optimal model was then selected and further integrated using a weighted ensemble,aiming to achieve the best prognosis by recommending usage strategies for tranexamic acid.The predictive performance of the constructed model was then verified against the testing set,and compared with the physician decision-making to complete the evaluation.Results In predicting intraoperative bleeding,the RF model achieved an area under the receiver operating characteristic curve(AUC)of 0.73,which was significantly better than other models.In predicting the prolonged postoperative length of hospital stay,the XGBoost model performed the best,with an AUC value of 0.84.Based on the above best-performing models,an ensemble strategy was implemented.The patients who followed the recommended strategy had reduced intraoperative bleeding and shorter postoperative length of hospital stay.Conclusion The use of tranexamic acid is associated with intraoperative bleeding and postoperative length of hospital stay.Personalized decision-making recommendation based on our constructed model can effectively improve the outcomes of the patients undergoing orthopedic surgery.