To identify risk factors for postoperative respiratory failure (PORF) in cardiovascular surgery patients using machine learning algorithms and to construct a specific risk prediction model.

A retrospective cohort was conducted on 1623 patients undergoing cardiovascular surgery between 2011 and 2020 from the INSPIRE database. Following data quality analysis, multiple imputation was employed to handle missing data, and the Boruta algorithm was used for feature selection. Eight machine learning models were constructed based on the selected features, including Gradient Boosting Machine (GBM), Generalized Linear Model (GLM), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), Neural Network (NNET), Naive Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF). Model performance was evaluated using metrics including the area under the curve (AUC), sensitivity, and specificity. Variables significantly influencing PORF were identified using the permutation importance algorithm.

The overall incidence of PORF was 27.05% (439/1623). The in-hospital mortality rate was significantly higher in the PORF group than the non-PORF group (12.98% vs 1.60%, P<0.001). Among the developed models, the SVM model demonstrated the best performance, achieving an AUC of 0.705 in the testing set, with a sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of 0.481, 0.825, 0.504, and 0.812, respectively. Based on feature importance analysis, the top 10 variables most predictive of PORF were anesthesia duration, arterial partial pressure of carbon dioxide (PaCO₂), calcium level, lymphocyte percentage, cardiopulmonary bypass duration, intraoperative blood loss, age, creatinine level, aspartate aminotransferase (AST) level, and activated partial thromboplastin time (aPTT).

A predictieon model for PORF following cardiovascular surgery is successfully developed. This model can identify high-risk patients and estimate their probability of developing respiratory failure, thereby facilitating data-driven clinical decision-making.

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.

Based on 2414 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 2143 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.

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 1850 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.

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 1850 mL, the risk of death significantly increases.