BackgroundRheumatic heart disease (RHD) accounts for a large proportion of Intensive Care Unit (ICU) deaths. Early prediction of RHD can help with timely and appropriate treatment to improve survival outcomes, and the XGBoost machine learning technology can be used to identify predictive factors; however, its use has been limited in the past. We compared the performance of logistic regression and XGBoost in predicting hospital mortality among patients with RHD from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database.MethodsThe patients with RHD in the MIMIC-IV database were divided into two groups retrospectively according to the availability of data and its clinical significance based on whether they survived or died. Backward stepwise regression was used to analyze the independent factors influencing patients with RHD, and to compare the differences between the two groups. The XGBoost algorithm and logistic regression were used to establish two prediction models, and the areas under the receiver operating characteristic curves (AUCs) and decision-curve analysis (DCA) were used to test and compare the models. Finally, DCA and the clinical impact curve (CIC) were used to validate the model.ResultsData on 1,634 patients with RHD were analyzed, comprising 207 who died during hospitalization and 1,427 survived. According to estimated results for the two models using AUCs [0.838 (95% confidence interval = 0.786–0.891) and 0.815 (95% confidence interval = 0.765–0.865)] and DCA, the logistic regression model performed better. DCA and CIC verified that the logistic regression model had convincing predictive value.ConclusionsWe used logistic regression analysis to establish a more meaningful prediction model for the final outcome of patients with RHD. This model might be clinically useful for patients with RHD and help clinicians to provide detailed treatments and precise management.

Background: Ventilator-associated pneumonia (VAP) is the most widespread and life-threatening nosocomial infection in intensive care units (ICUs). The duration of antibiotic use is a good predictor of prognosis in patients with VAP, but the ideal duration of antibiotic therapy for VAP in critically ill patients has not been confirmed. Research is therefore needed into the optimal duration of antibiotic use and its impact on VAP.Methods: The Medical Information Mart for Intensive Care database included 1,609 patients with VAP. Chi-square or Student’s t-tests were used to compare groups, and Cox regression analysis was used to investigate the factors influencing the prognoses of patients with VAP. Nonlinear tests were performed on antibiotic use lasting <7, 7–10, and >10 days. Significant factors were included in the model for sensitivity analysis. For the subgroup analyses, the body mass indexes (BMIs) of patients were separated into BMI <30 kg/m2 and BMI ≥30 kg/m2, with the criterion of statistical significance set at p < 0.05. Restricted cubic splines were used to analyze the relationship between antibiotic use duration and mortality risk in patients with VAP.Results: In patients with VAP, the effects of antibiotic use duration on the outcomes were nonlinear. Antibiotic use for 7–10 days in models 1–3 increased the risk of antibiotic use by 2.6020-, 2.1642-, and 2.3263-fold relative to for >10 days, respectively. The risks in models 1–3 for <7 days were 2.6510-, 1.9933-, and 2.5151-fold higher than those in models with >10 days of antibiotic use, respectively. These results were robust across the analyses.Conclusions: The duration of antibiotic treatment had a nonlinear effect on the prognosis of patients with VAP. Antibiotic use durations of <7 days and 7–10 days both presented risks, and the appropriate duration of antibiotic use can ensure the good prognosis of patients with VAP.