Development and Evaluation of a Risk Prediction Model for Intrahospital Transport Adverse Events in Critically Ill Gynecological Patients

Objective: To develop and evaluate a risk prediction model for intrahospital transport adverse events in critically ill gynecological patients, providing a scientific basis for early identification of high-risk individuals and optimization of transport decision-making. Methods: A retrospective observational cohort study was conducted, including 650 patients who underwent intrahospital interdepartmental transport. Patients were randomly assigned in a 7:3 ratio to a model training set (455 patients) and an internal validation set (195 patients). Data collected included patient demographics, pre-transport condition assessment indicators, transport process parameters, and adverse event occurrences. Potential predictive variables were identified through univariate analysis and least absolute shrinkage and selection operator (LASSO) regression, followed by multivariate Logistic regression to construct the risk prediction model. Model discrimination was evaluated using the receiver operating characteristic (ROC) curve, calibration was assessed by the Hosmer-Lemeshow test, and clinical utility was evaluated via decision curve analysis (DCA). Results: Baseline characteristics were comparable between the training and validation sets (all P>0.05). Multivariate analysis identified mechanical ventilation, Sequential Organ Failure Assessment (SOFA) score, Modified Early Warning Score (MEWS), and transport duration (minutes) as independent predictors of intrahospital transport adverse events in critically ill gynecological patients. Calibration curves demonstrated high consistency between predicted probabilities and observed outcomes, and the Hosmer-Lemeshow test indicated good calibration. Conclusion: The developed risk prediction model for intrahospital transport adverse events in critically ill gynecological patients demonstrates good discrimination and calibration. This study may provide a quantitative tool to support safe intrahospital transport management.