Nomogram for prediction of in-hospital mortality rate in children with congenital heart disease in pediatric intensive care: establishment and external validation.

Abstract

Background: The incidence of congenital heart disease (CHD) has remained constant in recent years. The mortality rate is high in CHD patients admitted to the intensive care unit (ICU), but there is limited research on risk factors for in-hospital mortality. Therefore, the aim of this study was to identify risk factors for in-hospital mortality of CHD children in the ICU and develop a nomogram model to predict in-hospital mortality.

Methods: Patient demographics, comorbidities, surgical history, laboratory indicators, and in-hospital mortality were extracted from the paediatric intensive care unit (PICU) database. These patients were divided into training and validation cohorts in a 7:3 ratio. Variable selection was performed using single-factor Cox regression and stepwise Cox regression based on Akaike information criterion (AIC) in the training cohort. The selected variables were used to build a nomogram model, and calibration curves and receiver operator characteristic (ROC) curves were generated to evaluate the predictive performance of the model. Subsequently, an external validation was also carried out in the Medical Information Mart for Intensive Care III (MIMIC-III) database.

Results: A total of 2,231 patients were included in the analysis. Lymphocyte percentage [hazard ratio (HR): 1.097, 95% confidence interval (CI): 1.038-1.160], magnesium ion (HR: 1.002, 95% CI: 1.001-1.002), neutrophil percentage (HR: 1.111, 95% CI: 1.050-1.175), oxygen partial pressure (pO₂) (HR: 0.987, 95% CI: 0.981-0.993), partial thromboplastin time (HR: 1.033, 95% CI: 1.020-1.047), and ventricular septal defect repair surgery (HR: 0.117, 95% CI: 0.028-0.494) were identified as independent predictors and were used to construct the nomogram model. ROC curves showed that the model had good discriminative ability with area under the curves (AUCs) of 0.940, 0.857, and 0.776 for predicting in-hospital mortality at 7-, 14-, and 30-days in the training cohort, and AUCs of 0.921, 0.858, and 0.699 in the validation cohort, respectively. In the external dataset, the AUC of the model for predicting 7-, 14-, and 30-day in-hospital mortality were 0.732, 0.722, and 0.629, respectively. The calibration curves demonstrated favorable consistency of the model.

Conclusions: Neutrophil percentage in the model exhibits the strongest predictive power, followed by lymphocyte percentage and pO₂. The model shows favorable performance and can provide effective predictive information for clinical practitioners.