Abstract
OBJECTIVE: Plastic bronchitis (PB) in children is a critical condition requiring prompt intervention. Early identification of high-risk patients is crucial for timely bronchoscopic management. This study aimed to develop and validate a novel nomogram model for the early prediction of PB risk in pediatric patients. METHODS: We conducted a retrospective analysis of clinical data from children with respiratory conditions. The cohort was divided into a training set (n = 326) and an independent validation set (n = 136). Univariate and multivariate logistic regression analyses were performed to identify independent risk factors for PB by comparing demographics, clinical symptoms, laboratory findings, and imaging features between groups. A predictive nomogram was subsequently constructed based on the results of the multivariate analysis. RESULTS: Multivariate analysis identified seven independent predictors of PB: elder age, longer cough duration, mycoplasma pneumoniae infection, atelectasis, lung consolidation, pleural effusion, and pleurisy. The nomogram demonstrated excellent discriminative ability, with an area under the receiver operating characteristic curve (AUC) of 0.920 in the training set and 0.929 in the validation set. Good calibration was confirmed by the Hosmer-Lemeshow test (p = 0.545). CONCLUSION: We successfully developed and validated a practical nomogram incorporating seven readily available clinical parameters. This model serves as a reliable and non-invasive tool for the early assessment of PB risk in children, potentially facilitating timely clinical decision-making and intervention.