Background: Respiratory syncytial virus (RSV) is a leading cause of severe lower respiratory tract infections in children, and early identification of high-risk patients is critical for improving outcomes. This study aimed to retrospectively study the clinical factors of children with severe RSV infection and, on this basis, develop and verify the nomogram model to identify independent risk factors for early prediction of children with severe RSV infection. Methods: This study retrospectively analyzed the clinical characteristics of children diagnosed with respiratory syncytial virus infection and divided the children into a severe group and a non-severe group. Based on five multiply imputed datasets, variable selection was performed using Elastic Net regression combined with clinical knowledge, and a multivariable logistic regression model was constructed. Internal validation was conducted using 500 bootstrap resamples to obtain optimism-corrected AUC and calibration slope, which was subsequently applied as a shrinkage factor to adjust regression coefficients for overfitting. Results: Of the 2595 children, 160 were in the severe group and 2435 were in the non-severe group. Five predictors were retained in the final model: Neutrophil-to-Lymphocyte Ratio (NLR), age, winter onset, hypoxemia, and preterm. The pooled area under the ROC curve was 0.847 (95% CI: 0.833– 0.860), and the optimism-corrected AUC after bootstrap validation was 0.843. The calibration slope was 0.975, indicating low overfitting risk after shrinkage correction. Conclusion: A nomogram incorporating five predictors (NLR, age, winter onset, hypoxemia, and preterm) was developed to predict severe RSV infection in children. Bootstrap internal validation showed good discrimination and indicated low overfitting. This tool can assist clinicians in timely identifying high-risk patients for early intervention. Keywords: respiratory syncytial virus, children, risk factors, nomogram, predicting
Li et al. (Wed,) studied this question.