Abstract
The objective of this study was to develop a nomogram model for the prediction of severe Mycoplasma pneumoniae pneumonia (SMPP) in children and adolescent. Through multivariate analysis, a total of six predictors, namely gender, PCR result, cough days, Neutrophil (N), hemoglobin (Hb), and platelet (PLT) were identified. These predictors were then incorporated into a nomogram to estimate the likelihood of developing SMPP. The nomogram exhibited favorable predictive accuracy, as evidenced by a C-index of 0.865. Moreover, and the discriminative ability of the nomogram was validated through ROC analysis, yielding an AUC value of 0.865. Furthermore, the clinical utility of the nomogram was evaluated by employing DCA curves, which demonstrated its efficacy in predicting the occurrence of severe pneumonia. Additionally, mediation analysis elucidated that cough days, N and PLT partially mediated the relationship between PCR result and the development of SMPP. In summary, our findings indicate that the nomogram holds significant potential as a valuable predictive tool for clinicians in the context of SMPP.