Abstract: Objective To investigate the influencing factors associated with prognosis and their clinical significance in children with Mycoplasma pneumoniae pneumonia (MPP) complicated by plastic bronchitis (PB).Methods A retrospective study was conducted involving 204 children diagnosed with MPP complicated by PB at the Affiliated Hospital of Xuzhou Medical University from January 2023 to December 2025. According to pulmonary imaging findings and pulmonary function test results at the 3-month follow-up, the patients were divided into a good prognosis group and a poor prognosis group. Clinical manifestations, laboratory findings, and imaging characteristics were compared between the two groups. Multivariate logistic regression analysis and receiver operating characteristic (ROC) curve analysis were performed. In addition, 48 patients were enrolled for external validation.Results Univariate analysis showed that there were significant differences between the two groups in the presence of pleural effusion, duration of fever, disease course before bronchoscopy, C-reactive protein (CRP), D-dimer, lactate dehydrogenase (LDH), immunoglobulin E (IgE), interleukin-6 (IL-6), and systemic inflammation response index (SIRI) (all P<0.05). Multivariate analysis demonstrated that pleural effusion, D-dimer, and SIRI were independent risk factors for poor prognosis in children with MPP complicated by PB. ROC curve analysis showed that the area under the curve (AUC) values for predicting poor prognosis using pleural effusion, D-dimer, and SIRI alone were 0.639, 0.823, and 0.784, respectively. The AUC of the combined prediction model reached 0.871, with a sensitivity of 85.4% and a specificity of 75.0%. External validation showed that the model achieved an AUC of 0.854, with a sensitivity of 77.8% and a specificity of 90.0%. The Hosmer-Lemeshow goodness-of-fit test indicated stable predictive performance of the model (χ²=12.856, P=0.117).Conclusions Pleural effusion, D-dimer, and SIRI are risk factors associated with poor prognosis in children with MPP complicated by PB. The combined detection of these indicators provides superior predictive performance, and the prediction model demonstrates good stability.