Abstract: Objective: Construction of a nomogram prediction model for severe Mycoplasma pneumoniae pneumonia (MPP) with lobar consolidation in children based on CT imaging, as well as clinical and laboratory indicators within 24 hours of admission. Methods: A total of 618 children diagnosed with lobar MPP at Cangzhou Maternal and Child Health Hospital between February 2023 and October 2025 were enrolled as study participants. They were randomly assigned to a training set (n = 432) or a validation set (n = 186) at a ratio of 7︰3 using a simple randomization method. Independent factors for severe lobar MPP were identified using univariate and binary logistic stepwise regression analyses. Subsequently, a nomogram model was constructed, and its discrimination, calibration, and clinical net benefit were evaluated, followed by internal validation in the validation set. Results: Within 7 days of admission, the incidence of severe lobar MPP in the training set was 18.29% (79/432), and 17.20% (32/186) in the validation set. Lower pulse oxygen saturation; lower hsCRP, LDH, and DD levels and higher mean CT value of the consolidation area; higher density inhomogeneity index; as well as higher consolidation size grade at admission were independent risk factors for progression to severe lobar MPP in children. The nomogram prediction model for severe lobar MPP based on CT imaging features and quantitative parameters demonstrated good performance in both the training and validation sets, with AUC values of 0.927 (95% CI:0.895−0.960) and 0.895 (95% CI:0.826−0.964), respectively. Calibration curves indicated good agreement between predicted probabilities and actual outcomes (Hosmer-Lemeshow test P = 0.875 and 0.236, respectively), whereas decision curve analysis demonstrated that the model provided net clinical benefit across a wide range of threshold probabilities. Conclusion: The constructed nomogram model for severe MPP with lobar consolidation in children—based on CT imaging, clinical and laboratory indicators—enables early and precise identification of high-risk children. Additionally, it optimizes individualized treatment and allocation of medical resources.