Objectives <p>To explore the risk factors for mortality in pediatric intensive care unit (PICU) patients with pneumonia and to develop and validate a mortality risk prediction model.</p> Methods <p>A research cohort was established using a public database from a pediatric intensive care unit (PICU), including data from 467 cases. Univariable and multivariable logistic regression analyses were conducted to identify independent risk factors for mortality in pneumonia patients, and a prediction model was constructed based on these risk levels, resulting in a nomogram.</p> Results <p>A total of 351 cases were included for modeling, with 69 in-hospital deaths and 282 in-hospital survivors identified as outcomes. The analysis identified independent risk factors for mortality in pneumonia patients as age in months, white blood cell count, C-reactive protein (CRP), potassium ion concentration, total bilirubin and administration of glucocorticoids. The area under the curve (AUC) for the prediction model was 0.765 (95% CI: 0.705–0.825), with a sensitivity of 0.813 and specificity of 0.578; internal validation demonstrated that the model has good consistency.</p> Conclusions <p>A convenient model for predicting the mortality risk of children with pneumonia in PICU has been developed, showing a reasonable level of accuracy.</p>