Objective: To develop and validate a risk prediction model for catheter-related thrombosis (CRT) in pediatric patients with severe traumatic brain injury (sTBI). Methods: Using convenience sampling, 216 pediatric patients with sTBI admitted to the Surgical Intensive Care Unit of Kunming Children’s Hospital between June 2022 and May 2025 were enrolled and randomly divided into a training set of 151 cases and a validation set of 65 cases. Influencing factors were identified through univariate analysis and logistic regression analysis to construct the prediction model. The model’s discrimination and calibration were evaluated by the area under the receiver operating characteristic (ROC) curve (AUC) and the Hosmer–Lemeshow goodness-of-fit test. Results: Univariate analysis showed that admission GCS score, CVC insertion site, D-dimer level, and duration of mechanical ventilation were risk factors for CRT in children with sTBI (P < 0.05). The logistic regression equation was constructed as follows: Logit(P) = 2.74 – 1.95 × GCS score + 0.25 × D-dimer (μg/mL) + 0.02 × duration of mechanical ventilation (h). Based on this model, the AUC was 0.87 in the training set and 0.88 in the validation set. The Hosmer–Lemeshow goodness-of-fit test indicated good agreement between the model’s calibration curve and the ideal curve. Conclusion: The developed prediction model demonstrates good predictive performance and can serve as a reference for the early clinical identification of CRT risk in pediatric patients with sTBI.