Development and validation of a clinical nomogram for predicting 30-day in-hospital mortality in children with moderate-to-severe traumatic brain injury - Report - MDSpire
Advertisement
Development and validation of a clinical nomogram for predicting 30-day in-hospital mortality in children with moderate-to-severe traumatic brain injury
Clinical Report: Nomogram for Predicting 30-Day Mortality in Pediatric TBI
Overview
This study developed a clinical nomogram to predict 30-day in-hospital mortality in pediatric patients with moderate-to-severe traumatic brain injury (msTBI). The model demonstrated strong predictive performance with an AUC of 0.898, incorporating key clinical variables.
Background
Traumatic brain injury (TBI) is a leading cause of death and disability in children, necessitating effective risk stratification tools. With a significant proportion of pediatric TBI cases classified as moderate-to-severe, early identification of high-risk patients is crucial for improving outcomes. Existing prediction models have limitations, highlighting the need for a robust tool like the nomogram developed in this study.
The nomogram predicts 30-day in-hospital mortality in pediatric msTBI patients.
Four independent predictors were identified: Glasgow Coma Scale score, lactic acid, albumin, and trauma-induced coagulopathy.
The model achieved an AUC of 0.898, indicating excellent predictive accuracy.
Good calibration was confirmed by a non-significant Hosmer-Lemeshow test (P = 0.475).
Clinical decision analysis indicated a threshold probability ranging from 0 to 0.95.
Clinical Implications
The nomogram serves as a valuable tool for clinicians to identify high-risk pediatric patients with msTBI, facilitating early intervention and tailored treatment strategies. By integrating key clinical variables, it enhances decision-making in acute care settings.
Conclusion
The developed nomogram provides a reliable method for predicting 30-day in-hospital mortality in children with msTBI, supporting improved clinical outcomes through early risk assessment.