Early prediction of clinically important progression in children with traumatic intracranial hemorrhage treated at a high-altitude tertiary hospital: a single-center retrospective study

Background Early identification of clinically important progression in children with traumatic intracranial hemorrhage (tICH) remains challenging, particularly in high-altitude settings. This study aimed to develop and internally validate a prediction model integrating clinical, radiological, oxygenation, and coagulation indicators. Methods This single-center retrospective cohort study included 584 children with CT-confirmed tICH admitted between January 2016 and December 2025. The primary outcome was clinically important in-hospital progression, comprising radiological progression, neurosurgical intervention, TBI-related neurological deterioration, or TBI-related death. Predictors were selected using 10-fold cross-validated LASSO regression. Model performance was evaluated using discrimination, calibration, Brier scores, and decision curve analysis, with internal validation using 1,000 bootstrap resamples. Additional analyses assessed performance across age and GCS severity groups and compared the model with the Rotterdam CT score. Results Clinically important progression occurred in 78 patients (13.4%). The final model included seven predictors: GCS ≤8, seizures or recurrent vomiting, mixed hemorrhagic lesions, maximum hematoma thickness, SpO 2 < 90%, PLT <150 × 10 9 /L, and INR >1.2. The apparent AUC was 0.845 (95% CI 0.792–0.898), with an optimism-corrected AUC of 0.821 and Brier score of 0.091. The comprehensive model showed higher apparent discrimination than the clinical-imaging base model (AUC 0.772) and Rotterdam CT score (AUC 0.779). Age-stratified AUCs were 0.854 and 0.842 for children aged 0–4 and 5–18 years, respectively. AUCs ranged from 0.729 to 0.785 across GCS severity groups. Conclusion The internally validated model showed promising discrimination for clinically important progression in this single-center pediatric tICH cohort. External validation and further evaluation of clinical utility are required before implementation.

Authors

Publication Details

Journal
Frontiers in Pediatrics
Published
2026-11-17
DOI
https://doi.org/10.3389/fped.2026.1930484
Primary Topic
Traumatic Brain Injury and Neurovascular Disturbances
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Early prediction of clinically important progression in children with traumatic intracranial hemorrhage treated at a high-altitude tertiary hospital: a single-center retrospective study

仁增, Zhuoma YiXi, Danbai Wujin, Yu Weng et al.
2 links
Frontiers in Pediatrics
Traumatic Brain Injury and Neurovascular Disturbances
article

Early prediction of clinically important progression in children with traumatic intracranial hemorrhage treated at a high-altitude tertiary hospital: a single-center retrospective study

仁增, Zhuoma YiXi, Danbai Wujin, Yu Weng, Xudong Cao, Duo Zha, Cidan Danzeng
article en

Abstract

Background Early identification of clinically important progression in children with traumatic intracranial hemorrhage (tICH) remains challenging, particularly in high-altitude settings. This study aimed to develop and internally validate a prediction model integrating clinical, radiological, oxygenation, and coagulation indicators. Methods This single-center retrospective cohort study included 584 children with CT-confirmed tICH admitted between January 2016 and December 2025. The primary outcome was clinically important in-hospital progression, comprising radiological progression, neurosurgical intervention, TBI-related neurological deterioration, or TBI-related death. Predictors were selected using 10-fold cross-validated LASSO regression. Model performance was evaluated using discrimination, calibration, Brier scores, and decision curve analysis, with internal validation using 1,000 bootstrap resamples. Additional analyses assessed performance across age and GCS severity groups and compared the model with the Rotterdam CT score. Results Clinically important progression occurred in 78 patients (13.4%). The final model included seven predictors: GCS ≤8, seizures or recurrent vomiting, mixed hemorrhagic lesions, maximum hematoma thickness, SpO 2 < 90%, PLT <150 × 10 9 /L, and INR >1.2. The apparent AUC was 0.845 (95% CI 0.792–0.898), with an optimism-corrected AUC of 0.821 and Brier score of 0.091. The comprehensive model showed higher apparent discrimination than the clinical-imaging base model (AUC 0.772) and Rotterdam CT score (AUC 0.779). Age-stratified AUCs were 0.854 and 0.842 for children aged 0–4 and 5–18 years, respectively. AUCs ranged from 0.729 to 0.785 across GCS severity groups. Conclusion The internally validated model showed promising discrimination for clinically important progression in this single-center pediatric tICH cohort. External validation and further evaluation of clinical utility are required before implementation.

Frontiers in PediatricsVol. 14
Good health and well-being
Traumatic Brain Injury and Neurovascular Disturbances
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon