Related Experiment Video
Updated: Jun 16, 2026
SECONDs Administration Guidelines: A Fast Tool to Assess Consciousness in Brain-injured Patients
Published on: February 6, 2021
Enhancing Pediatric Trauma Survival Prediction: Integrating ICISS and Glasgow Coma Scale for Greater Accuracy
A De Los Ríos-Perez1,2,3, A García Marin3,4,5, A Giraldo Arboleda3
1Doctoral Program in Methodology of Biomedical Research and Public Health, Universitat Autonoma de Barcelona, Barcelona, Spain.
Insights
A new model combining the International Classification of Disease-based Injury Severity Score (ICISS) with the Glasgow Coma Score (GCS) significantly improves survival prediction accuracy in pediatric trauma patients in Latin America.
Area of Science:
- Pediatric trauma research
- Injury severity scoring systems
- Public health in the Americas
Background:
- Global injury mortality has decreased, yet remains high in the Americas.
- Injury severity scores improve outcomes but have limited use in Latin American children.
- This study addresses the need for better pediatric trauma prediction in the region.
Purpose of the Study:
- To evaluate the International Classification of Disease-based Injury Severity Score (ICISS) for predicting pediatric survival in Latin America.
- To compare the predictive performance of ICISS with a novel model incorporating the Glasgow Coma Score (GCS).
Main Methods:
- Retrospective cohort study of 1047 children (<18 years) with trauma diagnoses in Cali, Colombia (2011-2019).
- Developed a logistic regression model for 30-day survival prediction.
- Assessed model performance using discrimination (AUROC) and calibration, comparing ICISS alone versus ICISS + GCS.
Main Results:
- The novel model (ICISS + GCS) showed superior discrimination (AUROC: 0.98) compared to ICISS alone (AUROC: 0.94), with a significant difference (p=0.01).
- The new model also demonstrated better calibration (Hosmer-Lemeshow p=0.6) versus ICISS alone (p<0.01).
- Internal validation confirmed the new model's excellent and maintained performance.
Conclusions:
- Integrating the Glasgow Coma Score (GCS) with the International Classification of Disease-based Injury Severity Score (ICISS) significantly enhances survival prediction accuracy in pediatric trauma.
- This combined approach offers a more precise tool for managing pediatric trauma in resource-limited settings.
Background:
The mortality rate from injuries globally has declined but remains high in the Americas. Despite the proven efficacy of severity scores in improving injury outcomes, their use in Latin American children has been limited. We aimed to assess the predictive performance of the International Classification of Disease-based Injury Severity Score (ICISS) in children's survival and compare it with a novel predictive model.
Methods:
A retrospective cohort study was conducted at a trauma center in Cali, Colombia, including children (< 18 years) with trauma-related diagnoses from 2011 to 2019, utilizing electronic health records from the Colombian national health system. A logistic regression model was developed to predict 30-day survival. Its performance was assessed by discrimination with the area under the receiver operating characteristic curve (AUROC) and calibration and was statistically compared with a new model incorporating the Glasgow Coma Score (GCS). The new model was internally validated by bootstrap resampling.
Results:
The study included 1047 children. The new model demonstrated superior discrimination (AUROC: 0.98, 95% CI: 0.97-0.99) compared to the ICISS-only model (AUROC: 0.94, 95% CI: 0.92-0.97), with a statistically significant difference (p = 0.01). Additionally, it exhibited better calibration (Hosmer-Lemeshow test: 6.7, p = 0.6 vs. 24.7, p < 0.01), indicating improved predictive accuracy. Following internal validation, the new model maintained excellent performance across all measures.
Conclusions:
Combining ICISS with the GCS significantly improved the accuracy of survival prediction in children.
