Selection of children with ultra-severe traumatic brain injury for neurosurgical intervention

Krista Greenan, Sandra L. Taylor, Daniel Fulkerson, Kiarash Shahlaie, Clayton Gerndt, Evan M. Krueger, Marike Zwienenberg-Lee

Research output: Contribution to journalArticle

Abstract

OBJECTIVE A recent retrospective study of severe traumatic brain injury (TBI) in pediatric patients showed similar outcomes in those with a Glasgow Coma Scale (GCS) score of 3 and those with a score of 4 and reported a favorable long-term outcome in 11.9% of patients. Using decision tree analysis, authors of that study provided criteria to identify patients with a potentially favorable outcome. The authors of the present study sought to validate the previously described decision tree and further inform understanding of the outcomes of children with a GCS score 3 or 4 by using data from multiple institutions and machine learning methods to identify important predictors of outcome. METHODS Clinical, radiographic, and outcome data on pediatric TBI patients (age < 18 years) were prospectively collected as part of an institutional TBI registry. Patients with a GCS score of 3 or 4 were selected, and the previously published prediction model was evaluated using this data set. Next, a combined data set that included data from two institutions was used to create a new, more statistically robust model using binomial recursive partitioning to create a decision tree. RESULTS Forty-five patients from the institutional TBI registry were included in the present study, as were 67 patients from the previously published data set, for a total of 112 patients in the combined analysis. The previously published prediction model for survival was externally validated and performed only modestly (AUC 0.68, 95% CI 0.47, 0.89). In the combined data set, pupillary response and age were the only predictors retained in the decision tree. Ninety-six percent of patients with bilaterally nonreactive pupils had a poor outcome. If the pupillary response was normal in at least one eye, the outcome subsequently depended on age: 72% of children between 5 months and 6 years old had a favorable outcome, whereas 100% of children younger than 5 months old and 77% of those older than 6 years had poor outcomes. The overall accuracy of the combined prediction model was 90.2% with a sensitivity of 68.4% and specificity of 93.6%. CONCLUSIONS A previously published survival model for severe TBI in children with a low GCS score was externally validated. With a larger data set, however, a simplified and more robust model was developed, and the variables most predictive of outcome were age and pupillary response.

Original languageEnglish (US)
Pages (from-to)670-679
Number of pages10
JournalJournal of Neurosurgery: Pediatrics
Volume23
Issue number6
DOIs
StatePublished - Jun 1 2019

Fingerprint

Decision Trees
Glasgow Coma Scale
Registries
Pediatrics
Traumatic Brain Injury
Survival
Decision Support Techniques
Statistical Models
Pupil
Area Under Curve
Retrospective Studies
Datasets
Sensitivity and Specificity

Keywords

  • Outcome prediction
  • Pediatric
  • Severe TBI
  • Trauma

ASJC Scopus subject areas

  • Surgery
  • Pediatrics, Perinatology, and Child Health
  • Clinical Neurology

Cite this

Selection of children with ultra-severe traumatic brain injury for neurosurgical intervention. / Greenan, Krista; Taylor, Sandra L.; Fulkerson, Daniel; Shahlaie, Kiarash; Gerndt, Clayton; Krueger, Evan M.; Zwienenberg-Lee, Marike.

In: Journal of Neurosurgery: Pediatrics, Vol. 23, No. 6, 01.06.2019, p. 670-679.

Research output: Contribution to journalArticle

Greenan, Krista ; Taylor, Sandra L. ; Fulkerson, Daniel ; Shahlaie, Kiarash ; Gerndt, Clayton ; Krueger, Evan M. ; Zwienenberg-Lee, Marike. / Selection of children with ultra-severe traumatic brain injury for neurosurgical intervention. In: Journal of Neurosurgery: Pediatrics. 2019 ; Vol. 23, No. 6. pp. 670-679.
@article{02d992284ac642e5a7a2a738378bffe5,
title = "Selection of children with ultra-severe traumatic brain injury for neurosurgical intervention",
abstract = "OBJECTIVE A recent retrospective study of severe traumatic brain injury (TBI) in pediatric patients showed similar outcomes in those with a Glasgow Coma Scale (GCS) score of 3 and those with a score of 4 and reported a favorable long-term outcome in 11.9{\%} of patients. Using decision tree analysis, authors of that study provided criteria to identify patients with a potentially favorable outcome. The authors of the present study sought to validate the previously described decision tree and further inform understanding of the outcomes of children with a GCS score 3 or 4 by using data from multiple institutions and machine learning methods to identify important predictors of outcome. METHODS Clinical, radiographic, and outcome data on pediatric TBI patients (age < 18 years) were prospectively collected as part of an institutional TBI registry. Patients with a GCS score of 3 or 4 were selected, and the previously published prediction model was evaluated using this data set. Next, a combined data set that included data from two institutions was used to create a new, more statistically robust model using binomial recursive partitioning to create a decision tree. RESULTS Forty-five patients from the institutional TBI registry were included in the present study, as were 67 patients from the previously published data set, for a total of 112 patients in the combined analysis. The previously published prediction model for survival was externally validated and performed only modestly (AUC 0.68, 95{\%} CI 0.47, 0.89). In the combined data set, pupillary response and age were the only predictors retained in the decision tree. Ninety-six percent of patients with bilaterally nonreactive pupils had a poor outcome. If the pupillary response was normal in at least one eye, the outcome subsequently depended on age: 72{\%} of children between 5 months and 6 years old had a favorable outcome, whereas 100{\%} of children younger than 5 months old and 77{\%} of those older than 6 years had poor outcomes. The overall accuracy of the combined prediction model was 90.2{\%} with a sensitivity of 68.4{\%} and specificity of 93.6{\%}. CONCLUSIONS A previously published survival model for severe TBI in children with a low GCS score was externally validated. With a larger data set, however, a simplified and more robust model was developed, and the variables most predictive of outcome were age and pupillary response.",
keywords = "Outcome prediction, Pediatric, Severe TBI, Trauma",
author = "Krista Greenan and Taylor, {Sandra L.} and Daniel Fulkerson and Kiarash Shahlaie and Clayton Gerndt and Krueger, {Evan M.} and Marike Zwienenberg-Lee",
year = "2019",
month = "6",
day = "1",
doi = "10.3171/2019.1.PEDS18293",
language = "English (US)",
volume = "23",
pages = "670--679",
journal = "Journal of neurosurgery. Pediatrics",
issn = "1933-0707",
publisher = "American Association of Neurological Surgeons",
number = "6",

}

TY - JOUR

T1 - Selection of children with ultra-severe traumatic brain injury for neurosurgical intervention

AU - Greenan, Krista

AU - Taylor, Sandra L.

AU - Fulkerson, Daniel

AU - Shahlaie, Kiarash

AU - Gerndt, Clayton

AU - Krueger, Evan M.

AU - Zwienenberg-Lee, Marike

PY - 2019/6/1

Y1 - 2019/6/1

N2 - OBJECTIVE A recent retrospective study of severe traumatic brain injury (TBI) in pediatric patients showed similar outcomes in those with a Glasgow Coma Scale (GCS) score of 3 and those with a score of 4 and reported a favorable long-term outcome in 11.9% of patients. Using decision tree analysis, authors of that study provided criteria to identify patients with a potentially favorable outcome. The authors of the present study sought to validate the previously described decision tree and further inform understanding of the outcomes of children with a GCS score 3 or 4 by using data from multiple institutions and machine learning methods to identify important predictors of outcome. METHODS Clinical, radiographic, and outcome data on pediatric TBI patients (age < 18 years) were prospectively collected as part of an institutional TBI registry. Patients with a GCS score of 3 or 4 were selected, and the previously published prediction model was evaluated using this data set. Next, a combined data set that included data from two institutions was used to create a new, more statistically robust model using binomial recursive partitioning to create a decision tree. RESULTS Forty-five patients from the institutional TBI registry were included in the present study, as were 67 patients from the previously published data set, for a total of 112 patients in the combined analysis. The previously published prediction model for survival was externally validated and performed only modestly (AUC 0.68, 95% CI 0.47, 0.89). In the combined data set, pupillary response and age were the only predictors retained in the decision tree. Ninety-six percent of patients with bilaterally nonreactive pupils had a poor outcome. If the pupillary response was normal in at least one eye, the outcome subsequently depended on age: 72% of children between 5 months and 6 years old had a favorable outcome, whereas 100% of children younger than 5 months old and 77% of those older than 6 years had poor outcomes. The overall accuracy of the combined prediction model was 90.2% with a sensitivity of 68.4% and specificity of 93.6%. CONCLUSIONS A previously published survival model for severe TBI in children with a low GCS score was externally validated. With a larger data set, however, a simplified and more robust model was developed, and the variables most predictive of outcome were age and pupillary response.

AB - OBJECTIVE A recent retrospective study of severe traumatic brain injury (TBI) in pediatric patients showed similar outcomes in those with a Glasgow Coma Scale (GCS) score of 3 and those with a score of 4 and reported a favorable long-term outcome in 11.9% of patients. Using decision tree analysis, authors of that study provided criteria to identify patients with a potentially favorable outcome. The authors of the present study sought to validate the previously described decision tree and further inform understanding of the outcomes of children with a GCS score 3 or 4 by using data from multiple institutions and machine learning methods to identify important predictors of outcome. METHODS Clinical, radiographic, and outcome data on pediatric TBI patients (age < 18 years) were prospectively collected as part of an institutional TBI registry. Patients with a GCS score of 3 or 4 were selected, and the previously published prediction model was evaluated using this data set. Next, a combined data set that included data from two institutions was used to create a new, more statistically robust model using binomial recursive partitioning to create a decision tree. RESULTS Forty-five patients from the institutional TBI registry were included in the present study, as were 67 patients from the previously published data set, for a total of 112 patients in the combined analysis. The previously published prediction model for survival was externally validated and performed only modestly (AUC 0.68, 95% CI 0.47, 0.89). In the combined data set, pupillary response and age were the only predictors retained in the decision tree. Ninety-six percent of patients with bilaterally nonreactive pupils had a poor outcome. If the pupillary response was normal in at least one eye, the outcome subsequently depended on age: 72% of children between 5 months and 6 years old had a favorable outcome, whereas 100% of children younger than 5 months old and 77% of those older than 6 years had poor outcomes. The overall accuracy of the combined prediction model was 90.2% with a sensitivity of 68.4% and specificity of 93.6%. CONCLUSIONS A previously published survival model for severe TBI in children with a low GCS score was externally validated. With a larger data set, however, a simplified and more robust model was developed, and the variables most predictive of outcome were age and pupillary response.

KW - Outcome prediction

KW - Pediatric

KW - Severe TBI

KW - Trauma

UR - http://www.scopus.com/inward/record.url?scp=85066468943&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066468943&partnerID=8YFLogxK

U2 - 10.3171/2019.1.PEDS18293

DO - 10.3171/2019.1.PEDS18293

M3 - Article

C2 - 30952132

AN - SCOPUS:85066468943

VL - 23

SP - 670

EP - 679

JO - Journal of neurosurgery. Pediatrics

JF - Journal of neurosurgery. Pediatrics

SN - 1933-0707

IS - 6

ER -