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.
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.
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%.
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.
ABBREVIATIONSAUC = area under the curve; ER = Emergency Room; GCS = Glasgow Coma Scale; GOS = Glasgow Outcome Scale; GOS-E = Extended GOS; ICP = intracranial pressure; MVA = motor vehicle accident; NAT = nonaccidental trauma; RH = Riley Hospital; TBI = traumatic brain injury; tSAH = traumatic subarachnoid hemorrhage; UCD = UC Davis.
Correspondence Marike Zwienenberg: University of California, Davis, Sacramento, CA. email@example.com.
INCLUDE WHEN CITING Published online April 5, 2019; DOI: 10.3171/2019.1.PEDS18293.
Disclosures This work was supported by a financial grant from the UC Davis Department of Neurological Surgery and the UC Davis Clinical and Translational Science Center supported by the National Institutes of Health through grant no. UL1 TR001860.
BrennanPM, MurrayGD, TeasdaleGM: Simplifying the use of prognostic information in traumatic brain injury. Part 1: The GCS-Pupils score: an extended index of clinical severity. 128:1612–1620, 20182963151610.3171/2017.12.JNS172780)| false
Centers for Disease Control and Prevention: Ten leading causes of death by age group, United States, 2016. CDC.gov (https://www.cdc.gov/injury/wisqars/LeadingCauses.html) [Accessed February 15 2019]
Centers for Disease Control and Prevention: Ten leading causes of death by age group, United States, 2016. CDC.gov (https://www.cdc.gov/injury/wisqars/LeadingCauses.html) [Accessed February 15, 2019])| false
ChiarettiA, PiastraM, PulitanòS, PietriniD, De RosaG, BarbaroR, : Prognostic factors and outcome of children with severe head injury: an 8-year experience. 18:129–136, 20021198161910.1007/s00381-002-0558-3)| false
DucrocqSCMeyerPGOrliaguetGABlanotSLaurent-VannierARenierD: Epidemiology and early predictive factors of mortality and outcome in children with traumatic severe brain injury: experience of a French pediatric trauma center. Pediatr Crit Care Med7:461–4672006
DucrocqSC, MeyerPG, OrliaguetGA, BlanotS, Laurent-VannierA, RenierD, : Epidemiology and early predictive factors of mortality and outcome in children with traumatic severe brain injury: experience of a French pediatric trauma center. 7:461–467, 200610.1097/01.PCC.0000235245.49129.2716885795)| false
EmamiPCzorlichPFritzscheFSWestphalMRuegerJMLeferingR: Impact of Glasgow Coma Scale score and pupil parameters on mortality rate and outcome in pediatric and adult severe traumatic brain injury: a retrospective, multicenter cohort study. J Neurosurg126:760–7672017
EmamiP, CzorlichP, FritzscheFS, WestphalM, RuegerJM, LeferingR, : Impact of Glasgow Coma Scale score and pupil parameters on mortality rate and outcome in pediatric and adult severe traumatic brain injury: a retrospective, multicenter cohort study. 126:760–767, 20172703517710.3171/2016.1.JNS152385)| false
FulkersonDHWhiteIKReesJMBaumanisMMSmithJLAckermanLL: Analysis of long-term (median 10.5 years) outcomes in children presenting with traumatic brain injury and an initial Glasgow Coma Scale score of 3 or 4. J Neurosurg Pediatr16:410–4192015
FulkersonDH, WhiteIK, ReesJM, BaumanisMM, SmithJL, AckermanLL, : Analysis of long-term (median 10.5 years) outcomes in children presenting with traumatic brain injury and an initial Glasgow Coma Scale score of 3 or 4. 16:410–419, 20152614039210.3171/2015.3.PEDS14679)| false
GómezPA, de-la-CruzJ, LoraD, Jiménez-RoldánL, Rodríguez-BotoG, SarabiaR, : Validation of a prognostic score for early mortality in severe head injury cases. 121:1314–1322, 201410.3171/2014.7.JNS13187425237737)| false
HaiderAHCromptonJGOyetunjiTRisucciDDiRussoSBasdagH: Mechanism of injury predicts case fatality and functional outcomes in pediatric trauma patients: the case for its use in trauma outcomes studies. J Pediatr Surg46:1557–15632011
HaiderAH, CromptonJG, OyetunjiT, RisucciD, DiRussoS, BasdagH, : Mechanism of injury predicts case fatality and functional outcomes in pediatric trauma patients: the case for its use in trauma outcomes studies. 46:1557–1563, 20112184372410.1016/j.jpedsurg.2011.04.055)| false
HanJX, SeeAAQ, GandhiM, KingNKK: Models of mortality and morbidity in severe traumatic brain injury: an analysis of a Singapore neurotrauma database. 108:885–893, 893.e1, 20172886731210.1016/j.wneu.2017.08.147)| false
HoffmannMLeferingRRuegerJMKolbJPIzbickiJRRueckerAH: Pupil evaluation in addition to Glasgow Coma Scale components in prediction of traumatic brain injury and mortality. Br J Surg99 (Suppl 1):122–1302012
HoffmannM, LeferingR, RuegerJM, KolbJP, IzbickiJR, RueckerAH, : Pupil evaluation in addition to Glasgow Coma Scale components in prediction of traumatic brain injury and mortality. 99 (Suppl 1):122–130, 20122244186610.1002/bjs.7707)| false
HukkelhovenCW, SteyerbergEW, RampenAJ, FaraceE, HabbemaJD, MarshallLF, : Patient age and outcome following severe traumatic brain injury: an analysis of 5600 patients. 99:666–673, 20031456760110.3171/jns.2003.99.4.0666)| false
JagannathanJOkonkwoDOYeohHKDumontASSaulleDHaizlipJ: Long-term outcomes and prognostic factors in pediatric patients with severe traumatic brain injury and elevated intracranial pressure. J Neurosurg Pediatr2:240–2492008
KesmarkyK, DelhumeauC, ZenobiM, WalderB: Comparison of two predictive models for short-term mortality in patients after severe traumatic brain injury. 34:2235–2242, 201710.1089/neu.2016.460628323524)| false
PerelP, ArangoM, ClaytonT, EdwardsP, KomolafeE, PoccockS, : Predicting outcome after traumatic brain injury: practical prognostic models based on large cohort of international patients. 336:425–429, 200810.1136/bmj.39461.643438.2518270239)| false
RizoliS, PetersenA, BulgerE, CoimbraR, KerbyJD, MineiJ, : Early prediction of outcome after severe traumatic brain injury: a simple and practical model. 16:32, 201610.1186/s12873-016-0098-x27553436)| false
SteyerbergEWMushkudianiNPerelPButcherILuJMcHughGS: Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics. PLoS Med5:e1652008
SteyerbergEW, MushkudianiN, PerelP, ButcherI, LuJ, McHughGS, : Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics. 5:e165, 20081868400810.1371/journal.pmed.0050165)| false
TienHC, CunhaJR, WuSN, ChughtaiT, TremblayLN, BrennemanFD, : Do trauma patients with a Glasgow Coma Scale score of 3 and bilateral fixed and dilated pupils have any chance of survival?60:274–278, 20061650848210.1097/01.ta.0000197177.13379.f4)| false
Tude MeloJR, Di RoccoF, BlanotS, Oliveira-FilhoJ, RoujeauT, Sainte-RoseC, : Mortality in children with severe head trauma: predictive factors and proposal for a new predictive scale. 67:1542–1547, 201010.1227/NEU.0b013e3181fa7049)| false