Predicting Long-Term Global Outcome after Traumatic Brain Injury: Development of a Practical Prognostic Tool Using the Traumatic Brain Injury Model Systems National Database

William C. Walker, Katharine A. Stromberg, Jennifer H. Marwitz, Adam P. Sima, Amma A. Agyemang, Kristin M. Graham, Cynthia Harrison-Felix, Jeanne M. Hoffman, Allen W Brown, Jeffrey S. Kreutzer, Randall Merchant

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

For patients surviving serious traumatic brain injury (TBI), families and other stakeholders often desire information on long-term functional prognosis, but accurate and easy-to-use clinical tools are lacking. We aimed to build utilitarian decision trees from commonly collected clinical variables to predict Glasgow Outcome Scale (GOS) functional levels at 1, 2, and 5 years after moderate-to-severe closed TBI. Flexible classification tree statistical modeling was used on prospectively collected data from the TBI-Model Systems (TBIMS) inception cohort study. Enrollments occurred at 17 designated, or previously designated, TBIMS inpatient rehabilitation facilities. Analysis included all participants with nonpenetrating TBI injured between January 1997 and January 2017. Sample sizes were 10,125 (year-1), 8,821 (year-2), and 6,165 (year-5) after cross-sectional exclusions (death, vegetative state, insufficient post-injury time, and unavailable outcome). In our final models, post-traumatic amnesia (PTA) duration consistently dominated branching hierarchy and was the lone injury characteristic significantly contributing to GOS predictability. Lower-order variables that added predictability were age, pre-morbid education, productivity, and occupational category. Generally, patient outcomes improved with shorter PTA, younger age, greater pre-morbid productivity, and higher pre-morbid vocational or educational achievement. Across all prognostic groups, the best and worst good recovery rates were 65.7% and 10.9%, respectively, and the best and worst severe disability rates were 3.9% and 64.1%. Predictability in test data sets ranged from C-statistic of 0.691 (year-1; confidence interval [CI], 0.675, 0.711) to 0.731 (year-2; CI, 0.724, 0.738). In conclusion, we developed a clinically useful tool to provide prognostic information on long-term functional outcomes for adult survivors of moderate and severe closed TBI. Predictive accuracy for GOS level was demonstrated in an independent test sample. Length of PTA, a clinical marker of injury severity, was by far the most critical outcome determinant.

Original languageEnglish (US)
Pages (from-to)1587-1595
Number of pages9
JournalJournal of Neurotrauma
Volume35
Issue number14
DOIs
StatePublished - Jul 15 2018

Fingerprint

Glasgow Outcome Scale
Amnesia
Databases
Wounds and Injuries
Confidence Intervals
Persistent Vegetative State
Decision Trees
Educational Status
Sample Size
Survivors
Inpatients
Cohort Studies
Rehabilitation
Biomarkers
Traumatic Brain Injury
Education

Keywords

  • classification tree; functional outcome; Glasgow Outcome Scale; prognosis; traumatic brain injury classification tree

ASJC Scopus subject areas

  • Clinical Neurology

Cite this

Predicting Long-Term Global Outcome after Traumatic Brain Injury : Development of a Practical Prognostic Tool Using the Traumatic Brain Injury Model Systems National Database. / Walker, William C.; Stromberg, Katharine A.; Marwitz, Jennifer H.; Sima, Adam P.; Agyemang, Amma A.; Graham, Kristin M.; Harrison-Felix, Cynthia; Hoffman, Jeanne M.; Brown, Allen W; Kreutzer, Jeffrey S.; Merchant, Randall.

In: Journal of Neurotrauma, Vol. 35, No. 14, 15.07.2018, p. 1587-1595.

Research output: Contribution to journalArticle

Walker, WC, Stromberg, KA, Marwitz, JH, Sima, AP, Agyemang, AA, Graham, KM, Harrison-Felix, C, Hoffman, JM, Brown, AW, Kreutzer, JS & Merchant, R 2018, 'Predicting Long-Term Global Outcome after Traumatic Brain Injury: Development of a Practical Prognostic Tool Using the Traumatic Brain Injury Model Systems National Database', Journal of Neurotrauma, vol. 35, no. 14, pp. 1587-1595. https://doi.org/10.1089/neu.2017.5359
Walker, William C. ; Stromberg, Katharine A. ; Marwitz, Jennifer H. ; Sima, Adam P. ; Agyemang, Amma A. ; Graham, Kristin M. ; Harrison-Felix, Cynthia ; Hoffman, Jeanne M. ; Brown, Allen W ; Kreutzer, Jeffrey S. ; Merchant, Randall. / Predicting Long-Term Global Outcome after Traumatic Brain Injury : Development of a Practical Prognostic Tool Using the Traumatic Brain Injury Model Systems National Database. In: Journal of Neurotrauma. 2018 ; Vol. 35, No. 14. pp. 1587-1595.
@article{2d8f01357c724d958da865af2dbdefd3,
title = "Predicting Long-Term Global Outcome after Traumatic Brain Injury: Development of a Practical Prognostic Tool Using the Traumatic Brain Injury Model Systems National Database",
abstract = "For patients surviving serious traumatic brain injury (TBI), families and other stakeholders often desire information on long-term functional prognosis, but accurate and easy-to-use clinical tools are lacking. We aimed to build utilitarian decision trees from commonly collected clinical variables to predict Glasgow Outcome Scale (GOS) functional levels at 1, 2, and 5 years after moderate-to-severe closed TBI. Flexible classification tree statistical modeling was used on prospectively collected data from the TBI-Model Systems (TBIMS) inception cohort study. Enrollments occurred at 17 designated, or previously designated, TBIMS inpatient rehabilitation facilities. Analysis included all participants with nonpenetrating TBI injured between January 1997 and January 2017. Sample sizes were 10,125 (year-1), 8,821 (year-2), and 6,165 (year-5) after cross-sectional exclusions (death, vegetative state, insufficient post-injury time, and unavailable outcome). In our final models, post-traumatic amnesia (PTA) duration consistently dominated branching hierarchy and was the lone injury characteristic significantly contributing to GOS predictability. Lower-order variables that added predictability were age, pre-morbid education, productivity, and occupational category. Generally, patient outcomes improved with shorter PTA, younger age, greater pre-morbid productivity, and higher pre-morbid vocational or educational achievement. Across all prognostic groups, the best and worst good recovery rates were 65.7{\%} and 10.9{\%}, respectively, and the best and worst severe disability rates were 3.9{\%} and 64.1{\%}. Predictability in test data sets ranged from C-statistic of 0.691 (year-1; confidence interval [CI], 0.675, 0.711) to 0.731 (year-2; CI, 0.724, 0.738). In conclusion, we developed a clinically useful tool to provide prognostic information on long-term functional outcomes for adult survivors of moderate and severe closed TBI. Predictive accuracy for GOS level was demonstrated in an independent test sample. Length of PTA, a clinical marker of injury severity, was by far the most critical outcome determinant.",
keywords = "classification tree; functional outcome; Glasgow Outcome Scale; prognosis; traumatic brain injury classification tree",
author = "Walker, {William C.} and Stromberg, {Katharine A.} and Marwitz, {Jennifer H.} and Sima, {Adam P.} and Agyemang, {Amma A.} and Graham, {Kristin M.} and Cynthia Harrison-Felix and Hoffman, {Jeanne M.} and Brown, {Allen W} and Kreutzer, {Jeffrey S.} and Randall Merchant",
year = "2018",
month = "7",
day = "15",
doi = "10.1089/neu.2017.5359",
language = "English (US)",
volume = "35",
pages = "1587--1595",
journal = "Journal of Neurotrauma",
issn = "0897-7151",
publisher = "Mary Ann Liebert Inc.",
number = "14",

}

TY - JOUR

T1 - Predicting Long-Term Global Outcome after Traumatic Brain Injury

T2 - Development of a Practical Prognostic Tool Using the Traumatic Brain Injury Model Systems National Database

AU - Walker, William C.

AU - Stromberg, Katharine A.

AU - Marwitz, Jennifer H.

AU - Sima, Adam P.

AU - Agyemang, Amma A.

AU - Graham, Kristin M.

AU - Harrison-Felix, Cynthia

AU - Hoffman, Jeanne M.

AU - Brown, Allen W

AU - Kreutzer, Jeffrey S.

AU - Merchant, Randall

PY - 2018/7/15

Y1 - 2018/7/15

N2 - For patients surviving serious traumatic brain injury (TBI), families and other stakeholders often desire information on long-term functional prognosis, but accurate and easy-to-use clinical tools are lacking. We aimed to build utilitarian decision trees from commonly collected clinical variables to predict Glasgow Outcome Scale (GOS) functional levels at 1, 2, and 5 years after moderate-to-severe closed TBI. Flexible classification tree statistical modeling was used on prospectively collected data from the TBI-Model Systems (TBIMS) inception cohort study. Enrollments occurred at 17 designated, or previously designated, TBIMS inpatient rehabilitation facilities. Analysis included all participants with nonpenetrating TBI injured between January 1997 and January 2017. Sample sizes were 10,125 (year-1), 8,821 (year-2), and 6,165 (year-5) after cross-sectional exclusions (death, vegetative state, insufficient post-injury time, and unavailable outcome). In our final models, post-traumatic amnesia (PTA) duration consistently dominated branching hierarchy and was the lone injury characteristic significantly contributing to GOS predictability. Lower-order variables that added predictability were age, pre-morbid education, productivity, and occupational category. Generally, patient outcomes improved with shorter PTA, younger age, greater pre-morbid productivity, and higher pre-morbid vocational or educational achievement. Across all prognostic groups, the best and worst good recovery rates were 65.7% and 10.9%, respectively, and the best and worst severe disability rates were 3.9% and 64.1%. Predictability in test data sets ranged from C-statistic of 0.691 (year-1; confidence interval [CI], 0.675, 0.711) to 0.731 (year-2; CI, 0.724, 0.738). In conclusion, we developed a clinically useful tool to provide prognostic information on long-term functional outcomes for adult survivors of moderate and severe closed TBI. Predictive accuracy for GOS level was demonstrated in an independent test sample. Length of PTA, a clinical marker of injury severity, was by far the most critical outcome determinant.

AB - For patients surviving serious traumatic brain injury (TBI), families and other stakeholders often desire information on long-term functional prognosis, but accurate and easy-to-use clinical tools are lacking. We aimed to build utilitarian decision trees from commonly collected clinical variables to predict Glasgow Outcome Scale (GOS) functional levels at 1, 2, and 5 years after moderate-to-severe closed TBI. Flexible classification tree statistical modeling was used on prospectively collected data from the TBI-Model Systems (TBIMS) inception cohort study. Enrollments occurred at 17 designated, or previously designated, TBIMS inpatient rehabilitation facilities. Analysis included all participants with nonpenetrating TBI injured between January 1997 and January 2017. Sample sizes were 10,125 (year-1), 8,821 (year-2), and 6,165 (year-5) after cross-sectional exclusions (death, vegetative state, insufficient post-injury time, and unavailable outcome). In our final models, post-traumatic amnesia (PTA) duration consistently dominated branching hierarchy and was the lone injury characteristic significantly contributing to GOS predictability. Lower-order variables that added predictability were age, pre-morbid education, productivity, and occupational category. Generally, patient outcomes improved with shorter PTA, younger age, greater pre-morbid productivity, and higher pre-morbid vocational or educational achievement. Across all prognostic groups, the best and worst good recovery rates were 65.7% and 10.9%, respectively, and the best and worst severe disability rates were 3.9% and 64.1%. Predictability in test data sets ranged from C-statistic of 0.691 (year-1; confidence interval [CI], 0.675, 0.711) to 0.731 (year-2; CI, 0.724, 0.738). In conclusion, we developed a clinically useful tool to provide prognostic information on long-term functional outcomes for adult survivors of moderate and severe closed TBI. Predictive accuracy for GOS level was demonstrated in an independent test sample. Length of PTA, a clinical marker of injury severity, was by far the most critical outcome determinant.

KW - classification tree; functional outcome; Glasgow Outcome Scale; prognosis; traumatic brain injury classification tree

UR - http://www.scopus.com/inward/record.url?scp=85049322892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049322892&partnerID=8YFLogxK

U2 - 10.1089/neu.2017.5359

DO - 10.1089/neu.2017.5359

M3 - Article

C2 - 29566600

AN - SCOPUS:85049322892

VL - 35

SP - 1587

EP - 1595

JO - Journal of Neurotrauma

JF - Journal of Neurotrauma

SN - 0897-7151

IS - 14

ER -