A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment

Concussion Assessment, Research, and Education Consortium Investigators

Research output: Contribution to journalArticle

Abstract

Kutcher and Giza suggested incorporating levels of certainty in concussion diagnosis decisions. These guidelines were based on clinical experience rather than objective data. Therefore, we combined data-driven optimization with predictive modeling to identify which athletes are unlikely to have concussion and to classify remaining athletes as having possible, probable, or definite concussion with diagnostic certainty. We developed and validated our framework using data from the Concussion Assessment, Research, and Education (CARE) Consortium. Acute concussions had assessments at <6 h (n = 1085) and 24-48 h post-injury (n = 1413). Normal performances consisted of assessments at baseline (n = 1635) and the time of unrestricted return to play (n = 1345). We evaluated the distribution of acute concussions and normal performances across risk categories and identified inter-class and intra-class differences in demographics, time-of-injury characteristics, the Standard Assessment of Concussion (SAC), Sport Concussion Assessment Tool (SCAT) symptom assessments, and Balance Error Scoring System (BESS). Our algorithm accurately classified concussions as probable or definite (sensitivity = 91.07-97.40%). Definite and probable concussions had higher SCAT symptom scores than unlikely and possible concussions (p < 0.05). Definite concussions had lower SAC and higher BESS scores (p < 0.05). Baseline to post-injury change scores for the SAC, SCAT symptoms, and BESS were significantly different between acute possible and probable concussions and normal performances (p < 0.05). There were no consistent patterns in demographics across risk categories, although a greater proportion of concussions classified as unlikely were reported immediately compared with definite concussions (p < 0.05). Although clinical interpretation is still needed, our data-driven approach to concussion risk stratification provides a promising step toward evidence-based concussion assessment.

Original languageEnglish (US)
Pages (from-to)1571-1583
Number of pages13
JournalJournal of Neurotrauma
Volume36
Issue number10
DOIs
StatePublished - May 15 2019
Externally publishedYes

Fingerprint

Symptom Assessment
Sports
Athletes
Wounds and Injuries
Demography
Guidelines
Education
Research

Keywords

  • acute concussion assessment
  • possible, probable, and definite concussion
  • risk stratification

ASJC Scopus subject areas

  • Clinical Neurology

Cite this

A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment. / Concussion Assessment, Research, and Education Consortium Investigators.

In: Journal of Neurotrauma, Vol. 36, No. 10, 15.05.2019, p. 1571-1583.

Research output: Contribution to journalArticle

Concussion Assessment, Research, and Education Consortium Investigators 2019, 'A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment', Journal of Neurotrauma, vol. 36, no. 10, pp. 1571-1583. https://doi.org/10.1089/neu.2018.6098
Concussion Assessment, Research, and Education Consortium Investigators. A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment. Journal of Neurotrauma. 2019 May 15;36(10):1571-1583. https://doi.org/10.1089/neu.2018.6098
Concussion Assessment, Research, and Education Consortium Investigators. / A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment. In: Journal of Neurotrauma. 2019 ; Vol. 36, No. 10. pp. 1571-1583.
@article{b1482494db814dd6b79c5ef8e63311ba,
title = "A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment",
abstract = "Kutcher and Giza suggested incorporating levels of certainty in concussion diagnosis decisions. These guidelines were based on clinical experience rather than objective data. Therefore, we combined data-driven optimization with predictive modeling to identify which athletes are unlikely to have concussion and to classify remaining athletes as having possible, probable, or definite concussion with diagnostic certainty. We developed and validated our framework using data from the Concussion Assessment, Research, and Education (CARE) Consortium. Acute concussions had assessments at <6 h (n = 1085) and 24-48 h post-injury (n = 1413). Normal performances consisted of assessments at baseline (n = 1635) and the time of unrestricted return to play (n = 1345). We evaluated the distribution of acute concussions and normal performances across risk categories and identified inter-class and intra-class differences in demographics, time-of-injury characteristics, the Standard Assessment of Concussion (SAC), Sport Concussion Assessment Tool (SCAT) symptom assessments, and Balance Error Scoring System (BESS). Our algorithm accurately classified concussions as probable or definite (sensitivity = 91.07-97.40{\%}). Definite and probable concussions had higher SCAT symptom scores than unlikely and possible concussions (p < 0.05). Definite concussions had lower SAC and higher BESS scores (p < 0.05). Baseline to post-injury change scores for the SAC, SCAT symptoms, and BESS were significantly different between acute possible and probable concussions and normal performances (p < 0.05). There were no consistent patterns in demographics across risk categories, although a greater proportion of concussions classified as unlikely were reported immediately compared with definite concussions (p < 0.05). Although clinical interpretation is still needed, our data-driven approach to concussion risk stratification provides a promising step toward evidence-based concussion assessment.",
keywords = "acute concussion assessment, possible, probable, and definite concussion, risk stratification",
author = "{Concussion Assessment, Research, and Education Consortium Investigators} and Garcia, {Gian Gabriel P.} and Lavieri, {Mariel S.} and Ruiwei Jiang and McAllister, {Thomas W.} and McCrea, {Michael A.} and Broglio, {Steven P.}",
year = "2019",
month = "5",
day = "15",
doi = "10.1089/neu.2018.6098",
language = "English (US)",
volume = "36",
pages = "1571--1583",
journal = "Journal of Neurotrauma",
issn = "0897-7151",
publisher = "Mary Ann Liebert Inc.",
number = "10",

}

TY - JOUR

T1 - A Data-Driven Approach to Unlikely, Possible, Probable, and Definite Acute Concussion Assessment

AU - Concussion Assessment, Research, and Education Consortium Investigators

AU - Garcia, Gian Gabriel P.

AU - Lavieri, Mariel S.

AU - Jiang, Ruiwei

AU - McAllister, Thomas W.

AU - McCrea, Michael A.

AU - Broglio, Steven P.

PY - 2019/5/15

Y1 - 2019/5/15

N2 - Kutcher and Giza suggested incorporating levels of certainty in concussion diagnosis decisions. These guidelines were based on clinical experience rather than objective data. Therefore, we combined data-driven optimization with predictive modeling to identify which athletes are unlikely to have concussion and to classify remaining athletes as having possible, probable, or definite concussion with diagnostic certainty. We developed and validated our framework using data from the Concussion Assessment, Research, and Education (CARE) Consortium. Acute concussions had assessments at <6 h (n = 1085) and 24-48 h post-injury (n = 1413). Normal performances consisted of assessments at baseline (n = 1635) and the time of unrestricted return to play (n = 1345). We evaluated the distribution of acute concussions and normal performances across risk categories and identified inter-class and intra-class differences in demographics, time-of-injury characteristics, the Standard Assessment of Concussion (SAC), Sport Concussion Assessment Tool (SCAT) symptom assessments, and Balance Error Scoring System (BESS). Our algorithm accurately classified concussions as probable or definite (sensitivity = 91.07-97.40%). Definite and probable concussions had higher SCAT symptom scores than unlikely and possible concussions (p < 0.05). Definite concussions had lower SAC and higher BESS scores (p < 0.05). Baseline to post-injury change scores for the SAC, SCAT symptoms, and BESS were significantly different between acute possible and probable concussions and normal performances (p < 0.05). There were no consistent patterns in demographics across risk categories, although a greater proportion of concussions classified as unlikely were reported immediately compared with definite concussions (p < 0.05). Although clinical interpretation is still needed, our data-driven approach to concussion risk stratification provides a promising step toward evidence-based concussion assessment.

AB - Kutcher and Giza suggested incorporating levels of certainty in concussion diagnosis decisions. These guidelines were based on clinical experience rather than objective data. Therefore, we combined data-driven optimization with predictive modeling to identify which athletes are unlikely to have concussion and to classify remaining athletes as having possible, probable, or definite concussion with diagnostic certainty. We developed and validated our framework using data from the Concussion Assessment, Research, and Education (CARE) Consortium. Acute concussions had assessments at <6 h (n = 1085) and 24-48 h post-injury (n = 1413). Normal performances consisted of assessments at baseline (n = 1635) and the time of unrestricted return to play (n = 1345). We evaluated the distribution of acute concussions and normal performances across risk categories and identified inter-class and intra-class differences in demographics, time-of-injury characteristics, the Standard Assessment of Concussion (SAC), Sport Concussion Assessment Tool (SCAT) symptom assessments, and Balance Error Scoring System (BESS). Our algorithm accurately classified concussions as probable or definite (sensitivity = 91.07-97.40%). Definite and probable concussions had higher SCAT symptom scores than unlikely and possible concussions (p < 0.05). Definite concussions had lower SAC and higher BESS scores (p < 0.05). Baseline to post-injury change scores for the SAC, SCAT symptoms, and BESS were significantly different between acute possible and probable concussions and normal performances (p < 0.05). There were no consistent patterns in demographics across risk categories, although a greater proportion of concussions classified as unlikely were reported immediately compared with definite concussions (p < 0.05). Although clinical interpretation is still needed, our data-driven approach to concussion risk stratification provides a promising step toward evidence-based concussion assessment.

KW - acute concussion assessment

KW - possible, probable, and definite concussion

KW - risk stratification

UR - http://www.scopus.com/inward/record.url?scp=85065516208&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065516208&partnerID=8YFLogxK

U2 - 10.1089/neu.2018.6098

DO - 10.1089/neu.2018.6098

M3 - Article

VL - 36

SP - 1571

EP - 1583

JO - Journal of Neurotrauma

JF - Journal of Neurotrauma

SN - 0897-7151

IS - 10

ER -