1 Department of Industrial and Operations Engineering and University of Michigan, Ann Arbor, Michigan.
2 Department of Psychiatry, Indiana University School of Medicine, Indianapolis, Indiana.
J Neurotrauma. 2019 May 15;36(10):1571-1583. doi: 10.1089/neu.2018.6098. Epub 2019 Jan 14.
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 ( = 1085) and 24-48 h post-injury ( = 1413). Normal performances consisted of assessments at baseline ( = 1635) and the time of unrestricted return to play ( = 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 ( < 0.05). Definite concussions had lower SAC and higher BESS scores ( < 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 ( < 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 ( < 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.
库彻和吉扎建议在脑震荡诊断决策中纳入确定性水平。这些指南是基于临床经验而不是客观数据制定的。因此，我们将数据驱动的优化与预测建模相结合，以确定哪些运动员不太可能患有脑震荡，并将其余运动员分类为可能、可能或明确的脑震荡，具有诊断确定性。我们使用 Concussion Assessment, Research, and Education (CARE) 联盟的数据开发和验证了我们的框架。急性脑震荡在受伤后<6 小时（ = 1085）和 24-48 小时（ = 1413）进行评估。正常表现包括基线评估（ = 1635）和无限制重返比赛的时间（ = 1345）。我们评估了急性脑震荡和正常表现在风险类别中的分布，并确定了人口统计学、受伤时间特征、标准脑震荡评估（SAC）、运动脑震荡评估工具（SCAT）症状评估和平衡错误评分系统（BESS）之间的组间和组内差异。我们的算法准确地将脑震荡分类为可能或明确（敏感性 = 91.07-97.40%）。明确和可能的脑震荡的 SCAT 症状评分高于不太可能和可能的脑震荡（ < 0.05）。明确的脑震荡的 SAC 和 BESS 评分较低（ < 0.05）。SAC、SCAT 症状和 BESS 的基线到受伤后变化评分在急性可能和明确脑震荡与正常表现之间有显著差异（ < 0.05）。虽然在风险类别中没有一致的人口统计学模式，但与明确的脑震荡相比，报告不太可能的脑震荡的比例更高（ < 0.05）。虽然仍然需要临床解释，但我们基于数据的脑震荡风险分层方法为基于证据的脑震荡评估提供了一个有前途的步骤。
