Citation

Jacquin A, Kanakia S, Oberly D, Prichep LS. Comput. Biol. Med. 2018; 102: 95-103.

Affiliation

Algorithm Development, BrainScope Co., Inc, Bethesda, MD, United States; Department of Psychiatry, NYU School of Medicine, New York, NY, United States.

Copyright

(Copyright © 2018, Elsevier Publishing)

DOI

10.1016/j.compbiomed.2018.09.011

PMID

30261405

Abstract

BACKGROUND: Prompt, accurate, objective assessment of concussion is crucial, particularly for children/adolescents and young adults. While there is currently no gold standard for the diagnosis of concussion, the importance of multidimensional/multimodal assessments has recently been emphasized.

METHODS: Concussed subjects (N = 177), matched controls (N = 187) and healthy volunteers (N = 204) represented a convenience sample of male and female subjects between the ages of 13 and 25 years, enrolled at 29 Colleges and 19 High Schools in the US. Subjects were tested at time of injury and at multiple time points during recovery. Assessments included EEG, neurocognitive tests and standard concussion assessment tools. Multimodal classifiers to maximally separate controls from concussed subjects with prolonged recovery (≥14 days) were derived using quantitative EEG, neurocognitive and vestibular measures, informed feature reduction and a Genetic Algorithm methodology for classifier derivation. The methodology protected against overtraining using an internal cross-validation framework. An enhanced multimodal Brain Function Index (eBFI) was derived from the classifier output and mapped to a percentile scale which expressed the index relative to non-injured controls.

RESULTS: At time of injury eBFIs were significantly different between controls and concussed subjects with prolonged recovery, showing return to non-concussed levels at return-to-play plus 45 days. For the combined concussed population, and for the short recovery subjects, a more rapid recovery was seen.

CONCLUSIONS: This multivariate, multimodal, objective index of brain function impairment can potentially be used, along with other tools, to aid in diagnosis, assessment, and tracking of recovery from concussion.

Copyright © 2018 Elsevier Ltd. All rights reserved.

Language: en

Keywords

Brain function index; Classifier algorithms; Concussion; Electrophysiology of TBI; Enhanced BFI; Neurocognitive assessments; Quantitative brain activity; Return to play; Sport-related concussion; TBI