Prichep LS, Jacquin A, Filipenko J, Ghosh-Dastidar S, Zabele S, Vodenčarević A, Rothman NS.
IEEE Transactions on Neural Systems & Rehabilitation Engineering. 2012; 20(6): 806-822.
Assessment of medical disorders is often aided by ob-jective diagnostic tests which can lead to early intervention and appropriate treatment. In the case of brain dysfunction caused by head injury, there is an urgent need for quantitative evaluation methods to aid in acute triage of those subjects who have sustained traumatic brain injury (TBI). Current clinical tools to detect mild TBI (mTBI/concussion) are limited to subjective reports of symp-toms and short neurocognitive batteries, offering little objective ev-idence for clinical decisions; or computed tomography (CT) scans, with radiation-risk, that are most often negative in mTBI. This paper describes a novel methodology for the development of algo-rithms to provide multi-class classification in a substantial popu-lation of brain injured subjects, across a broad age range and rep-resentative subpopulations. The method is based on age-regressed quantitative features (linear and nonlinear) extracted from brain electrical activity recorded from a limited montage of scalp elec-trodes. These features are used as input to a unique “informed data reduction” method, maximizing confidence of prospective val-idation and minimizing over-fitting. A training set for supervised learning was used, including: “normal control,” “concussed,” and “structural injury/CT positive (CT+).” The classifier function sep-arating CT+ from the other groups demonstrated a sensitivity of 96% and specificity of 78%; the classifier separating “normal con-trols” from the other groups demonstrated a sensitivity of 81% and specificity of 74%, suggesting high utility of such classifiers in acute clinical settings. The use of a sequence of classifiers where the de-siredriskcanbe stratified further supports clinical utility. Download the PDF