A Quantitative Electroencephalographic Index for Stroke Detection in Adults

Electroencephalography (EEG) remains underutilized for stroke characterization. We sought to assess the performance of the EEG Correlate Of Injury to the Nervous system (COIN) index, a quantitative metric designed for stroke recognition in children, in discriminating large from small ischemic strokes in adults.

Retrospective, single-center cohort of adults with acute (within 7 days) ischemic stroke who underwent at least 8 hours of continuous EEG monitoring in hospital. Stroke size was categorized as large or small based on a threshold of 100 mL using the ABC/2 approach. EEG data were processed on MATLAB. COIN was independently calculated from consecutive 4-second EEG epochs. Student t-test and logistic regression were used to assess COIN performance in stroke size discrimination across the entire recording; random forest classification was used to determine COIN performance in limited EEG time windows ranging from 5 to 30 minutes in duration.

Thirty-five patients with mean age 67 (SD ± 17) years were analyzed with mean 4.5 ± 1.3 hours of clean EEG per patient. Ten patients had large stroke and 25 had small stroke. Participants with large strokes had larger COIN values than those with small strokes (-53 vs. -16, P = 0.0001). Logistic regression for stroke size classification model showed accuracy 83% ± 8%, sensitivity 70%±15%, specificity 88%±8%, and area under the receiver operator curve 0.75±0.10. Random Forest Classification performance was similar using 5 or 30 minutes of EEG data with accuracy 81% to 82%, specificity 91% to 92%, and sensitivity 55% to 58%, respectively.

COIN differentiated large from small acute ischemic strokes in this single-center cohort. Prospective evaluation in larger multicenter data sets is necessary to determine COIN utility as an aid for bedside detection of large ischemic strokes in contexts where neuroimaging cannot be easily obtained or when neurologic examination is limited by sedation or neuromuscular blockade.