Identification of acute stroke using quantified brain electrical activity

Abstract

Objectives: Acute stroke is a leading cause of brain injury and death and requires rapid and accurate diagnosis. Noncontrast head computed tomography (CT) is the first line for diagnosis in the emergency department (ED). Complicating rapid triage are presenting conditions that clinically mimic stroke. There is an extensive literature reporting clinical utility of brain electrical activity in early diagnosis and management of acute stroke. However, existing technologies do not lend themselves to easily acquired rapid evaluation. This investigation used an independently derived classifier algorithm for the identification of traumatic structural brain injury based on brain electrical activity recorded from a reduced frontal montage to explore the potential clinical utility of such an approach in acute stroke assessment.

Methods: Adult patients (age 18 to 95 years) presenting with stroke-like and/or altered mental status symptoms were recruited from urban academic EDs as part of a large research study evaluating the clinical utility of quantitative brain electrical activity in acutely brain-injured patients. All patients from the parent study who had confirmed strokes, and a control group of stroke mimics (those with final ED diagnoses of migraine or syncope), were selected for this study. All stroke patients underwent head CT scans. Some patients with negative CTs had further imaging with magnetic resonance imaging (MRI). Ten minutes of electroencephalographic data were acquired on a hand-held device in development, from five frontal electrodes. Data analyses were done offline. A Structural Brain Injury Index (SBII) was derived using an independently developed binary discriminant classification algorithm whose input was specified features of brain electrical activity. The SBII was previously found to have high accuracy in the identification of traumatic brain-injured patients who were found to have brain injury on CT (CT+). This algorithm was applied to patients in this study and used to classify patients as CT+ or not CT+. Performance was assessed using sensitivity, specificity, and negative and positive predictive values (NPV, PPV).

Results: Forty-eight stroke patients (31 ischemic and 17 hemorrhagic) and 135 stroke mimic controls were included. Within the ischemic population, approximately half were CT- but later confirmed for stroke with MRI (CT-/MRI+). Sensitivity to stroke was 91.7%, specificity 50.4% (to stroke mimic), NPV 94.4%, and PPV 39.6%. Eighty percent of the CT-/MRI+ ischemic strokes were correctly identified at the time of the CT- scan.

Conclusions: Despite a small population and the use of a classifier without the benefit of training on a stroke population, these data suggest that a rapidly acquired, easy-to-use system to assess brain electrical activity at the time of evaluation of acute stroke could be a valuable adjunct to current clinical practice.