Abstract TP314: EEG Has High Precision for Diagnosing Stroke Hours After Onset

Abstract

Background: Improvements are needed in prehospital diagnosis of stroke. The electroencephalogram (EEG) changes immediately after brain ischemia, and advances in EEG technology enable rapid acquisition in the acute care setting. We hypothesized that EEG data increase the accuracy with which patients are correctly classified as having acute stroke or not, and so performed a study in the Emergency Department (ED) as an initial step towards evaluating prehospital utility of EEG. Methods: Patients with suspected stroke in a comprehensive stroke center ED underwent a 3 min EEG using a wireless, dry-electrode system; data were analyzed offline. A model was developed to classify patients as stroke/TIA vs non-stroke using a training set of 60 randomly selected patients. The model was then tested in an independent validation cohort of 40 new patients. EEG variables were selected using Lasso regression. Four models were examined, the first three using logistic regression: [1] clinical data only; [2] EEG data only; [3] combined clinical and EEG data; [4] a deep learning neural network model using clinical and EEG data. Results: Of the 100 ED patients (mean age 64.5 ± 15.7), 63 were ultimately discharged with a diagnosis of stroke (43 ischemic, 7 hemorrhagic) or TIA (13). Median time from last known well (LKW) to EEG was 9.4 hours; from ED arrival to EEG, 3.7 hours. Median time to prepare/place EEG leads then initiate recording was 9 min, shortened during the study (p<0.0001), and was as brief as 36 seconds. To classify patients as stroke/TIA vs non-stroke: [1] The clinical data (including LKW and Rapid Arterial Occlusion Evaluation score) model had AUC=62.3. [2] The EEG data (Lasso selected 4 frontocentral leads, in higher frequencies) model had AUC=78.2. [3] The clinical+EEG data model had AUC=80.3. [4] The deep learning neural network model yielded AUC=87.8. Conclusions: The data support the feasibility of using a dry lead EEG system to rapidly acquire EEG in the acute stroke ED setting and suggest utility to improve prehospital stroke diagnosis once acquisition and analysis approaches are appropriately streamlined. EEG captures a signal that is diagnostically useful, independent from clinical measures, and improves the precision with which acute stroke can be diagnosed.