Background and Purpose: Clinical methods have incomplete diagnostic value for early diagnosis of acute stroke and large vessel occlusion (LVO). Electroencephalography is rapidly sensitive to brain ischemia. This study examined the diagnostic utility of electroencephalography for acute stroke/transient ischemic attack (TIA) and for LVO. Methods: Patients (n=100) with suspected acute stroke in an emergency department underwent clinical exam then electroencephalography using a dry-electrode system. Four models classified patients, first as acute stroke/TIA or not, then as acute stroke with LVO or not: (1) clinical data, (2) electroencephalography data, (3) clinical+electroencephalography data using logistic regression, and (4) clinical+electroencephalography data using a deep learning neural network. Each model used a training set of 60 randomly selected patients, then was validated in an independent cohort of 40 new patients. Results: Of 100 patients, 63 had a stroke (43 ischemic/7 hemorrhagic) or TIA (13). For classifying patients as stroke/TIA or not, the clinical data model had area under the curve=62.3, whereas clinical+electroencephalography using deep learning neural network model had area under the curve=87.8. Results were comparable for classifying patients as stroke with LVO or not. Conclusions: Adding electroencephalography data to clinical measures improves diagnosis of acute stroke/TIA and of acute stroke with LVO. Rapid acquisition of dry-lead electroencephalography is feasible in the emergency department and merits prehospital evaluation.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.