Differentiating ischemic stroke patients from healthy subjects using a large-scale, retrospective EEG database and machine learning methods.

Autor: Peterson W; University of Virginia, Charlottesville, VA, United States. Electronic address: wcp7cp@virginia.edu., Ramakrishnan N; Baylor College of Medicine, Houston, TX, United States., Browder K; Aspen Insights, Dallas, TX, United States., Sanossian N; Roxanna Todd Hodges Stroke Program, United States; Keck School of Medicine of the University of Southern California, United States., Nguyen P; Keck School of Medicine of the University of Southern California, United States., Fink E; Houston Hospital, Houston, TX, United States; Weill Cornell School of Medicine Sciences, New York, NY, United States.
Jazyk: angličtina
Zdroj: Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association [J Stroke Cerebrovasc Dis] 2024 Jun; Vol. 33 (6), pp. 107714. Date of Electronic Publication: 2024 Apr 16.
DOI: 10.1016/j.jstrokecerebrovasdis.2024.107714
Abstrakt: Objectives: We set out to develop a machine learning model capable of distinguishing patients presenting with ischemic stroke from a healthy cohort of subjects. The model relies on a 3-min resting electroencephalogram (EEG) recording from which features can be computed.
Materials and Methods: Using a large-scale, retrospective database of EEG recordings and matching clinical reports, we were able to construct a dataset of 1385 healthy subjects and 374 stroke patients. With subjects often producing more than one recording per session, the final dataset consisted of 2401 EEG recordings (63% healthy, 37% stroke).
Results: Using a rich set of features encompassing both the spectral and temporal domains, our model yielded an AUC of 0.95, with a sensitivity and specificity of 93% and 86%, respectively. Allowing for multiple recordings per subject in the training set boosted sensitivity by 7%, attributable to a more balanced dataset.
Conclusions: Our work demonstrates strong potential for the use of EEG in conjunction with machine learning methods to distinguish stroke patients from healthy subjects. Our approach provides a solution that is not only timely (3-minutes recording time) but also highly precise and accurate (AUC: 0.95).
Competing Interests: Declaration of competing interest W. Peterson, N. Ramakrishnan, Krag Browder, N. Sanossian, P. Nguyen, and E. Fink are all employees, owners, and/or advisors of Asterion AI, a start-up that uses machine learning to understand the nervous system.
(Copyright © 2024 Elsevier Inc. All rights reserved.)
Databáze: MEDLINE