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

• Published in: Journal of stroke and cerebrovascular diseases Vol. 33; no. 6; p. 107714
• Main Authors: Peterson, William, Ramakrishnan, Nithya, Browder, Krag, Sanossian, Nerses, Nguyen, Peggy, Fink, Ezekiel
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.06.2024
• Subjects: Electroencephalogram (EEG); Feature engineering; Ischemic stroke; Large vessel occlusion; Machine learning; Prehospital stroke scale; Electroencephalogram (EEG); Ischemic stroke; Feature engineering; Prehospital stroke scale; Machine learning; Large vessel occlusion
• ISSN: 1052-3057; 1532-8511; 1532-8511
• DOI: 10.1016/j.jstrokecerebrovasdis.2024.107714

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. 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). 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. 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).