AUTHOR=Korda Athanasia , Wimmer Wilhelm , Wyss Thomas , Michailidou Efterpi , Zamaro Ewa , Wagner Franca , Caversaccio Marco D. , Mantokoudis Georgios 

TITLE=Artificial intelligence for early stroke diagnosis in acute vestibular syndrome

JOURNAL=Frontiers in Neurology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2022.919777

DOI=10.3389/fneur.2022.919777

ISSN=1664-2295

ABSTRACT=Objective: Measuring the Vestibular-Ocular-Reflex (VOR) gains with the video head impulse test (vHIT) is accurately discriminating between peripheral and central causes of acute vestibular syndrome (AVS). In this study, we sought to investigate whether the accuracy of artificial intelligence (AI) for vestibular stroke classification applied in unprocessed vHIT data is comparable to VOR gain classification. 
Methods: We performed a prospective study from February 2015 until September 2020 on all patients presenting at the emergency department (ED) with signs of an AVS.  All patients underwent vHIT followed by a delayed MRI, which served as a gold standard for stroke confirmation. The MRI ground truth labels were then applied to train a recurrent neural network (long short-term memory architecture) that used eye- and head velocity time series extracted from the vHIT examinations. 
Results: We assessed 57 AVS patients, 39 acute unilateral vestibulopathy patients (AUVP) and 18 stroke patients. The overall sensitivity and specificity for detecting stroke with a VOR gain cut-off of 0.57 was 88.8% and 92.3% respectively. Accuracy was 91.2%. The trained neural network was able to classify strokes with an accuracy of 87.9% with a sensitivity of 87.7% and specificity of 88.4% based on the vHIT unprocessed data. The accuracy of these two methods was not significantly different (p = 0.09).
Conclusions: AI can accurately diagnose a vestibular stroke by using only vHIT unprocessed data. The quantification of eye- and head movements with the use of machine learning and AI can serve in the future for an automated diagnosis in ED patients with acute dizziness.