Machine Learning

Wireless visor detects severe stroke in seconds

BY SVER AUNE

Clinical researchers at the Medical University of South Carolina (MUSC), Mount Sinai, the University of Tennessee Health Sciences Center and elsewhere tested a new device worn like a visor that can detect emergent large-vessel occlusion in patients with suspected stroke. In a study appearing online on March 6, 2018, in the Journal of Neurointerventional Surgery, the volumetric impedance phase shift spectroscopy (VIPS) device (Cerebrotech Visor™, Cerebrotech Medical Systems, Pleasanton, CA) displayed 92 percent accuracy when detecting large-vessel stroke, compared to 40 to 89 percent accuracy using standard physical examinations.¹

 Endovascular therapy at a comprehensive stroke center within 24 hours is the standard of care for emergent large-vessel occlusion, but the chance of achieving a good outcome decreases by approximately 20 percent for each hour that passes before treatment.² The accuracy of the device simplifies the decisions made by emergency personnel about where to take patients first, according to Raymond D. Turner, M.D., professor of neurosurgery and chief of the Neuroscience Integrated Center of Clinical Excellence at MUSC Health. Turner served as principal investigator for MUSC in the VIPS for the Non-Invasive Detection of Hemispheric Bioimpedance Asymmetry in Severe Brain Pathology (VITAL, NCT03148340) study reported in the article.

“Transfer between hospitals takes a lot of time,” says Turner. “If we can give the information to emergency personnel out in the field that this is a large-vessel occlusion, that should change their thought process in triage as to which hospital they go to.”

The noninvasive wireless VIPS device works by sending low-energy radio waves through the brain. When a patient has a severe stroke, the brain’s fluids change, producing an asymmetry in the radio waves detected by the device. The greater the asymmetry, the more severe the stroke.

In the study, the VIPS device was deployed with emergency medical personnel in regions served by five comprehensive stroke centers. Both healthy participants and those with suspected stroke were evaluated by three readings taken and averaged using the VIPS device — a process that takes about 30 seconds. Patients were later evaluated by neurologists who provided definitive diagnoses using neuroimaging.

Compared with the neurologists’ diagnoses, the device displayed 92 percent specificity — the ability to detect the difference between severe stroke and mild stroke or no brain pathology. This places the VIPS device above standard physical examination tools used by emergency personnel such as the Prehospital Acute Stroke Severity Scale that display specificity scores between 40 and 89 percent.

In their next steps, the researchers are undertaking the VITAL 2.0 study to determine if the VIPS device can use complex machine learning algorithms to teach itself how to discriminate between minor and severe stroke without the help of neurologists. This could lead to widespread clinical implications. “This could potentially be something like an electrocardiogram,” says Turner. “You can find out if a patient is having a stroke, just like you can use an electrocardiogram to see if a patient is having a heart attack.”

References

1. Kellner CP, et al. J Neurointerv Surg. Published Online First: 06 March 2018. doi: 10.1136/neurintsurg-2017-013690.

2. Saver JL, et al. JAMA. 2016;316:1279-1288.