Motion evaluation of video recorded on a smartphone accurately detected narrowed arteries within the neck, that are a risk factor for stroke, in keeping with recent research published today within the Journal of the American Heart Association, an open access, peer-reviewed journal of the American Heart Association.

Fatty deposits (plaque) can accumulate in arteries causing them to narrow (stenosis). Narrowed arteries within the carotid artery (within the neck) may cause an ischemic stroke, which occurs when a vessel that supplies blood to the brain is obstructed by a clot. Nearly 87% of all strokes are ischemic strokes.

Between 2% and 5% of strokes every year occur in individuals with no symptoms, so higher and earlier detection of stroke risk is required.”

Hsien-Li Kao MD, Study Lead Writer and Interventional Cardiologist, National Taiwan University Hospital

“This was an exciting ‘eureka’ moment for us,” Kao said. “Existing diagnostic methods – ultrasound, CT and MRI – require screening with specialized medical imaging equipment and personnel. Evaluation of video recorded on a smartphone is non-invasive and simple to perform, so it might provide a possibility to extend screening. Though more research and development are needed, the recordings and motion evaluation may have the option to be implemented remotely, or a downloadable app may even be feasible.”

Arteries within the neck are only beneath the skin’s surface and changes in the rate and pattern of blood flow through them are reflected within the motion of the overlying skin, Kao explained. Nevertheless, these differences are too subtle to be detected by the naked eye.

This study, conducted between 2016 and 2019, used motion magnification and pixel evaluation to detect the minute changes in pulse characteristics on the skin’s surface captured in a smartphone video recording.

A gaggle of 202 Taiwanese adults (average age of 68 years; roughly 79% men) who received care at a single Taiwanese hospital participated within the study. Among the many participants, 54% had significant carotid artery stenosis, meaning they’d at the least 50% blockage that was previously diagnosed by ultrasound, while 46% didn’t have significant stenosis. Recordings were captured with participants laying on their back, with their head tilted back in a custom-made box that minimized outside movement. An Apple iPhone 6, 64GB, was mounted to the box to capture a 30-second video recording of the person’s neck. The older generation phone was used as researchers believed it will be more common to the common user, Kao explained.

Researchers found that the video motion evaluation algorithm had an 87% accuracy rate of detecting stenosis within the group known to have carotid artery stenosis. All study participants also had standard Doppler ultrasound testing to verify narrowing of their arteries and to gauge and validate the estimates from the video motion evaluation.

“More research is required to find out whether video recorded on smartphones is a promising approach to assist expedite and increase stroke screening,” Kao said. “Carotid artery stenosis is silent until a stroke happens. With this method, clinicians may have the option to record a video of the patient’s neck with a smartphone, upload the videos for evaluation and receive a report inside five minutes. The early detection of carotid artery stenosis may improve patient outcomes.”

There have been several limitations to the study including the small variety of study participants, all of whom were considered at high risk for a cardiovascular event. As well as, neck length and neck angle weren’t analyzed, which can affect the outcomes of the video evaluation. Skin color is just not prone to hinder applications to a broader population since a normal lighting method was used for this assessment, in keeping with Kao.

Source:

American Heart Association

Journal reference:

Tsai, C.-H., et al. (2022) Detection of Carotid Artery Stenosis Based on Video Motion Evaluation for Fast Screening. Journal of the American Heart Association. doi.org/10.1161/JAHA.122.025702.