Smartphone Video Analysis Can Identify Narrowing Arteries in Neck

Published on: 

A study of 202 patients in Taiwan suggests use of a video motion analysis using video captured from a smartphone could help identify carotid artery stenosis.

New research from investigators in Taiwan suggests smartphone cameras could be used to identify narrowed arteries in the neck, which investigators suggest could help revolutionize stroke prevention.

An analysis using video‐based motion analysis (VMA) from video captured through a smartphone could help identify and provide a novel noninvasive and noncontact detection method for clinicians.

“This was an exciting ‘eureka’ moment for us,” said Hsien-Li Kao, MD, an interventional cardiologist at National Taiwan University Hospital in Taipei, Taiwan, in a statement. “Existing diagnostic methods – ultrasound, CT and MRI – require screening with specialized medical imaging equipment and personnel. Analysis of video recorded on a smartphone is non-invasive and easy to perform, so it may provide an opportunity to increase screening. Though more research and development are needed, the recordings and motion analysis may be able to be implemented remotely, or a downloadable app may even be feasible.”

Funded by the Ministry of Science and Technology in Taiwan, the present study was designed by Kao and a team of colleagues to examine whether VMA could provide an alternative to Carotid Doppler ultrasound, which Kao and team pointed out is costly and may not be suitable for use in regular screenings. With this in mind, investigators designed their study to validate and assess use of a VMA-based detection technique for identifying useful information from subtle pulses on the skin surface to identify carotid artery stenosis.

Conducted from 2016-2019, the study enrolled 202 patients who had undergone carotid Doppler ultrasonography using an EPIQ Ultrasound system before the video for VMA was recorded. Of these 202, 40 were used in the setup cohort, which was, and 162 were used in the validation cohort. Investigators pointed out the setup cohort had 20 patients with carotid artery stenosis and 20 without carotid artery stenosis. In the validation cohort, 89 patients had carotid artery stenosis and 73 did not.

Of the 109 patients with carotid artery stenosis, 31% had isolated right-sided stenosis, 27% had isolated left-sided stenosis, and 42% had bilateral stenosis. Compared to those without carotid artery stenosis, patients with carotid artery stenosis were significantly older, were predominantly women, had a lower body mass index, and more had a history of head and neck radiation.

Using a receiver operating characteristic curve analysis, investigators found the area under the curve of VMA-derived discrepancy values to differentiate patients with and without carotid artery stenosis was 0.914 (95% CI, 0.84-0.954; P <.01). Based on these results, investigators determine the best cutoff value of VMA-derived discrepancy values to screen for carotid artery stenosis was 5.1, with a sensitivity of 87% and a specificity of 87%. Investigators also pointed out the diagnostic accuracy observed with the VMA was consistently high across patient subgroups.

Investigators noted multiple limitations within their stud. Specific imitations highlighted within the aforementioned statement included the small number of participants and not assessing neck length or angle. However, investigators also pointed out that, since standard lighting was used, they did not expect skin color to be likely to hinder applications to a broader population.

“More research is needed to determine whether video recorded on smartphones is a promising approach to help expedite and increase stroke screening,” Kao said. “Carotid artery stenosis is silent until a stroke happens. With this method, clinicians may be able to record a video of the patient’s neck with a smartphone, upload the videos for analysis and receive a report within five minutes. The early detection of carotid artery stenosis may improve patient outcomes.”

This study, “Detection of Carotid Artery Stenosis Based on Video Motion Analysis for Fast Screening,” was published in the Journal of the American Heart Association.