Smartphone cameras can now be used to monitor heartrate and breathing, making them perfect for teleh
As we highlighted in a previous blog post, telehealth/telemedicine services have come into their own during the Covid-19 pandemic, allowing patients to connect with their clinicians in a way that’s fast, convenient and safe.
However, remote consultations often have their limitations, including how to perform diagnostic tests and take medical measurements. But now researchers from the University of Washington have devised a way to measure patients' pulse and breathing rates via a smartphone's camera. The researchers say the advancement will make telehealth more accurate and useful.
According to UW News, the system, called MetaPhys, can detect a patient’s pulse or respiration rate using in real-time using video of their face.
"Machine learning is pretty good at classifying images. If you give it a series of photos of cats and then tell it to find cats in other images, it can do it," Xin Liu, the study's lead author and a student in the Paul G. Allen School of Computer Science & Engineering doctoral student, told UW News.
"But for machine learning to be helpful in remote health sensing, we need a system that can identify the region of interest in a video that holds the strongest source of physiological information — pulse, for example — and then measure that over time."
The team's original iteration of MetaPhys was presented last December at the Neural Information Processing Systems conference. However, the first iteration had some pitfalls, most notably that it struggled with certain lights, backgrounds and skin colors. The second version, the researchers say, improves upon the first and overcomes these limitations.
*Image courtesy of tookapic from Pixabay