Wish you could check your vital stats while brushing your teeth? Thanks to the new innovation by MIT PhD student Ming-Zher Poh, reading your pulse and other vital stats may someday be as easy as standing in your bathroom.
Working with public-domain software, Poh developed a way to measure the pulse by analyzing subjects sitting in front of a two-way mirror.
The MIT Media Lab Medical Mirror is equipped with a computer monitor along with a built-in camera that tracks changes in brightness produced by blood flow through the vessels in the face. Behind the two-way glass, the webcam-equipped monitor is wired to a laptop. Stand before the mirror, and the blank monitor projects your heart rate on top of your reflection.
When your heart beats, it sends a pulse of blood through your blood vessels. Blood absorbs light, so when more of it travels through the vessels, less of the light hitting your skin is reflected. A webcam can pick up those small fluctuations in reflected light, Poh says, and a computer program can translate that data into a heart-rate reading.
While the Medical Mirror can currently only provide pulse readings, Poh hopes further work will allow him to obtain blood pressure and blood oxygen measurements from the same images. Poh’s concept could not only help monitor patients’ health minus the wires and physical sensors but it could also help doctors keep better track of their patients without costly office visits.
Researchers had tracked this effect with a high-resolution camera, but Poh wanted to use a simple webcam so that nearly every computer and smartphone could double as a heart-rate monitor. To make that possible, he developed an algorithm that could pick out the heart rate’s light pattern from all the other reflected light captured by a webcam. With help from McDuff, a grad student at the MIT Media Lab, Poh wrote code to process the data in real time, allowing the laptop to generate an instant heart-rate reading.
So far, graduate student Ming-Zher Poh has demonstrated that the system can indeed extract accurate pulse measurements from ordinary low-resolution webcam imagery. Now he’s working on extending the capabilities so it can measure respiration and blood-oxygen levels. He hopes eventually to be able to monitor blood pressure as well.
Poh suggests that such noninvasive monitoring could prove useful for situations where attaching sensors to the body would be difficult or uncomfortable, such as for monitoring burn victims or newborns.
It could also be used for initial telemedicine screening tests over the Internet using a patient’s own webcam or even cell-phone camera. Such a system could also be built into a bathroom mirror so that patients who need ongoing monitoring, or just people who want to keep track of their own health, could get pulse, respiration, oxygen saturation and blood-pressure readings routinely while they brush their teeth or wash up, displayed in a corner of the mirror.
Public-domain software is used to identify the position of the face in the image, and then the digital information from this area is broken down into the separate red, green and blue portions of the video image.
The big challenge was dealing with movements of the subject and variations in the ambient lighting. But Poh was able to adapt signal-processing techniques originally developed to extract a single voice from a roomful of conversations, a method called Independent Component Analysis, in order to extract the pulse signal from the “noise” of these other variations.
The system produced pulse rates that agreed to be within about three beats per minute with the rates obtained from the approved monitoring device, and was able to obtain valid results even when the subject was moving a bit in front of the camera. In addition, the system was able to get accurate pulse signals from three people in the camera’s view at the same time.
Poh continues to work on developing the capability to get blood pressure and blood-oxygen measurements from the same video images. Extracting such data from optical imagery should work, he says, since conventional blood oxygen sensors already work by using optical detection, although they use a dedicated light source rather than ambient lighting.
“It’s not going to be easy,” he says of the next steps. “But it theoretically should be possible.”
For more information please visit: www.mit.edu
