Covid-19 app to measure blood oxygen saturation and pulse rate
COVID-19, the disease caused by the coronavirus, affects the lungs, resulting in pneumonia in serious cases. Medical professionals can use a technique called pulse oximetry — the measurement of oxygen level in the blood — to detect a decline in blood oxygen saturation, which can indicate problems with lung function such as those found in more severe cases of COVID-19. Usually, this technique requires a device clipped to the tip of a finger that uses light to measure oxygen in red blood cells as well as heart rate.
In order to minimize contact between people, however, the CDC and other health experts have advised those who suspect they may have COVID-19 to stay home and call a doctor to assess their symptoms before determining whether they should go to a hospital (but, to call 911 if it is an emergency). Furthermore, COVID-19 patients discharged from the hospital may want to continue to track their condition. It can sometimes be challenging, though, for people to communicate the details of their symptoms to a doctor over the phone, and most don’t have access at home to equipment like pulse oximeters to quantitatively self-monitor and relay those values to their doctor on a telemedicine call.
“The idea started from a conversation with an A&E MD in Bergamo,” Product Lead Dario D’Aprile explained. Bergamo is a small town in northern Italy, an “epicenter” for COVID-19. Now, a team of over a hundred volunteers, working together online through Slack and Github, is developing a solution to help people monitor their blood oxygen levels at home using only their phones. This project, CoVital, is supported by Helpful Engineering.
CoVital’s objective is “to build a completely open-source mobile application that accurately measures blood oxygen saturation and heart rate,” in order to enable “inclusive monitoring” for the public. With the CoVital app, currently under development, a smartphone camera could be used in concert with an algorithm to measure blood oxygen saturation and heart rate from video data. The project team also plans to have a “health diary” built into the app, so that users could keep a detailed personal record to share with medical professionals.
There are already other pulse ox apps, but the current ones are not accurate, D’Aprile says. CoVital hopes to fill this need and help COVID-19 patients share data with medical professionals. The project’s Science Lead, Yoni Schirris, said it was important that individuals be able to self-monitor at home because of anecdotes of people who were rightly admitted to a hospital only because they happened to have a pulse oximeter and were able to share with the hospital their decreasing blood oxygen levels.
“We want this to be available to everyone in the world who owns a smartphone,” Schirris wrote. Mr. D’Aprile adds that this idea has been at the core of the project from the beginning, and is the reason that the CoVital app will not require dedicated devices.
Right now, CoVital is in a test stage; the team is working with scientists at the Vrije Universiteit Amsterdam to develop methods of translating video data from smartphone cameras into the values described above that could be informative to app users and their doctors. The CoVital team is looking for ways to collect a high volume of data from patients, and investigating machine-learning methods for the design of the app’s algorithm.
We asked the project leaders what CoVital needs right now: “CoVital most needs MDs/nurses who want to use our mobile application to collect fingertip video data while filling in the true SpO2 value from clinical-grade pulse oximeters.” Mr. Schirris wrote that this data collection is necessary for the delivery of a “state-of-the-art” algorithm.
Algorithms must be trained in order to learn to identify patterns (like a pattern between qualities of a video and blood oxygen level). For example, if you wanted to teach an algorithm to accurately identify cars in photographs, you’d have to show it many, many photos of cars, contrasted with many photos of non-cars, in order to train it to recognize cars before testing could commence with new photos that it had to sort itself. In the same fashion, CoVital’s algorithm needs to be trained to link fingertip video data with the actual, known blood oxygen saturation values of the subject in each video in order to accurately measure blood oxygen saturation with new, unknown fingertip video data in the future.
See the CoVital website: www.covital.org
Learn more about this project: here
Want to help? Learn how to volunteer: here
These designs are presented As-Is. The goal is to present designs that can foster further discussion and be utilized in countries that permit this product. These are not finalized designs and do not represent certification from any country. You accept responsibility and release Helpful Engineering from liability for the manufacture or use of this product. This design was created in response to the announcement on March 10, 2020, from the HHS. Secretary of the Department of Health and Human Services (HHS) who issued a declaration pursuant to the Public Readiness and Emergency Preparedness (PREP) Act.
Link to Prep act. :https://www.phe.gov/Preparedness/legal/prepact/Pages/default.aspx
ALL WARRANTIES OF ANY KIND WHATSOEVER, EXPRESS, IMPLIED AND STATUTORY, ARE HEREBY DISCLAIMED. ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE HEREBY DISCLAIMED. THIS DEVICE (INCLUDING ANY ACCESSORIES AND COMPONENTS) IS PRESENTED ‘AS IS.’