Scientists are working overtime amid the COVID-19 pandemic, developing everything from pharmaceuticals to masks to apps. In separate projects, university researchers have developed two COVID-19-related apps—one that permits contact tracing for coronavirus infections and one that attempts to detect signs of the disease through voice analysis.
TrackCOVID
As countries and governments struggle to deal with the COVID-19 pandemic, some have proposed monitoring the location of citizens at any given time. For example, three weeks ago, the Czech Republic announced a plan to use real-time phone-location data to track the movements of virus carriers and people they come in contact with. Almost two weeks ago, South Korea’s government said it will strap electronic wristbands on people who defy self-quarantine orders. In the United States, Apple and Google said they plan to add software to iPhones and Android phones that will make it easier to use Bluetooth technology to track down people who may have been infected by COVID-19 carriers.
Of course, these plans have been met with sharp criticism and claims of invasion of privacy. Researchers at the University of California, Irvine may have found a way around that, though. They designed TrackCOVID, a free, open-source app that permits contact tracing for potential coronavirus infections while preserving privacy.
According to the research team, TrackCOVID is different from other contact tracing solutions because it does not require the continuous tracking of a person’s locations. Rather, it creates an anonymous graph of interactions. Every time a person gathers with others or goes to a public place, he or she can use the app to log contacts by either hosting or joining a checkpoint, which allows possible paths of virus transmission to be discovered. The first person to register as a checkpoint host is given a Quick Response code; others subsequently join the checkpoint by scanning this QR code. As people congregate with others over time, their interactions are linked to each other anonymously. Anyone who tests positive for COVID-19 can report it through the app without revealing his or her identity. Using the graph of interactions, the app can notify users who may be at elevated risk of exposure.
The team’s project is detailed in a paper published recently in JMIR mHealth and uHealth.
COVID Voice Detector
Test kits for COVID-19 are in short supply globally. Most analysis assumes there are more COVID-19 cases than being reported, but due to mild symptoms and a lack of available tests, there is no way to confirm suspicions.
While not approved by the FDA, CDC or any public health agency, researchers at Carnegie Mellon have released an early version of an app they say can determine if you have COVID-19 just by analyzing your voice.
“What we are attempting to do is to develop a voice-based solution, which, based on preliminary experiments and prior expertise, we believe is possible. The app’s results are preliminary and untested,” Bhiksha Raj, a professor at Carnegie Mellon, told Futurism. “The score the app currently shows is an indicator of how much the signatures in your voice match those of other COVID patients whose voices we have tested. This is not medical advice. The primary objective of our effort/website at this point of time is to collect large numbers of voice recordings that we could use to refine the algorithm into something we—and the medical community—are confident about.”
The app is still a work in progress but the researchers say it could be a valuable tool in tracking the spread of the virus. The research team includes Carnegie computer science professor Rita Singh, who is an expert in creating algorithms that identify micro-signatures in the human voice that may reveal medical status.
In designing the app, the team gathered audio from patients with and without COVID-19, as well as patients with other viruses, such as the flu. The team then trained the app algorithm to spot the differences between the types of coughs in each sub-population.
The app is simple to use. From a smartphone or computer with a microphone, users are asked to cough several times, records vowel sounds and receipt the alphabet. The app then provides a score representing how likely the algorithm believes it is that you have COVID-19.
While the app’s accuracy cannot be determined at the moment, the researchers say the algorithm will only get better as the user base increases. You can assess the app here.
Photo: The TrackCOVID smartphone application, developed by UCI researchers, works by allowing users to log their interactions anonymously, making it easier to trace when and where people may have come in contact with someone carrying the COVID-19 virus. Photo credit: Tyler Yasaka, Brandon Lehrich and Ronald Sahyouni/UCI