It's also expected to help public health identify hot spots of infection and determine just how infectious the virus that causes COVID-19 really is.
The app is the brainchild of Dr. Jose Vazquez, chief of AU's Division of Infectious Diseases, and Dr. Arni S.R. Srinivasa Rao, director of the Laboratory for Theory and Mathematical Modeling in the Division of Infectious Diseases. It builds on mathematical modeling the division has already done to more accurately predict the spread of other infectious diseases such as hepatitis C that have been shared with the Centers for Disease Control and Prevention.
The modeling on this virus, severe acute respiratory syndrome coronavirus 2 or SARS CoV2, is also being shared with CDC and Rao is scheduled to present on it at CDC later this month.
With the app, which should be finished within the next couple of weeks, anyone in the U.S. could download it and enter information through their phone so that an algorithm can assess their risk, Rao said. The app could then class them from low-risk to high-risk and then direct high-risk respondents to the nearest testing site.
As happened in other countries and elsewhere, if everyone who is worried about whether they have SARS CoV2 shows up at the Emergency Room or clinics, "they're going to over-saturate the health care system," Vazquez said. "And we only have a certain number of limited" resources.
Previous case studies have shown that about 80 percent of the infections from the virus have been mild and don't need hospitalization and could be treated and isolated at home, he noted.
"Our key is really keeping coronavirus patients out of the hospital," Vazquez said.
Most patients would be "already at home so they don't have to" go to the ER, Rao said. Those at low risk could be spared a trip to get tested.
The app could also aid public health because artificial intelligence would then gather and process thousands of data points to help better predict outbreaks, Rao said.
"The more data we can feed into the system, the AI can predict whether that particular region is infected, which particular blocks or census tracts are infected," he said. The app will also learn from the data and the risk factors to better refine its own risk modeling, he said.
The value in public health will be in being able to know where those hot spots are, Vazquez said.
"For instance, we could be having an outbreak in south Augusta and this app would or the data generated would pick it up," he said. "So we know where a lot of these patients are coming from, which could be a common source. An individual who is asymptomatic could infect many, many people."
A preliminary analysis from the Chinese Centers for Disease Control and Prevention found that about 1 percent of the positive patients in the outbreak there were asymptomatic, Vazquez noted. And it is knowing how many of those patients there are, where most places are just testing those that have symptoms, that is preventing researchers from determining how infectious the virus is, he said.
That is the big problem we have with coronavirus, all over the world now," Vazquez said.
©2020 The Augusta Chronicle (Augusta, Ga.). Distributed by Tribune Content Agency, LLC.
