Mines professors building app to predict likelihood of catching COVID-19

Another is studying how stay-at-home orders have impacted streams

Paul Albani-Burgio
palbaniburgio@coloradocommunitymedia.com
Posted 5/26/20

Colorado School of Mines professors have received two National Science Foundation grants for projects related to COVID-19, including one effort to produce a mobile app that could be used to predict …

This item is available in full to subscribers.

Please log in to continue

Username
Password
Log in

Don't have an ID?


Print subscribers

If you're a print subscriber, but do not yet have an online account, click here to create one.

Non-subscribers

Click here to see your options for becoming a subscriber.

If you made a voluntary contribution in 2019-2020, but do not yet have an online account, click here to create one at no additional charge. VIP Digital Access includes access to all websites and online content.


Our print publications are advertiser supported. For those wishing to access our content online, we have implemented a small charge so we may continue to provide our valued readers and community with unique, high quality local content. Thank you for supporting your local newspaper.

Mines professors building app to predict likelihood of catching COVID-19

Another is studying how stay-at-home orders have impacted streams

Posted

Colorado School of Mines professors have received two National Science Foundation grants for projects related to COVID-19, including one effort to produce a mobile app that could be used to predict how likely someone is to suffer dangerous complications if they get the disease.

Judith Klein-Seetharaman, the director of bioscience and bioengineering at Mines, and Hua Wang, an associate professor of computer science at the school, are teaming up on the effort to develop the computational model that will provide the foundation for the app, which will synthesize patient data to create a model to predict future COVID-19 outcomes.

“We are going to use existing COVID-19-related patient data and proteomics data and develop a computational model that will take all of the different types of risk factors into account such as comorbidities, lifestyle factors, symptoms and behavioral information,” said Klein-Seetheraman. “And we will develop a model from this and then an individual or a physician will be able to enter this information to give a score for that person.”

That score will then indicate the person’s probability of getting COVID-19 or, if they already have the disease, their likelihood of developing complications. A high score would mean someone should call a doctor because they are likely to be infected or develop complications, Klein-Seetharaman said.

The pair said they are hoping to have a first version of the app, which will be called iCOVID and made available for free on the iTunes app store and Google play, up and running in five or six weeks. However, they said the grant funding they have received lasts for one year, which will allow the pair to improve the model and app interface while incorporating user feedback.

So far, one of the pair’s main challenges has been the difficulty accessing patient data, which hospitals usually do not make available for privacy reasons. To get around those concerns, the team has used anonymized data from medical databases, which still presents an obstacle since it can take awhile for COVID-19-related patient data to become available.

Klein-Seetharaman said she contacted Wang, who she worked with on other projects, about bringing his expertise to the project when she realized how many factors seem to be involved in COVID-19 risk. Wang’s research focuses on machine learning, which is the study of computer algorithms that improve automatically through experience and can be used to synthesize complex data.

“So, when we work together we can use the machine learning knowledge from my side as well as the experience and knowledge from Judy’s side to collectively build some more useful tools,” said Wang.

But while the app will be able to help someone who gets a cough determine the likelihood that they have COVID-19, Klein-Seetharaman said the app could also be utilized for planning by hospitals and even governments.

“Hospitals need to be able to predict how many beds they need and how many respirators they need and so on and our app could potentially help with that by helping to predict what is the chance that you are going to have n number of patients with complications,” she said. “And then it can also be used by local and even global governments to evaluate what the risk is and what we need to plan for.”

John McCray, a professor of civil and environmental engineering, also received a NSF grant for a project that will study the impact of Colorado’s stay-at-home orders on the quality of urban streams in metro Denver.

“The COVID-19 pandemic could potentially accelerate future sustainable living practices into typical living scenarios,” McCray wrote in a section of his proposal included in an article on the Mines website. “Research is underway looking at air pollution but little has been done to understand the impacts on water quality. Cleaner, fishable and swimmable urban rivers would be another justification for sustainable living that includes working from home and much less driving. The information will also be useful to urban planners regarding types of green infrastructure for cleaning urban water, and to public health officials and legislators for urban water quality management.”

Comments

Our Papers

Ad blocker detected

We have noticed you are using an ad blocking plugin in your browser.

The revenue we receive from our advertisers helps make this site possible. We request you whitelist our site.