Researchers at West Virginia University are well placed to tap AI for teasing out the role of existing respiratory concerns in the progression of COVID-19.
How so? The Mountain State is home to an abundance of smokers (25% of the population), asthma sufferers (tied with Maine for first) and past or present coal miners (largest employer of coal workers as of 2016).
The work is being undertaken by a study team led by Larissa Casaburi, MD, an associate professor of radiology. She and colleagues will focus on outcomes of COVID patients who have existing lung issues.
According to a WVU news release, the project has received $30,000 from the West Virginia Clinical and Translational Science Institute. The team will apply the resulting resources to training a machine learning model on demographic and health data from West Virginia’s COVID-19 Registry.
Then they’ll test the model’s acumen for accurately predicting outcomes.
En route to issuing these, the algorithm will consider preexisting conditions, review lung CT scans and take into account other relevant risk factors.
“One of the features of machine learning is that it can develop personalized predictive models,” Casaburi says in the news release. “It’s a novel approach to improve patients’ care, and there’s a lot of research interest in it.”