Clinicians can use AI to screen patients and identify the probability of COVID-19 prior to testing, according to a study published April 13 in ScienceDaily.
Researchers from the College of Health and Human Services at Fairfax, Va.-based George Mason University created algorithms to predict the probability that a patient has COVID-19, the flu, or another respiratory illness prior to testing.
Here's what they found:
- The algorithms were created by analyzing the symptoms reported by 774 COVID-19 patients in China, 273 COVID-19 patients in the U.S., and 2,885 influenza and 884 influenza-like illnesses in U.S. patients.
- The researchers found that the algorithms helped healthcare providers triage patient care while they are waiting on lab testing.
- But, the algorithms proved to be too complex to expect clinicians to perform these calculations while providing care.
- The researchers suggested that a web-based AI calculator can be used to allow clinicians to arrive at a presumed diagnosis prior to a patient's visit.
"When there is a new outbreak, collecting data is time consuming," said Farrokh Alemi, PhD, principal investigator and professor of health administration and policy at the College of Health and Human Services. "Analysis of existing data can reduce the time to differentiate presentation of new diseases from illnesses with overlapping symptoms."