Artificial intelligence, season could help physicians predict COVID-19, flu in patients

Physicians could use artificial intelligence (AI), along with seasonality, to predict whether patients have COVID-19 or flu, according to a new study.

Researchers analyzed patients in the United States and China to create an algorithm that predicts the likelihood patients have COVID-19, flu, or another respiratory illness prior to testing.

The information can help clinicians triage patients who are most suspected of having COVID-19, and could be helpful creating rapid responses in future pandemics, according to a press release about the findings.

“When access to reliable COVID testing is limited or test results are delayed, clinicians, especially those who are community-based, are more likely to rely on signs and symptoms than on laboratory findings to diagnose COVID-19,” principal investigator Farrokh Alemi said in a press release. Alemi observed those challenges throughout the pandemic.

“Our algorithm can help health care providers triage patient care while they are waiting on lab testing or help prioritize testing if there are testing shortages,” said Alemi, professor of health administration and policy at George Mason University.

The algorithms are helpful but “too complex to expect clinicians to perform these calculations while providing care, Alemi said.

“The next step is to create an AI, web-based, calculator that can be used in the field,” Alemi said in the press release. "This would allow clinicians to arrive at a presumed diagnosis prior to the visit,” then make triage decisions while waiting for official lab results.

The researchers created the algorithms by analyzing symptoms reported by 774 COVID patients in China and 273 COVID patients in the United States. The analysis also included 2,885 influenza and 884 influenza-like illnesses in US patients.

The findings suggested community-based health care providers should follow different signs and symptoms for diagnosing COVID depending on the time of year, according to the researchers.

For example, outside of flu season, fever is an even stronger predictor of COVID than during flu season. During flu season, a person with a cough is more likely to have the flu than COVID. The study showed that assuming anyone with a fever during flu season has COVID would be incorrect.

“Modeling the Probability of COVID-19 Based on Symptom Screening and Prevalence of Influenza and Influenza-Like Illnesses” was published in Quality Management in Health Care’s April/June 2022 issue.