AI could determine long COVID risk factors, new research says

New findings out of the NIH have potential to improve clinical research on long COVID and lead to a more regulated treatment regiment.

 The COVID-19 vaccine (illustrative). (photo credit: PIXABAY)
The COVID-19 vaccine (illustrative).
(photo credit: PIXABAY)

Since the onset of the COVID-19 pandemic, researchers have remained puzzled by the cause of long-haul COVID, in which individuals experience symptoms that last for weeks or months after the initial coronavirus infection has passed.

Scientists at the National Institutes of Health (NIH), determined to learn more about long COVID, used machine learning artificial intelligence – and, according to a study published in The Lancet Digital Health this week, they’ve already found some success in pinpointing the risk factors for the condition. 

The findings, which are based on patient medical records, have the potential to improve clinical research on long COVID and lead to a more regulated treatment regimen.

Long COVID affects people regardless of prior health conditions and vaccination status, leaving them with long-lasting fatigue, “brain fog,” headaches or chest pain, and more.

Research published last month found that 30% of people treated for COVID-19 developed Post Acute Sequelae of COVID-19 (PASC), commonly known as “long COVID.”

In the study, the researchers pulled data from the electronic health records of nearly 100,000 adults who had tested positive for the virus — both minor and severe cases — including almost 600 who were diagnosed as long-haulers and treated in a long COVID clinic.

 Office workers go for lunch at the central business district on the first day free of coronavirus disease (COVID-19) restrictions in Singapore April 26, 2022.  (credit: REUTERS/EDGAR SU) Office workers go for lunch at the central business district on the first day free of coronavirus disease (COVID-19) restrictions in Singapore April 26, 2022. (credit: REUTERS/EDGAR SU)

Using data on the patients’ demographics, healthcare utilization, diagnoses and medications, the NIH-backed team trained a trio of machine learning models to look for data points that distinguish long-haulers from those diagnosed with COVID but without the follow-up condition.

With that information, AI was able to sift through a larger database of de-identified EHRs that represented nearly five million people who have tested positive for COVID.

In records dating up to October 2021, the model was able to spot more than 100,000 people who had many of the risk factors and symptoms of long COVID; the researchers estimate that the number has since doubled.

The model pointed to several factors that seem to carry the most weight in determining whether a COVID-positive person will go on to develop long COVID.

They include the presence of long-term respiratory symptoms and non-respiratory symptoms like sleep disorders, chest pain and malaise after the acute COVID infection has passed, as well as preexisting risk factors that make for more severe acute COVID infections including chronic conditions like diabetes, kidney disease and pulmonary disease.

AI also determined that receiving a COVID vaccination after recovering from the infection lessened the risk of being labeled as a potential long-hauler. 

Researcher Josh Fessel said there are more questions to be explored.

“Once you’re able to determine who has long COVID in a large database of people, you can begin to ask questions about those people," he said. "Was there something different about those people before they developed long COVID? Did they have certain risk factors? Was there something about how they were treated during acute COVID that might have increased or decreased their risk for long COVID?”