A newly released study finds that one in four Americans may suffer from long COVID, a much higher rate than typically cited. Scientists at Mass General Brigham used a sophisticated AI tool for the peer-reviewed study. While the Centers for Disease Control and Prevention suggested that in 2022 roughly 6.9% of Americans had long COVID, the new research finds the actual number may be 22.8%.

According to The Boston Globe, the new study drew criticism from other COVID researchers who challenged their estimate, but the authors countered that the condition is hard to diagnose and official counts often don’t include patients who are in marginalized communities.

“Long COVID is destined to be underrepresented, and patients are overlooked because it sits exactly under the health system’s blind spot,” said senior author Hossein Estiri, head of AI Research at the Center for AI and Biomedical Informatics at Mass General Brigham.

The AI-based tool developed by the scientists sifted through electronic records of nearly 300,000 patients in 14 hospitals and 20 community centers in the Mass General Brigham health system, according to The Harvard Gazette. Researchers searched for symptoms of long COVID that included fatigue, chronic cough, and brain fog after infection from the SARS-CoV-2 virus.

The study results were published in the journal Med. The researchers said their unique algorithm could help identify more people who should be receiving care for this often-debilitating long-term condition.

“Our AI tool could turn a foggy diagnostic process into something sharp and focused, giving clinicians the power to make sense of a challenging condition,” said Estiri. “With this work, we may finally be able to see long COVID for what it truly is — and more importantly, how to treat it.”

Researchers used a method called “precision phenotyping” to pinpoint symptoms and conditions associated with COVID-19 that weren’t related to the patient’s medical records but were linked to infection. This highly accurate tool can evaluate patients more thoroughly, including those individuals who don’t have easy access to healthcare.

“This broader scope ensures that marginalized communities, often sidelined in clinical studies, are no longer invisible,” said Estiri. The researchers hope that their tool will open the door to new research into other medical conditions such as diabetes and COPD. They plan to make the AI tool public so that other healthcare professionals can access the information.

Their current research has now revealed a new understanding about the genetic and biochemical factors that drive long COVID. “Questions about the true burden of long COVID — questions that have this far remained elusive — now seem more within reach,” said Estiri.