A groundbreaking AI-assisted analysis has revealed that long COVID may be significantly more prevalent than previously thought, affecting nearly 23% of U.S. adults. This figure, published November 8 in the journal Med, is substantially higher than the 7% prevalence rate suggested by earlier studies.
Researchers at Mass General Brigham in Boston developed an artificial intelligence tool capable of sifting through extensive electronic health records to identify the often subtle and varied symptoms associated with long COVID—a condition characterized by persistent health problems following a COVID-19 infection.
"Questions about the true burden of long COVID—questions that have thus far remained elusive—now seem more within reach," said senior researcher Hossein Estiri, head of AI research at Mass General Brigham.
Advanced AI Detection of Long COVID Symptoms
The AI tool specifically searches for symptoms that cannot be explained by a person's existing medical history, have persisted for two months or longer, and occur following a COVID infection. This approach allows for more accurate identification of long COVID cases by distinguishing them from symptoms related to pre-existing conditions.
"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," Estiri explained.
Long COVID encompasses a wide range of symptoms affecting multiple body systems, including debilitating fatigue, chronic cough, cardiovascular problems, and cognitive difficulties often described as "brain fog." These symptoms typically develop weeks or months after the initial COVID-19 infection has resolved.
Lead researcher Dr. Alaleh Azhir, an internal medicine resident at Brigham and Women's Hospital, highlighted the tool's potential impact: "Physicians are often faced with having to wade through a tangled web of symptoms and medical histories, unsure of which threads to pull, while balancing busy caseloads. Having a tool powered by AI that can methodically do it for them could be a game-changer."
Significant Impact on Daily Functioning
The burden of long COVID extends beyond its prevalence. According to a December 2024 report from the U.S. Centers for Disease Control and Prevention (CDC), approximately one in five adults with long COVID—or about 20% of those affected—experience symptoms so debilitating that they significantly interfere with daily activities.
These individuals report substantial limitations in everyday tasks such as walking, exercise, shopping, and housework due to their persistent symptoms. The CDC researchers, led by Nicole Ford of the National Center for Immunization and Respiratory Diseases, analyzed 2023 federal survey data to reach these conclusions.
"Frequently reported symptoms include fatigue that interferes with daily life, difficulty thinking or concentrating, cough and heart palpitations," the CDC team noted in their report.
Clinical Implications and Future Directions
The researchers plan to release their AI tool on an open-access platform, enabling healthcare systems and physicians worldwide to employ and test it in clinical settings. This could potentially transform how long COVID is diagnosed and managed across healthcare systems.
The findings underscore the need for comprehensive support systems for those affected by long COVID, including specialized healthcare resources and workplace accommodations to aid recovery.
Health experts emphasize that vaccination remains a crucial preventive measure against both acute COVID-19 infection and the subsequent development of long COVID. The CDC researchers stressed that "these findings support the ongoing importance of tools to reduce the risk for Long COVID, including vaccination."
As the healthcare community continues to grapple with the long-term consequences of the pandemic, this AI-assisted approach offers new hope for more accurate diagnosis and better management of a condition that appears to affect a substantial portion of the population who have contracted COVID-19.
