AI tool shows three times as many long Covid cases than previously thought

More than one in five people have long Covid, according to a new AI-based study from Harvard Medical School.

Previously, diagnostic studies have estimated that about 7% of the population has long Covid. The new study, however, which uses an AI tool developed by Mass General Brigham health care system, has found that the rate is 22.8%.

The AI-based tool can sift through electronic health records to help clinicians identify cases of long Covid, a condition characterised by symptoms such as fatigue, chronic cough and brain fog after a Covid-19 infection.

The AI algorithm was developed by drawing anonymised patient data from the clinical records of nearly 300,000 patients across 14 hospitals and 20 community health centres in the Mass General Brigham system. The results, published in the journal Med, could identify more people who should be receiving care for long Covid

Hossein Estiri, head of AI Research at the Center for AI and Biomedical Informatics at Mass General Brigham, an associate professor at Harvard Medical School and senior author on the study, said: “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. With this work, we may finally be able to see long Covid for what it truly is — and more importantly, how to treat it.”

For the purposes of their study, Estiri and his colleagues defined long Covid as a diagnosis of exclusion that is infection-associated. That means the diagnosis could not be explained in the patient’s unique medical record but was associated with a Covid infection. The diagnosis needed to have persisted for two months or longer in a 12-month follow-up window.

Tracking symptoms over time

The method developed by Estiri and colleagues, called “precision phenotyping,” sifts through individual records to identify symptoms and conditions linked to Covid-19 to track symptoms over time in order to differentiate them from other illnesses. For example, the algorithm can detect if shortness of breath results from pre-existing conditions like heart failure or asthma rather than long Covid. Only when every other possibility was exhausted would the tool flag the patient as having long Covid.

“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,” said Alaleh Azhir, co-lead author and an internal medicine resident at Brigham and Women’s Hospital, which is part of the Mass General Brigham healthcare system.

The new tool’s diagnoses may also help alleviate biases built into current diagnostics for long Covid, the researchers said. They noted that diagnoses with the official ICD-10 diagnostic code for long Covid are more likely to be applied to those with easier access to health care.

The researchers said their tool is about 3% more accurate than the data ICD-10 codes capture, while being less biased. The study demonstrated that the people they identified as having long Covid reflect the broader demographic makeup of Massachusetts, unlike long Covid algorithms that rely on a single diagnostic code or individual clinical encounters.

“This broader scope ensures that marginalized communities, often sidelined in clinical studies, are no longer invisible,” said Estiri.

As well as opening the door to better clinical care, this work may lay the foundation for future research into the genetic and biochemical factors behind long Covid’s various subtypes. “Questions about the true burden of long Covid — questions that have thus far remained elusive — now seem more within reach,” said Estiri.