Researchers at Mass General Brigham have developed a new artificial intelligence tool that may significantly improve our understanding of long COVID, a condition that plagues many who have recovered from the virus. Originally, diagnostic studies indicated that about 7 percent of individuals suffered from long COVID symptoms. Yet, the innovative AI diagnostic tool suggests the reality might be steeper, affecting almost 23 percent of the population, as reported by
The Harvard Gazette
.
The condition, characterized by a range of persistent symptoms like fatigue, chronic cough, and brain fog, has been elusive for healthcare providers due to its variable nature. By drawing from electronic health records of nearly 300,000 patients within the Mass General Brigham healthcare system, the AI instrument aims to streamline the diagnostic process by examining symptoms and health patterns to separate long COVID from similar ailment, an significant obstacle in current diagnostics.
“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,” Hossein Estiri, head of AI Research at the Center for AI and Biomedical Informatics of the Learning Healthcare System (CAIBILS) at MGB and an associate professor of medicine at Harvard Medical School, told
The Harvard Gazette
. “With this work, we may finally be able to see long COVID for what it truly is — and more importantly, how to treat it.”
The AI’s “precision phenotyping” method is a novel approach to serving as a sieve through patients’ records to flag long COVID symptoms that can’t be attributed to other causes, a complex task that health care providers grapple with amidst their demanding schedules. This method stands to become a game-changer, according to Alaleh Azhir, co-lead author of the study and an internal medicine resident at Brigham and Women’s Hospital. “Physicians are often faced with having to wade through tangled web of symptoms and medical histories, unsure of which threads to pull, while balancing busy caseloads,” as per
The Harvard Gazette
.
Moreover, the AI tool might adequately address inherent biases present in the current diagnostic process, by adopting a patient-centric approach. Researchers observed that current long COVID diagnoses that rely on ICD-10 codes often skew toward those with easier access to healthcare. By mirroring the demographic makeup of Massachusetts more closely, the AI tool offers a less biased and slightly more accurate picture at approximately 3 percent better than the ICD-10 codes.
However, the tool is not without limitations. Incomplete health record data and declines in COVID-19 testing complicate the identification process, but the researchers see this as a stepping stone for further development. Future studies look to explore the tool’s effectiveness in specific patient cohorts and make the AI algorithm available on open access for wider use, Estiri elaborated.
This breakthrough has potential implications beyond merely diagnosing long COVID; it may serve as a foundation for research into the genetic and biochemical underpinnings of the condition’s subtypes. “Questions about the true burden of long COVID — questions that have thus far remained elusive — now seem more within reach,” Estiri said, signaling a hopeful direction in ongoing efforts to combat the aftermath of the COVID-19 pandemic, as reported by
The Harvard Gazette
.
Note: Thank you for visiting our website! We strive to keep you informed with the latest updates based on expected timelines, although please note that we are not affiliated with any official bodies. Our team is committed to ensuring accuracy and transparency in our reporting, verifying all information before publication. We aim to bring you reliable news, and if you have any questions or concerns about our content, feel free to reach out to us via email. We appreciate your trust and support!
Leave a Reply