Mass General Brigham: Bringing AI to the Long COVID Battle

When COVID-19 hit the world five years ago, it transformed global healthcare systems.

Not only did it necessitate a radical new way of operating in the medical sphere, but it also brought about a illness who's after effects would be not widely know.

The World Health Organization estimates that up to 20% of individuals infected by SARS-CoV-2 may experience symptoms for weeks or even months after their initial recovery.

While the immediate symptoms of COVID-19 have become familiar, long COVID, a condition where symptoms persist well beyond the acute infection phase, remains elusive in diagnosis and treatment.

This has been leaving suffers feeling hopeless. However, amid this complex diagnostic landscape, researchers at Mass General Brigham in Boston are pioneering an AI tool specifically designed to detect long COVID symptoms.

AI analysis

Already, AI has been used to great effect in the world's fight against COVID, and now, the solutions are being applied in the aftermath.

This tool analyses electronic health records (EHRs), a promising step towards better understanding and identifying long COVID.

The AI distinguishes symptoms that cannot be explained by prior medical history and links them to post-COVID conditions, offering an advanced diagnostic approach that is both precise and scalable.

"Questions about the true burden of long COVID, questions that have thus far remained elusive, now seem more within reach," says Hossein Estiri, Head of AI Research at Mass General Brigham.

"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.”

This innovative AI examines patient symptoms that arise post-COVID and rules out those likely caused by existing conditions like heart disease or asthma.

By streamlining this analysis, the AI removes much of the diagnostic uncertainty, allowing clinicians to focus their efforts on patients who likely have long COVID, rather than those with unrelated medical issues.

The implications are substantial; the technology holds promise not only for diagnosing long COVID more accurately but also for potentially uncovering diagnostic strategies that could apply to other complex, multi-symptom conditions.

Lead Researcher Dr Alaleh Azhir, an internal medicine resident at Brigham and Women’s, further underscores the tool’s importance in the clinical environment.

"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," she explains. "Having a tool powered by AI that can methodically do it for them could be a game-changer."

Mass General Brigham's goal is to release this AI tool for broader use, allowing healthcare systems worldwide to integrate it into their diagnostic frameworks.

This move could enable a larger dataset, enhancing the AI's diagnostic capabilities and facilitating global collaboration on long COVID research.

A new path for diagnostics

While this AI innovation advances the fight against long COVID, it also raises broader questions about AI’s evolving role in healthcare.

Although being implemented across sectors, healthcare is one of the main areas due to its ability to cut physician's times doing associated admin or reaching a diagnosis. 

Thus if adopted widely, such a tool may change how the healthcare industry approaches other chronic conditions that emerge from infectious diseases, supporting a more tailored and data-driven approach to patient care.

Amid the ongoing challenges posed by COVID-19, this AI tool offers a beacon of hope. By transforming complex, scattered patient data into meaningful diagnostic insights, it illustrates AI’s potential to bridge gaps in human-led diagnostics and improve healthcare outcomes for patients suffering from long COVID and other post-viral conditions.

******

Make sure you check out the latest edition of AI Magazine and also sign up to our global conference series - Tech & AI LIVE 2024

******

AI Magazine is a BizClik brand ​​​​​​​