More than 1 in 5 Americans likely suffer from long COVID, a new AI-assisted review has found.
The analysis suggests that nearly 23% of U.S. adults experience the symptoms of long COVID, according to results published Nov. 8 in the journal Med.
That’s much higher than the 7% prevalence of long COVID that’s been suggested by other studies, researchers said.
“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 in Boston.
For the study, researchers developed an AI tool that can sift through mounds of electronic health records looking for the frequently subtle symptoms related to long COVID.
These symptoms can occur in a wide range of body systems, and include fatigue, chronic cough, heart problems and “brain fog.” They typically develop weeks or months after a person shakes off their initial COVID-19 infection.
“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 said in a Mass General news release.
The AI specifically looks for symptoms that can’t be explained by a person’s medical history, have persisted for two months or longer and occur following a COVID infection, researchers said.
For example, the AI can detect if shortness of breath might be explained by pre-existing heart failure or asthma, rather than 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 lead researcher Dr. Alaleh Azhir, an internal medicine resident at Brigham and Women’s.
Based on these parameters, the AI estimated that nearly 23% of Americans likely have long COVID, a figure that researchers argue aligns more closely with national trends.
The researchers plan to release the AI publicly on open access, so doctors and health care systems can employ and test it.
More information:
Precision Phenotyping for Curating Research Cohorts of Patients with Unexplained Post-Acute Sequelae of COVID-19, Med (2024). DOI: 10.1016/j.medj.2024.10.009. www.cell.com/med/fulltext/S2666-6340(24)00407-0
Copyright © 2024 HealthDay. All rights reserved.
Citation:
1 in 5 people could have long COVID (2024, November 10)
retrieved 10 November 2024
from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.
More than 1 in 5 Americans likely suffer from long COVID, a new AI-assisted review has found.
The analysis suggests that nearly 23% of U.S. adults experience the symptoms of long COVID, according to results published Nov. 8 in the journal Med.
That’s much higher than the 7% prevalence of long COVID that’s been suggested by other studies, researchers said.
“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 in Boston.
For the study, researchers developed an AI tool that can sift through mounds of electronic health records looking for the frequently subtle symptoms related to long COVID.
These symptoms can occur in a wide range of body systems, and include fatigue, chronic cough, heart problems and “brain fog.” They typically develop weeks or months after a person shakes off their initial COVID-19 infection.
“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 said in a Mass General news release.
The AI specifically looks for symptoms that can’t be explained by a person’s medical history, have persisted for two months or longer and occur following a COVID infection, researchers said.
For example, the AI can detect if shortness of breath might be explained by pre-existing heart failure or asthma, rather than 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 lead researcher Dr. Alaleh Azhir, an internal medicine resident at Brigham and Women’s.
Based on these parameters, the AI estimated that nearly 23% of Americans likely have long COVID, a figure that researchers argue aligns more closely with national trends.
The researchers plan to release the AI publicly on open access, so doctors and health care systems can employ and test it.
More information:
Precision Phenotyping for Curating Research Cohorts of Patients with Unexplained Post-Acute Sequelae of COVID-19, Med (2024). DOI: 10.1016/j.medj.2024.10.009. www.cell.com/med/fulltext/S2666-6340(24)00407-0
Copyright © 2024 HealthDay. All rights reserved.
Citation:
1 in 5 people could have long COVID (2024, November 10)
retrieved 10 November 2024
from
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.