Artificial city

Toronto Institute of Technology monitors long COVID with artificial intelligence and social media

TORONTO — A Toronto Institute of Technology is using artificial intelligence and social media to track and determine which long-running COVID symptoms are most prevalent.

TORONTO — A Toronto Institute of Technology is using artificial intelligence and social media to track and determine which long-running COVID symptoms are most prevalent.

The Vector Institute, an artificial intelligence organization based at the MaRS Technology Center in Toronto, has partnered with telecommunications company Telus Corp., consulting firm Deloitte and diagnostics and pharmaceuticals company Roche Canada to help healthcare professionals learn more about the symptoms that people with a long-lasting form of COVID experience.

They built an artificial intelligence framework that used machine learning to locate and process 460,000 Twitter posts from people with long-term COVID – defined by the Canadian government as people who show symptoms of COVID-19 for weeks or months after their initial recovery.

The executive analyzed the tweets to determine what the first-person accounts of long COVID are, then compiled the symptoms described. It found that fatigue, pain, brain fog, anxiety and headaches were the most common symptoms, and many patients with long-term COVID had multiple symptoms at once.

Replicating this research without the AI ​​would have taken enormous hours of staff and staff, who would have had to manually locate hundreds of thousands of posts or people on social media and siphon off those who did not have long accounts. COVID or first person and counting symptoms.

“AI is very good at taking large sets of large amounts of data to find patterns,” said Cameron Schuler, Vector’s chief marketing officer and vice president of industry innovation.

“It’s for things that are way too big for a human to actually hold in their brain.”

The framework speeds up the research process around a rapidly evolving virus still associated with so many unknowns.

So far, the long COVID is not well understood. There is no uniform way to diagnose it or a single treatment to alleviate or cure it. Information is key to giving patients better outcomes and ensuring hospitals are not overwhelmed in the years to come.

A May 2021 survey of 1,048 Canadians with long COVID, also known as post-COVID syndrome, revealed more than 100 symptoms or difficulties with daily activities.

About 80% of adults surveyed by Viral Neuro Exploration, COVID Long Haulers Support Group Canada and Neurological Health Charities Canada reported one or more symptoms between four and 12 weeks after being first infected.

Sixty percent reported one or more long-term symptoms. The symptoms were so severe that about 10% are unable to return to work long term.

Researchers and those behind the technology hope it will quickly contribute to the global fight against long COVID, but are already imagining ways to further advance the framework or apply it to other situations.

“This is a new kind of tool,” said Dr. Angela Cheung, senior physician-researcher at the University Health Network, who is leading two large studies on long COVID.

“I’m not aware of anyone else doing this, so I think it could really be very helpful in moving forward in health research.”

The researchers say preliminary uses of the framework show it can help uncover patterns related to symptom frequency, co-occurrence and distribution over time.

It could also be applied to other health events like emerging infections or rare diseases or the effects of booster shots on infection.

This report from The Canadian Press was first published on February 11, 2022.

Companies in this story: (TSX:T)

Tara Deschamps, The Canadian Press