Toronto scientist gets big award to study artificial intelligence in health care

Rahul Krishnan, an assistant professor at the University of Toronto, receives a research award from Amazon (Supplied).

Amazon just awarded a Toronto-based researcher $85,000 to study the consequences of implementing artificial intelligence in health care.

“I think there needs to be a conversation about how to mitigate the potential negative harms that [these tools] may come with,” Rahul Krishnan, an assistant professor exploring computational medicine at the University of Toronto, told CTV News Toronto.

Amazon Research Awards were handed to 79 academic researchers last week to study topics from sustainability to automated reasoning.

The 33-year-old Toronto recipient began taking an interest in computational medicine years ago when he was studying electrical and computer engineering at the University of Toronto, beginning in 2008.

“This is well before machine learning was in the public eye in any way,” Krishnan said. “By the time I completed my PhD (at the Massachusetts Institute of Technology), machine learning exploded.”

Krishnan's award comes at a time when artificial intelligence has captured the public's attention, with programs such as ChatGPT and MidJourney made accessible to anyone with an internet connection.

Just last week, Microsoft announced plans to integrate GPT-3 language models into Epic, an electronic health record (EHR) software used in North American hospitals.

“There are obviously consequences with this decision and so what we would like to do is study some of these consequences,” Krishnan said.

“I think it’s a really important question to study because medicine is a field that is not static, what constitutes the standard of care is something that is dynamic and changes over time.”

‘PLAYING CATCH-UP’

As popularity spikes, questions on the future of artificial intelligence have surfaced, and many are asking how we will regulate the tools.

“I think our regulation, particularly in the context of health care, has been playing catch-up over the years,” Krishnan said.

“There is really a need for regulation to catch-up so we’re not caught flat footed if these tools do have unintended consequences when deployed in health care.”

One such danger could include “internal biases, baked into the model,” that have the potential to harm patients by perpetuating prejudiced decision-making.

Another research topic he’s pursuing investigates how these biases manifest in machine learning models, in an effort to create tools to help doctors make decisions faster or in a more informed manner.

As an example, he pointed to disparities that exist in the kidney transplant waitlist. Black people are four times more likely to develop kidney failure than white people in the United States, yet they are less likely to receive a lifesaving transplant, according to 2020 findings in the National Library of Medicine (NLM).

“Our findings support previous work examining the effects of discrimination and medical mistrust on referral,” the research states.

One of the challenges in Canada is a lack of sufficient data available on subgroup identities, Krishnan said. “I think it’s naive to say there is no disparity. I believe those disparities do exist.”

His goal with this research is to identify disparities existing in medical data, work to improve outcomes for those patients, and then assess how to apply the methods they adapt to other discriminated groups.

Across the board, Krishnan said he aims to understand the strength of tools in artificial intelligence, alongside their limitations.

“I think that there is both an enormous amount of opportunity here and an enormous amount of care that needs to be given.”