AI tools could significantly reduce the amount of time physicians spend documenting patient visits, addressing a key factor contributing to burnout, according to research led by the University of Toronto's LaShawn Murray.
The study, published in JAMIA Open , assessed the impact of AI scribes - digital tools that can record audio and produce structured, regulatory-compliant clinical notes - in simulations with nine primary-care physicians, each of whom conducted four simulated patient encounters with and without AI assistance.
AI scribes were found to account for a 69.1 per cent reduction in time required to document notes for patients' medical charts.
"We know health-care workers are experiencing burnout, which is associated with compromised patient safety and increased potential for errors, and can contribute to physician turnover," says Murray, a PhD student in the department of mechanical and industrial engineering in the Faculty of Applied Science & Engineering. "We also know that administrative tasks contribute to said burnout, so we want to find ways to reduce that strain."
The study, whose co-authors include Enid Montague, a professor of industrial engineering at U of T, and Onil Bhattacharyya, senior scientist at Women's College Hospital and associate professor in the department of family and community medicine in U of T's Temerty Faculty of Medicine, is part of a multi-phase collaboration between U of T's Wellness and Health Enhancement Engineering Lab and the Centre for Digital Health Evaluation at the Women's College Hospital Institute for Health System Solutions and Virtual Care. The team's previous research compared the usability and performance of six AI scribe products, three of which were used in the latest study.
Physicians who weren't using the tools were found to spend more than a third of each simulated patient encounter on note-taking; Murray says this suggests AI scribes could be useful in tackling documentation inaccuracies and delays.
"That would also create a reduction in cognitive labour with physicians having to remember what happened during appointments that occurred days prior," she says.
Researchers also observed an unexpected shift in workflow when AI scribes were used. While the tools reduced the need for real-time documentation, they also highlighted the usefulness of note-taking beyond record-keeping. "The most interesting finding for me was seeing how physically creating the charts throughout the appointment prompted thinking and more clinical decision-making questions from the doctors," says Murray.
Instead of charting throughout the visit, physicians using AI scribes typically reviewed and edited the AI-generated notes afterward. Some supplemented the technology with scratch notes during appointments, reducing the need to switch back and forth between the patient and the computer.
Murray notes many existing studies on the use of AI tools in health care emerged from U.S. hospital systems, which operate in a different context - and different set of privacy regulations - than their Canadian and Ontario counterparts.
"For us, it was really about focusing on the Canadian context, and even more specifically, within Ontario… there was a gap in the literature looking at how AI impacts primary care delivery and what that means for Canadian healthcare," says Murray.
Murray, who has been researching AI scribes since 2023, says the tools have evolved to develop more customizable features and better integration into existing platforms. But she says expectations about what the tools can accomplish have also become more realistic.
"When the technology was new, the conversation was very much that this would solve all our problems," says Murray. "Now that's shifted to, 'hey, maybe this is just one piece of the overall documentation burden that we're seeing,' because charts are not the only administrative burden facing physicians.
"We're also thinking about things like referrals, prescription orders, billing and regulatory expectations that are contributing to administrative work."
Given that the study relied on simulated patient encounters, Murray says more research will be needed to understand how AI scribes perform in everyday clinical practice.
As the technology becomes more widely adopted, Murray says researchers will also need to examine how receptive different patients are to the use of AI tools in the course of their care.
"Are they appreciative of the differences in communication? Are there hesitancies in terms of being recorded and who has access to these recordings?" says Murray. "I wonder about the impact for different patient populations as well. What happens when physicians who are almost always using AI scribes suddenly have one patient that doesn't consent to it being used in their care?
"This research has opened a lot more discussions and possibilities to consider."
