AI scribes save doctors’ time and may ease administrative burden – study

AI scribes cut doctors’ documentation time by 69.1 per cent during simulated primary care appointments, a study of nine physicians found.

The digital tools can record audio and use it to generate structured, regulatory-compliant clinical notes for patients’ medical charts.

The research, led by University of Toronto PhD student LaShawn Murray, involved nine physicians completing simulated patient encounters with and without AI scribes.

Using video recordings of each appointment, researchers analysed how physicians spent their time and found they spent significantly less time documenting when the technology was used.

Murray said: “We know healthcare workers are experiencing burnout, which is associated with compromised patient safety and increased potential for errors, and can contribute to physician turnover.

“We also know that administrative tasks contribute to said burnout, so we want to find ways to reduce that strain.”

The study was co-authored with University of Toronto professor Enid Montague and Dr Onil Bhattacharyya of Women’s College Hospital.

It is part of a multi-phase project between the University of Toronto’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.

Previous research by the team compared six AI scribe products, with the three performing tools used in the subsequent study.

Without AI scribes, physicians spent more than one-third of each simulated patient encounter taking notes.

Murray hopes AI scribes could also lead to more timely documentation.

“Documentation often gets delayed because there’s just so much to do and the days are so busy; this can make it less accurate,” she said.

“I hope with this technology we see a reduction in things like charting being done after hours or days later. That would also create a reduction in cognitive labour with physicians having to remember what happened during appointments that occurred days prior.”

Researchers also observed changes in how some physicians kept track of their thoughts during appointments when AI scribes were used.

Some doctors began using scratch pads to keep track of questions and thoughts, highlighting the role note taking can play in clinical decision-making.

Murray said: “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.

“When the scribes were in use, we saw the adoption of scratch pads for note taking to help physicians remember to ask follow-up questions.”

Instead of switching between patients and typing on a computer throughout appointments, physicians tended to review and edit AI-generated documentation afterwards. This resulted in fewer interruptions during the simulated encounters.

One of the project’s goals is to generate Ontario-specific research on AI in healthcare, as physicians there work under different privacy regulations from their US counterparts.

“When the studies were first coming out, we were seeing them come from these large U.S.-based hospital systems,” Murray said.

“So for us, it was really about focusing on the Canadian context and, even more specifically, within Ontario. It’s not to say that we were the only ones in the space, but there was a gap in the literature looking at how AI impacts primary care delivery and what that means for Canadian healthcare.”

Murray, who has been studying AI scribes since 2023, said the technology has gained more customisable features and better integration with existing platforms, while expectations around its potential have also changed as adoption has grown.

“When the technology was new, the conversation was very much that this would solve all our problems,” she said.

“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.”

Further studies are needed to understand how AI scribes perform in everyday clinical practice because the study used simulated patient encounters.

Murray said questions also remain about how receptive patients will be to AI scribes during 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,” she said.

“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.”