Using artificial intelligence for replies to patients could help reduce burnout amongst doctors facing a growing number of online messages.
A recent study has found that AI-generated non-emergency replies to patients, while failing to reduce doctor response times, can help to relieve to cognitive burden.
AI responses can help to break ‘writer’s block’ by supplying doctors with an “empathy-infused draft” as a guide which they can edit, rather than starting from scratch.
- Artificial intelligence detects type 2 diabetes earlier, researchers claim
- Patients prefer ChatGPT responses over doctors’ responses
- Study to detect type 2 diabetes from voice launches
They have been piloted by the University of California San Diego Health, and a recent study by the university’s School of Medicine was the first randomised evaluation of AI-drafted doctor messaging.
The study’s senior author, Christopher Longhurst, chief medical officer and chief digital officer at UC San Diego Health, said: “We are very interested in using AI to help solve health system challenges, including the increase in patient messages that are contributing to physician burnout.
“The evidence that the messages are longer suggests that that they are higher quality, and the data is clear that physicians appreciated the help, which lowered cognitive burden.”
The study found that the integration of AI responses into patient-physician digital interactions could support patient care by improving the quality of communications, efficiency and engagement.
By taking away some of a doctor’s workload, it could also free up their time so they can concentrate on the more complicated aspects of patient care, researchers say.
Lead author Ming Tai-Seale, professor of family medicine at UC San Diego School of Medicine, said: “This study shows that generative AI can be a collaborative tool.
“Our physicians receive about 200 messages a week. AI could help break ‘writer’s block’ by providing physicians an empathy-infused draft upon which to craft thoughtful responses to patients.”
- AI model flags up hypo symptoms to drivers with diabetes
- AI-powered eye exams improve screening rates among young people with diabetes
- AI support for paramedics could save lives
The study found that AI can help compose longer, empathetic replies, rather than shorter, more facts-based responses, helping patients to better understand and appreciate what is being said.
The responses include a line about how they have been crafted with help from AI.
Study co-author Marlene Millen, chief medical information officer for ambulatory care at UC San Diego Health, said: “AI doesn’t get tired, so even at the end of a long day, it still has the capacity to help draft an empathetic message while synthesising the request and relevant data into the response.
“So, while we were surprised by the study’s findings that AI messaging didn’t save doctors time, we see that it may help prevent burnout by providing a detailed draft as a starting point.”
The study has been published in JAMA Network Open.
