Study shows how flawed AI responses increase physician workloads
· News-MedicalThe result is that physicians may spend more time editing responses than it would've taken to write them, the researchers report.
The team reports that AI-generated answers frequently misalign with what clinicians would actually write. This includes automated responses that are too long, don't ask follow-up questions, and use irrelevant or inaccurate medical details.
Even little changes can add up over hundreds or thousands of messages, Preum says. "You don't want to integrate large language models into the workflow and just shift the bottleneck so that doctors are devoting their cognitive energy to playing AI janitor and fixing mistakes," Preum says. "But if we're not careful, that's a likely outcome."
The study shows that there are such things as "good" AI responses and provides a framework for implementing them into patient-physician portals, Preum says. These platforms are increasingly common among large health care systems and often customized, she says.
The researchers created a technique called TADPOLE-or Thematic Agentic Direct Preference Optimization for Learning Enhancement-that trains AI platforms using the hybrid model they constructed from physician- and AI-generated responses.
Tim Burdick, co-author and associate professor of community and family medicineWe're still nowhere near the point of having clinicians removed from the workflow."
"If you have to edit 75% of the message, you may be spending more time and energy on making changes than if you were to just write it from scratch," Burdick says. "I would guess we need to get to where the physician is editing less than 30% of the content before it has substantial benefit."
This means AI could be used to help "nudge" doctors to show more understanding and care for the patient's situation, or answer patient's questions more effectively so that patients feel more heard, Preum says. The team produced sample responses such as showing empathy by praising patients for following a treatment plan ("You've been doing a great job with your tapering.") or planning for changes in symptoms ("If you're feeling dizzy, please call triage.").
The researchers also find that 65% of all the portal messages they studied came from people over 55, with patients over 65 generating 24% of all messages. These figures suggest that patient portals in general should be designed to accommodate older people, Preum says.
"This is one of the first studies that uses real patient portal messages to establish a generative AI model. In that regard, it's innovative and shows us that this is not a simple task," Burdick says. "We're still nowhere near the point of having clinicians removed from the workflow."
Burdick, Preum, and Seegmiller worked with co-authors Joseph Gatto, who received his PhD from Dartmouth this year; Sarah Greer, a former physician at Dartmouth Health; and 2026 Dartmouth graduates Ganza Belise Isingizwe and Rohan Ray.
Source:
Journal references: