Artificial intelligence can be used to improve medical communications by giving information about patients' health, detecting high-risk situations when providers are under stress and preventing unneeded testing, researchers report in the BMJ.
The researchers, from The Dartmouth Institute for Health Policy and Clinical Practice in Lebanon, N.H., Trinity College Dublin in Ireland and the University of Edinburgh in Scotland, explored AI's potential to improve patient-provider communication.
"Many clinicians' communications skills aren't formally assessed — either during school or in early practice. At the same time, there is a lot of evidence that clinicians often struggle when communicating with their patients. It's hard to improve on something when you're not being given any feedback and don't know how you're doing," said senior author Glyn Elwyn, MD, PhD.
When used with the digital recordings of medical visits, AI can revolutionize communication in medicine by giving clinicians personalized evaluations of their communication skills, the researchers said.
They highlighted three key ways AI can improve medical communications:
1. Analysis of words and phrases. Automated analysis of words and phrases could give feedback on whether patients and providers understood each other, how aligned they were in their manner of expression and evaluate whether providers are taking appropriate histories.
2. Turn-taking analysis. This analysis looks at how much time patients and providers spend speaking and if the provider pauses to allow the patient to voice concerns or ask questions. Turn-taking analysis could provide important insights into dialogue patterns and eventually "intervene to prevent knee-jerk decisions to order invasive investigations," the researchers said.
3. Tone and style in interactions. Examining the tone and style in patient-provider communication could help detect when clinicians are under stress or subjected to workloads that might affect how well they communicate. Voice pattern analysis also could provide information about patients' physical and mental health.