Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

How Doctors Can Use AI to Have Better Conversations With Patients

DZone's Guide to

How Doctors Can Use AI to Have Better Conversations With Patients

Can doctors use AI to better their conversations with patients?

· AI Zone ·
Free Resource

Bias comes in a variety of forms, all of them potentially damaging to the efficacy of your ML algorithm. Read how Alegion's Chief Data Scientist discusses the source of most headlines about AI failures here.

Rarely are conversations as important as those between a doctor and their patient. Being able to communicate often complex and distressing information in a clear and understandable manner is crucial. A recent paper from researchers at Trinity College Dublin, the University of Edinburgh and The Dartmouth Institute for Health Policy and Clinical Practice explores the possibility of using AI to improve the communication between doctor and patient.

"Many clinicians' communications skills aren't formerly 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," the authors say.Image title

The researchers suggest that AI can help to improve doctors communication skills by giving them detailed and personalized assessments of their communication abilities. What's more, it can do so at a much lower price than current methods. The authors believe the benefit can broadly be boiled down into three core areas:

  1. Analysis of words and phrases — by automating the analysis of words, the researchers believe that technology can help the doctor understand whether the patient understood them and whether they understood the patient. Eventually, they believe this analysis can be performed in real time, with prompts given to doctors on how they can improve the conversation and potentially even offer new treatments that the doctors themselves had not thought of.
  2. Turn-taking analysis — by looking at the amount of time each party spends talking, the researchers believe AI can help to assess the structure of the conversation. For instance, is the doctor allowing sufficient time for the patient to absorb the information and ask any questions they may have? The best conversations should be two-way discussions rather than a monologue. Eventually, they believe the technology can provide real-time analyses and intervene when things are going badly awry.
  3. Tone and style of interactions — this form of analysis is already common in the aviation sector, with pilots' communication assessed for its vocal pitch and energy. The authors believe that adopting a similar approach in healthcare could help detect high-risk situations that place the doctor under extreme stress. It could also provide insight into the patients' mental wellbeing.

While healthcare poses unique challenges in terms of the complexity of the language used, the researchers believe that AI can eventually prove to be invaluable in analyzing the effectiveness of communication between doctor and patient.

"Five years ago, the idea of using AI to analyze medical communication wouldn't have been on anyone's radar," they conclude. "As the technology advances, it will be interesting to see whether healthcare systems can employ it effectively and whether providers will be open to using it as a tool for improving their communication skills."

What are your thoughts? Leave them in the comments below.

Your machine learning project needs enormous amounts of training data to get to a production-ready confidence level. Get a checklist approach to assembling the combination of technology, workforce and project management skills you’ll need to prepare your own training data.

Topics:
ai in healthcare ,doctors using ai ,ai in conversation ,artificial intelligence

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}