Sign in Subscribe
Machine learning

Artificial Intelligence Enhances Perioperative Medicine Education

Strategic Insights

— 1 min read

Research published in the Journal of Perioperative Practice demonstrates the feasibility of using large language models, such as ChatGPT, to support the delivery of case-based perioperative medicine content. The study, conducted by the University of Adelaide, indicates that artificial intelligence can provide accurate information and assist in education, with 99.3% of questions answered appropriately.

Key Takeaways:

  • The study used a custom large language model platform to assist in case-based education in perioperative clinical cases, with five cases developed and uploaded to the platform.
  • Anaesthetic trainees engaged with the artificial intelligence, asking questions to obtain information regarding history, examination, and investigations.
  • The artificial intelligence responded appropriately to nearly all questions, with no hallucinations observed and a proportion of questions answered appropriately at 99.3% (543/547).
  • The study concluded that the large language model appears capable of supporting the delivery of case-based perioperative medicine content with a high degree of accuracy.
  • The research highlights concerns regarding the accuracy of large language models, particularly the risk of hallucinations and generating factually incorrect outputs.
  • The study was conducted by a team of researchers from the University of Adelaide, including Nicholas Fitzgerald, Timothy Trewren, and others, and has been peer-reviewed.

Statistics:

  • 99.3% of questions asked to the artificial intelligence were answered appropriately.
  • 543 out of 547 questions were answered correctly.
  • The artificial intelligence responded with no hallucinations observed.
  • 4 instances of inappropriate responses were found, with the large language model declining to provide information in the case description rather than hallucinate.

Sources:

  • Artificial intelligence in perioperative medicine education: A feasibility test of case-based learning. Journal of Perioperative Practice, 2025:17504589251346634.
  • NewsRx. University of Adelaide Reports Findings in Artificial Intelligence (Artificial intelligence in perioperative medicine education: A feasibility test of case-based learning). Education Letter. June 25, 2025; p 551.

Read more