The next best teacher: Using large language models to provide technical advice to trainees in regional Anaesthesia
Authors' conclusion
LLM have a role to play in intraprocedural queries, however, should only be used as an adjunct to the decision-making process and need to be critically appraised.
Study context
- Population
- LLM advice on seven regional nerve blocks, appraised by ten anaesthetists7 nerve blocks · 10 appraisers
- Exposure
- ChatGPT vs Bing Chat/Copilot vs Gemini
- Outcome
- Appraisal score for safety, accuracy and appropriateness for trainees
Methodological detailssingle-centre, comparative
- Single-centre
- Comparative
Main finding
As reported in the abstract
| Group | Value | Cronbach Alpha |
|---|---|---|
| ChatGPT | mean 3.71 out of 5 | 0.98 (95% CI 0.89-0.99) |
ChatGPT
Valuemean 3.71 out of 5
Cronbach Alpha0.98 (95% CI 0.89-0.99)
Observational data: associations, not effects.
Further findings
- Reference accuracy (references that existed) — ChatGPT
- 25%
Readability (Flesch Reading Ease Score and Flesch-Kincaid Grade level)
- ChatGPT advice intended to be read by a University Graduate
Reference accuracy (references that existed)
- All references supplied by Bing and Gemini were real
Original publication
The next best teacher: Using large language models to provide technical advice to trainees in regional Anaesthesia. J Clin Anesth. Published 6 April 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →