Article Text

other Versions

Download PDFPDF

Can artificial intelligence make clinical decisions in regional anesthesia? An infographic
Free
  1. Nathan C Hurley1 and
  2. Eric S Schwenk2
  1. 1Anesthesiology, University of Wisconsin-Madison, Madison, Wisconsin, USA
  2. 2Anesthesiology and Perioperative Medicine, Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, Pennsylvania, USA
  1. Correspondence to Dr Eric S Schwenk, Anesthesiology and Perioperative Medicine, Sidney Kimmel Medical College at Thomas Jefferson University, Philadelphia, PA 19107, USA; Eric.Schwenk{at}jefferson.edu

Statistics from Altmetric.com

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Summary

In this study, Hurley et al1 examined whether the use of GPT-3 artificial intelligence could improve the ability of clinicians to apply the ASRA Pain Medicine anticoagulation guidelines to hypothetical patients. The baseline model without context produced an area under the receiver operating characteristic curve with a value of 0.55 (95% CI 0.50 to 0.61), which was only slightly above chance, but the addition of context improved the model’s area under the curve to 0.70 (95% CI 0.64 to 0.77). The authors concluded that artificial intelligence has the potential to aid clinicians with decision-making, but relies on accurate and relevant prompts.

Ethics statements

Patient consent for publication

Ethics approval

Not applicable.

Acknowledgments

We would like to acknowledge Jim Snively, artist, from Pittsburgh, Pennsylvania, USA, for the creation of this infographic.

Reference

Footnotes

  • Twitter @ESchwenkMD

  • Contributors Both authors contributed equally.

  • Funding The authors have not declared a specific grant for this research from any funding agency in the public, commercial or not-for-profit sectors.

  • Competing interests None declared.

  • Provenance and peer review Commissioned; internally peer reviewed.

Linked Articles