An Artificial Intelligence–Enabled Cardiopulmonary Resuscitation Instructor

Can contemporary artificial intelligence (AI) models provide guideline-concordant cardiopulmonary resuscitation (CPR) instruction?In this cross-sectional study of 6 widely available AI models, the models met most guideline-based criteria for CPR instruction in simulated out-of-hospital cardiac arrest scenarios, informing the development of a purpose-built AI-enabled CPR instructor agent. In head-to-head comparisons using 911 calls, this agent demonstrated higher adherence to guideline-based CPR instruction than human dispatchers.In this early proof-of-concept study, AI-enabled CPR instruction offered a potentially more accurate and scalable method to standardize early resuscitation instruction through further development, evaluation, and general population implementation.

Corresponding Author: John W. Ayers, PhD, MA, 9500 Gilman Dr, La Jolla, CA 92093 (ayers.john.w@gmail.com).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.