Perioperative medicine & outcomes
Artificial intelligence for predicting perioperative anaesthetic complications and supporting clinical decision-making: a scoping review
Authors' conclusion
Artificial intelligence has substantial potential to support prediction of perioperative anaesthetic complications. However, clinical implementation is limited by methodological weaknesses, including predominantly retrospective designs, limited external validation, and scarce assessment of real-world impact.
Study context
- Population
- Adult surgical patients; studies applying machine learning, deep learning or hybrid models to predict perioperative anaesthetic complications (PubMed, Scopus, Web of Science, 2015–2025)51 studies
- Outcome
- Artificial intelligence (AI) models for predicting perioperative anaesthetic complications
Methodological detailsJoanna Briggs Institute methodology, PRISMA-ScR reporting, conceptual mapping and thematic analysis
- Joanna Briggs Institute methodology
- PRISMA-ScR reporting
- Conceptual mapping and thematic analysis
Main finding
As reported in the abstract
Studies included
51
Original publication
Artificial intelligence for predicting perioperative anaesthetic complications and supporting clinical decision-making: a scoping review. J Clin Monit Comput. Published 20 August 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →