Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI Extension
CONSORT-AI connects transparent trial reporting with the details that make an AI intervention reproducible.
What the paper explores
This peer-reviewed reporting-methodology paper introduces the CONSORT-AI extension for clinical trials involving AI. Developed through a stakeholder consensus process, it asks authors to describe the intervention, required user skills, handling of inputs and outputs, human-AI interaction and analysis of errors.
How to interpret the evidence
A reporting checklist is not a regulatory approval standard, nor does completion alone demonstrate clinical benefit or remove bias from a study.
Questions for MedTech teams
Use reporting considerations during study planning so that relevant information is captured prospectively. This paper concerns reporting methodology, not the performance of a particular medical product.
Sources & further reading
Read original paperDOI: 10.1136/bmj.m3164
Bibliographic record and abstract on PubMedThis is a short editorial reading note on external research. The original research is attributed to its authors and does not represent an HMC study, product validation or regulatory determination.
