The CONSORT-AI extension is a set of recommendations for clinical trial reports evaluating interventions with an AI component. The checklist includes 14 new items, which were considered sufficiently important for AI interventions, that should be routinely reported in addition to the core CONSORT 2010 items. CONSORT-AI recommends that investigators provide a clear description of the AI intervention, including instructions and skills required for use, handling of the input/output data of the AI algorithm, the human-AI interaction and results of any error cases analyses.
As well as the checklist items, a number of illustrative examples are provided in the publication of CONSORT-AI, to assist users in understanding and applying the principles of the reporting items.
We strongly recommend users read the explanation text associated with each item, which will help to contextualise the items.
When referring to the CONSORT-AI guidelines, please cite one of the following articles: