Table 3

Additional criteria to be included for studies relating to AI interventions within the CONSORT-AI statement (in addition to the CONSORT 2010 statement)

SectionItem noCONSORT 2010 itemAmendmentCONSORT-AI item
Title and abstract
Title and abstract1aIdentification as a randomised trial in the titleElaborationIndicate that the intervention involves artificial intelligence/machine learning in the title and/or abstract and specify the type of model.
1bStructured summary of trial design, methods, results and conclusionsElaborationState the intended use of the AI intervention within the trial in the title and/or abstract.
Background and objectives2aScientific background and explanation of rationaleExtensionExplain the intended use of the AI intervention in the context of the clinical pathway, including its purpose and its intended users (eg, healthcare professionals, patients, public).
Participants4aEligibility criteria for participantsElaborationState the inclusion and exclusion criteria at the level of participants.
ExtensionState the inclusion and exclusion criteria at the level of the input data.
4bSettings and locations where the data were collectedExtensionDescribe how the AI intervention was integrated into the trial setting, including any onsite or offsite requirements.
Interventions5The interventions for each group with sufficient details to allow replication, including how and when they were actually administeredExtensionState which version of the AI algorithm was used.
ExtensionDescribe how the input data were acquired and selected for the AI intervention.
ExtensionDescribe how poor quality or unavailable input data were assessed and handled
ExtensionSpecify whether there was human–AI interaction in the handling of the input data, and what level of expertise was required of users.
ExtensionSpecify the output of the AI intervention.
ExtensionExplain how the AI intervention’s outputs contributed to decision making or other elements of clinical practice.
Harms19ExtensionDescribe results of any analysis of performance errors and how errors were identified, where applicable. If no such analysis was planned or done, justify why not.
Funding25ExtensionState whether and how the AI intervention and/or its code can be accessed, including any restrictions to access or re-use.
  • Table adapted from Liu et al.17–19 Items within the CONSORT 2010 statement that have not been changed for the CONSORT-AI statement have been omitted.

  • AI, artificial intelligence; CONSORT, Consolidated Standards of Reporting Trials.