Table 2

Additional items proposed for studies relating to AI intervention clinical protocols within the SPIRIT-AI statement (in addition to the SPIRIT 2013 statement)

SectionItem noSPIRIT 2013 itemAmendmentSPIRIT-AI item
Administrative information
Title1Descriptive title identifying the study design, population, interventions and if applicable, trial acronymElaborationIndicate that the intervention involves artificial intelligence/machine learning and specify the type of model.
ElaborationSpecify the intended use of the AI intervention.
Introduction
Background and rationale6aDescription of research question and justification for undertaking the trial, including summary of relevant studies (published and unpublished) examining benefits and harms for each interventionExtensionExplain the intended use of the AI intervention in the context of the clinical pathway, including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).
ExtensionDescribe any pre-existing evidence for the AI intervention.
Methods: Participants, interventions and outcomes
Study Setting9Description of study settings (eg, community clinic, academic hospital) and list of countries where data will be collected. Reference to where list of study sites can be obtainedExtensionDescribe the onsite and offsite requirements needed to integrate the AI intervention into the trial setting.
Eligibility criteria10Inclusion and exclusion criteria for participants. If applicable, eligibility criteria for study centres and individuals who will perform the interventions (eg, surgeons, psychotherapists)ElaborationState the inclusion and exclusion criteria at the level of participants.
ExtensionState the inclusion and exclusion criteria at the level of the input data.
Interventions11aInterventions for each group with sufficient detail to allow replication, including how and when they will be administeredExtensionState which version of the AI algorithm will be used.
ExtensionSpecify the procedure for acquiring and selecting the input data for the AI intervention.
ExtensionSpecify the procedure for assessing and handling poor quality or unavailable input data.
ExtensionSpecify whether there is human-AI interaction in the handling of the input data, and what level of expertise is required for users.
ExtensionSpecify the output of the AI intervention.
ExtensionExplain the procedure for how the AI intervention’s output will contribute to decision making or other elements of clinical practice.
Methods: Monitoring
Harms22Plans for collecting, assessing, reporting and managing solicited and spontaneously reported adverse events and other unintended effects of trial interventions or trial conductExtensionSpecify any plans to identify and analyse performance errors. If there are no plans for this, justify why not.
Access to data29Statement of who will have access to the final trial dataset and disclosure of contractual agreements that limit such access for investigatorsExtensionState whether and how the AI intervention and/or its code can be accessed, including any restrictions to access or reuse.
  • Table adapted from Cruz Rivera et al.21–23 Items within the SPIRIT 2013 statement that have not changed for the SPIRIT-AI statement have been omitted.

  • AI, artificial intelligence; SPIRIT, Standard Protocol Items: Recommendations for Interventional Trials.