SPIRIT-AI & CONSORT-AI

Improving The Quality Of Evidence For AI Health Interventions



Reporting Guidelines for Clinical Trial Protocols for Interventions Involving Artificial Intelligence

The SPIRIT-AI Extension

Reporting Guidelines for Clinical Trial Reports for Interventions Involving Artificial Intelligence

The CONSORT-AI Extension

The SPIRIT-AI and CONSORT-AI initiative is an international collaborative effort to improve the transparency and completeness of reporting of clinical trials evaluating interventions involving artificial intelligence (AI). SPIRIT-AI stands for Standard Protocol Items: Recommendations for Interventional Trials - Artificial Intelligence and CONSORT-AI stands for (Consolidated Standards of Reporting Trials - Artificial Intelligence).

The SPIRIT-AI and CONSORT-AI statements are extensions to the SPIRIT 2013 and CONSORT 2010 reporting guidelines for clinical trial protocols and clinical trial reports, respectively. The two extensions build upon existing recommendations to address considerations specific to AI health interventions.

They are intended to help promote transparency and completeness for clinical trial protocols for AI interventions and assist editors and peer-reviewers, as well as the general readership, to understand, interpret and critically appraise clinical trial protocols and reports.

The SPIRIT-AI and CONSORT-AI initiative was announced in Nature Medicine in October 2019. The two statements were developed simultaneously through international multi-stakeholder consensus and published in Nature Medicine, the British Medical Journal and the Lancet Digital Health in September 2020. The guidelines are supported by, and developed according to guidelines set out by, the EQUATOR (Enhancing the QUAlity and Transparency Of health Research) network. The use of the guidelines are endorsed by key medical journals for the reporting of clinical trials for AI interventions.



Funding and Support

The development of the SPIRIT-AI and CONSORT-AI guidelines was funded by the Wellcome Trust, Research England (part of UK Research and Innovation), Health Data Research UK and The Alan Turing Institute; and sponsored by the University of Birmingham and the Birmingham Health Partners Centre for Regulatory Science and Innovation, Birmingham, UK.