An extension of the SPIRIT checklist that tells you what to put in a clinical trial protocol when the intervention includes AI.
| Full name | Standard Protocol Items, Recommendations for Interventional Trials, Artificial Intelligence extension |
| Website | https:// |
| Developed by | SPIRIT-AI and CONSORT-AI Working Group (2020) |
| Type | Reporting guideline: Checklist extension with explanatory paper |
| Lifecycle phase | Evaluation |
| FUTURE-AI | Traceability, General recommendations |
| For | Researchers, Healthcare professionals |
| Facilitation | No facilitator needed |
| Skills needed | Clinical trial methods |
| Cost | Free |
| Languages | English |
| Maturity | Established |
| Licence | CC-BY-4.0 |
What it is¶
SPIRIT-AI adds 15 AI-specific items to the SPIRIT checklist for trial protocols. They ask you to state, before the trial starts, what the AI intervention is and what skills people need to use it, the setting it will be built into, how its input and output data will be handled, how people will interact with it, and how you will analyse its errors. It is the protocol companion to CONSORT-AI: plan with SPIRIT-AI, then report with CONSORT-AI. Both were published in 2020 in several journals, including Nature Medicine and The BMJ.
In healthcare¶
Designed for interventional clinical trials of AI, so it fits directly when you write a protocol for a prospective trial of a clinical AI system.
Where to use it in The ELSA Way¶
Evaluation planning › Pre-specification: When your evaluation is a trial, this checklist turns pre-specification into a concrete protocol that covers the AI-specific choices as well as the usual trial design.
Reporting and transparency › International reporting guidelines: Use it for the protocol of a randomised trial of AI, the planning counterpart to CONSORT-AI in this table.
References¶
Cruz Rivera S, Liu X, Chan AW, Denniston AK, Calvert MJ; SPIRIT-AI and CONSORT-AI Working Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nature Medicine. 2020;26:1351-1363. Cruz Rivera et al. (2020)
Cruz Rivera S, Liu X, Chan AW, Denniston AK, Calvert MJ; SPIRIT-AI and CONSORT-AI Working Group. Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. BMJ. 2020;370:m3210. Cruz Rivera et al. (2020)
Related tools¶
CONSORT-AI: An extension of the CONSORT checklist that tells you what to report when a randomised trial tests an intervention with an AI component.
DECIDE-AI: A reporting checklist for small, early clinical studies of AI decision support, where you first test a tool with real users before a large trial.
- Cruz Rivera, S., Liu, X., Chan, A.-W., Denniston, A. K., Calvert, M. J., Darzi, A., Holmes, C., Yau, C., Moher, D., Ashrafian, H., Deeks, J. J., Ferrante di Ruffano, L., Faes, L., Keane, P. A., Vollmer, S. J., Lee, A. Y., Jonas, A., Esteva, A., Beam, A. L., … Rowley, S. (2020). Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. Nature Medicine, 26(9), 1351–1363. 10.1038/s41591-020-1037-7
- Cruz Rivera, S., Liu, X., Chan, A.-W., Denniston, A. K., & Calvert, M. J. (2020). Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension. BMJ, 370, m3210. 10.1136/bmj.m3210