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.
| Full name | Developmental and Exploratory Clinical Investigations of DEcision support systems driven by Artificial Intelligence |
| Website | https:// |
| Developed by | DECIDE-AI Expert Group (Baptiste Vasey, Peter McCulloch and colleagues) (2022) |
| Type | Reporting guideline: Checklist with explanatory paper |
| Lifecycle phase | Evaluation, Deployment |
| FUTURE-AI | Usability, Traceability, General recommendations |
| For | Researchers, Healthcare professionals, AI developers |
| Facilitation | No facilitator needed |
| Skills needed | Clinical research methods |
| Cost | Free |
| Languages | English |
| Maturity | Established |
| Licence | CC-BY-NC-4.0 (BMJ version); Nature Medicine version is not openly licensed |
What it is¶
DECIDE-AI covers the stage between building a model and running a large comparative trial: the first studies in which clinicians use the system with real patients. It has 17 AI-specific items and 10 generic ones, and asks you to report how the system was used in practice, how it fitted into the workflow, what human factors and usability issues came up, how safety was monitored and what changed in the tool during the study. It was agreed through an international consensus process and published in 2022 in Nature Medicine and The BMJ.
In healthcare¶
Written for clinical decision support systems, so it fits first-in-clinic pilots, feasibility studies and silent or shadow-mode evaluations that come before a randomised trial.
Where to use it in The ELSA Way¶
Clinical utility and safety › The clinical evaluation plan: If you cannot yet justify a full trial, the checklist helps you plan a smaller first clinical study that still collects the safety, usability and workflow evidence a later trial will need.
Reporting and transparency › International reporting guidelines: Use it to report early clinical evaluations: the first studies with real users, between model validation and a randomised trial.
References¶
Vasey B, Nagendran M, Campbell B, Clifton DA, Collins GS, Denaxas S, et al. Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nature Medicine. 2022;28:924-933. Vasey et al. (2022)
Vasey B, Nagendran M, Campbell B, Clifton DA, Collins GS, Denaxas S, et al. Reporting guideline for the early stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. BMJ. 2022;377:e070904. Vasey et al. (2022)
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.
SPIRIT-AI: An extension of the SPIRIT checklist that tells you what to put in a clinical trial protocol when the intervention includes AI.
System Usability Scale: A ten-item questionnaire that produces a single score from 0 to 100 for how usable people find a system.
- Vasey, B., Nagendran, M., Campbell, B., & others. (2022). Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nature Medicine, 28, 924–933. 10.1038/s41591-022-01772-9
- Vasey, B., Nagendran, M., Campbell, B., Clifton, D. A., Collins, G. S., Denaxas, S., Denniston, A. K., Faes, L., Geerts, B., Ibrahim, M., Liu, X., Mateen, B. A., Mathur, P., McCradden, M. D., Morgan, L., Ordish, J., Rogers, C., Saria, S., Ting, D. S. W., … McCulloch, P. (2022). Reporting guideline for the early stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. BMJ, 377, e070904. 10.1136/bmj-2022-070904