PROBAST+AI| Study design(s) targeted by the tool | Prediction modelsprediction-models |
|---|---|
| Additional details on designs | Including models with AI |
| Tool area | Health |
| Link to the tool | Get the PROBAST+AI tool |
Details | |
| Website | https://www.probast.org/probast_ai |
| Primary publication | Moons K, Damen J, Kaul T, et al. PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods. BMJ. 2025;388:e082505. |
| DOI | 10.1136/bmj-2024-082505 |
| Guidance document | Get the PROBAST+AI guidance |
| Training | None known – please contact us if you are aware of any training that should be listed here |
| Language | English |
| Translations | None known – please contact us if you are aware of any translations that should be listed here |
| Record last updated | 23/01/2026 |
Related tools and Publications | |
| Previous versions | |
| Updated versions | None |
| Related tools | |
| Evaluations | None known |
| Other publications | None known |
Key Criteria | |
| Focuses on risk of bias, or makes a distinction between items that assess risk of bias and other aspects of study quality | Yes |
| Offers a method to reach either a domain specific or overall assessment of risk of bias | Yes |
| Tool developed for use across topic areas (i.e. not developed for specific clinical area such as physiotherapy or dentistry) | Yes |
| Avoids recommending use of summary numerical quality scores | Yes |
