Artificial intelligence in radiology: 173 commercially available products and their scientific evidence
Question Evaluating advancements in peer-reviewed evidence for CE-certified radiological AI products is crucial to understand their clinical adoption and impact. Findings CE-certified AI products with peer-reviewed evidence increased from 36% in 2020 to 66% in 2023, but the proportion of higher-level evidence papers (~24%) remained unchanged. Clinical relevance The study highlights increased validation of radiological AI products but underscores a continued lack of evidence on their clinical and socio-economic impact, which may limit these tools' safe and effective implementation into clinical workflows.
Authors
- Olga Tryfonos (ORCID: https://orcid.org/0000-0002-5145-6812)
- Colin Jacobs (ORCID: https://orcid.org/0000-0003-1180-3805)
- Kicky G. van Leeuwen (ORCID: https://orcid.org/0000-0002-8902-5161)
- Ignas B. Houben (ORCID: https://orcid.org/0000-0001-8975-528X)
- Maarten de Rooij (ORCID: https://orcid.org/0000-0001-7257-7907)
- Noa J.C. Antonissen (ORCID: https://orcid.org/0000-0001-8702-3640)
Institutions
- Radboud University Nijmegen (NL)
- European University Cyprus (CY)
- Dutch Health Care Inspectorate (NL)
- Radboud University Medical Center (NL)
- Netherlands Heart Registration (NL)
- Radboud Institute for Molecular Life Sciences (NL)
- Isala (NL)
Publication Details
- Journal
- European Radiology
- Published
- 2025-07-24
- DOI
- https://doi.org/10.1007/s00330-025-11830-8
- Citations
- 14
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 9.16