Artificial intelligence in radiology: 173 commercially available products and their scientific evidence
- PMID: 40707732
- DOI: 10.1007/s00330-025-11830-8
Artificial intelligence in radiology: 173 commercially available products and their scientific evidence
Abstract
Objectives: To assess changes in peer-reviewed evidence on commercially available radiological artificial intelligence (AI) products from 2020 to 2023, as a follow-up to a 2020 review of 100 products.
Materials and methods: A literature review was conducted, covering January 2015 to March 2023, focusing on CE-certified radiological AI products listed on www.healthairegister.com . Papers were categorised using the hierarchical model of efficacy: technical/diagnostic accuracy (levels 1-2), clinical decision-making and patient outcomes (levels 3-5), or socio-economic impact (level 6). Study features such as design, vendor independence, and multicentre/multinational data usage were also examined.
Results: By 2023, 173 CE-certified AI products from 90 vendors were identified, compared to 100 products in 2020. Products with peer-reviewed evidence increased from 36% to 66%, supported by 639 papers (up from 237). Diagnostic accuracy studies (level 2) remained predominant, though their share decreased from 65% to 57%. Studies addressing higher-efficacy levels (3-6) remained constant at 22% and 24%, with the number of products supported by such evidence increasing from 18% to 31%. Multicentre studies rose from 30% to 41% (p < 0.01). However, vendor-independent studies decreased (49% to 45%), as did multinational studies (15% to 11%) and prospective designs (19% to 16%), all with p > 0.05.
Conclusion: The increase in peer-reviewed evidence and higher levels of evidence per product indicate maturation in the radiological AI market. However, the continued focus on lower-efficacy studies and reductions in vendor independence, multinational data, and prospective designs highlight persistent challenges in establishing unbiased, real-world evidence.
Key points: 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.
Keywords: Artificial intelligence; Device approval; Evidence-based practice; Radiology.
© 2025. The Author(s).
Conflict of interest statement
Compliance with ethical standards. Guarantor: The scientific guarantor of this publication is Maarten de Rooij. Conflict of interest: The following authors of this manuscript declare relationships with the following companies: KvL is co-owner of Romion Health and Health AI Register and has received speaker fees from Siemens Healthineers and Bayer Pharmaceuticals. M.d.R. has an in-kind research agreement with Siemens Healthineers and has received speaker fees from Siemens Healthineers. C.J. receives research grants and royalties to the host institution from MeVis Medical Solutions, a public-private research grant with Philips Medical Systems, and a public-private research grant with Siemens Healthineers. C.J. received speaker fees from Canon Medical Systems and Johnson & Johnson. C.J. is a member of the Scientific Editorial Board of European Radiology (section: Imaging Informatics and Artificial Intelligence) and, as such, did not participate in the selection or review processes for this article. The other authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article. Statistics and biometry: Gerjon Hannink kindly provided statistical advice for this manuscript. Informed consent: No human subjects were involved in this study. Ethical approval: Institutional Review Board approval was not required because this study deals with public data and data provided by vendors. Study subjects or cohorts overlap: The collected data partially overlaps with the study by van Leeuwen et al (2021), which analysed peer-reviewed publications on 100 CE-certified radiological AI products and their supporting evidence. The current study builds upon this foundation by including additional AI products, updating the dataset to March 2023, and conducting a more comprehensive evaluation of peer-reviewed evidence. This overlap is clearly indicated in the Methods section, and the results are systematically compared to highlight trends and differences in study characteristics, efficacy levels, and overall evidence maturity [9]. Methodology: Retrospective Observational
References
-
- Najjar R (2023) Redefining radiology: a review of artificial intelligence integration in medical imaging. Diagnostics (Basel) 13:2760 - PubMed
-
- Radiology Health AI Register (2024) Radiology. Available via https://radiology.healthairegister.com/products . Accessed 17 Nov 2024
-
- van Leeuwen KG, de Rooij M, Schalekamp S, van Ginneken B, Rutten MJCM (2024) Clinical use of artificial intelligence products for radiology in the Netherlands between 2020 and 2022. Eur Radiol 34:348–354 - PubMed
LinkOut - more resources
Full Text Sources
