As AI tools continue to flood the radiology market, understanding their clinical value is essential. This study systematically reviewed 173 commercially available radiology AI products, revealing a significant gap between availability and peer-reviewed evidence. While many tools are marketed for clinical use, few are supported by robust, published validation, especially in real-world settings.
The analysis highlights how difficult it can be for radiologists and health systems to judge which AI tools are trustworthy. Many products lack transparency around performance, generalizability, and safety, raising concerns about premature adoption without adequate scrutiny.
This study reinforces the urgent need for higher evidence standards and regulatory oversight. For health systems navigating AI procurement, it suggests that decision-making should not rely on vendor claims alone. Instead, independent validation and ongoing performance assessment are critical to ensure safe and meaningful use of AI in clinical practice.
Artificial intelligence in radiology: 173 commercially available products and their scientific evidence
European Radiology, 2025
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.