AIFI evaluation: Collaborating on AI in radiology
How can we ensure that AI solutions are not only smart but also effective in real-world settings? AIFI explored how to deploy AI in medical imaging of patients, with attention to technology, integration, clinical impact, and procurement.
This factsheet reflects on the first phase of AIFI, the feasibility study conducted with five hospitals: Catharina Ziekenhuis, Gelre Ziekenhuizen, Radboudumc, Ziekenhuisgroep Twente, and Ziekenhuis Rivierenland. Three AI solutions for three clinical application areas, one shared infrastructure.
For suppliers, this offers valuable insights into both the technical and organizational aspects of AI adoption in healthcare.
Key findings
- The fracture detection application (RBfracture™ version 2.2) was used by more than half of the users in at least 70% of cases
- RBfracture led to adjusted workflows in some hospitals, allowing radiographers to act more independently and quickly
- The AIFI pilot has been extended one year until June 30, 2026, and all five hospitals remain involved in the next phase
Download the evaluation
Evaluation AIFI
This original research was published in August 2025 by AIFI. The PDF is available for download.
Entering your information does not subscribe you to marketing emails from Radiobotics. You can always read our privacy policy.
Funding and conflicts of interests
AIFI is a feasibility project for a national radiology AI infrastructure, containing technical, clinical and financial components.
Extensive testing was done with all three AI applications, evaluating both technical performance and clinical usability.
AIFI is funded by Zorgverzekeraars Nederland.