Pilot use case: The Mammography Screening with Artificial Intelligence trial (MASAI)

Use case description: A commercial AI tool for triage and detection support in mammography screening has been evaluated in a large randomised controlled trial that aimed to compare AI-supported mammography screening to standard double reading without AI. With the use of AI, the cancer detection rate increased by 29% without increasing false positives and while reducing the screen-reading workload by 44%

More information about the project can be found here: AI-supported breast cancer screening – new results suggest even higher accuracy | Lund University

Location: Mammografimottagning Unilabs, Skåne university hospital, Malmö

Solutions this pilot contributes to: 2.1 (Need identification, Game plan, Guiding principles)

How and why we piloted the Clinical AI Pathway tools

In CAIDX, piloting means testing the Clinical AI Pathway tools in real AI projects before wider roll-out. The purpose is to ensure that the tools genuinely support healthcare professionals, researchers, and companies in developing and integrating AI solutions. By engaging directly with stakeholders across 16 use cases from six partner countries, we can validate what works, identify what needs improvement, and ensure the Clinical AI Pathway Toolbox becomes a practical, relevant guide—from idea to deployment.

To achieve this, we piloted the tools through surveys, interviews, workshops, roundtables, and real-life testing in clinical and development settings. The three pilots covered different stages of the AI pathway—initiation, development, and implementation—and involved input from clinicians, researchers, hospitals, companies, legal experts, and other specialists. Using diverse methods and real AI projects allowed us to refine the tools and confirm their usefulness before final publication.

Programme Manual Online

Choose