Pilot use case: Shock prediction in ICU (SPICU)

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.