With over 12000 employees, UMCU is one on the biggest public healthcare institutions in the Netherlands.
UMCU has a strong track record with set-up, logistical support, coordination and coordination of (access to) large (international) real-world (imaging) data infrastructures (ALLURE, MOMENTUM). Also, UMCU is a pioneer and experienced partner when it comes to initiating and conducting (randomized) studies embedded in large RWE infrastructures or in routine care. Participants from the UMCU hold several advisory and scientific positions in relevant RWE committees, research groups and boards, including the MR-Linac consortium, CONSORT-ROUTINE and Trials within Cohorts Network. As such, UMCU is in the perfect position to create and oversee an international imaging repository which can be used not only by the AI imaging analysis experts to develop and train algorithms, but also by clinical epidemiologists to clinically evaluate the AI systems, and by future researchers for AI activities beyond the scope of the current project.
Evaluation of medical ethical aspects of the AI systems will be led by a medical ethicist with ample experience from the UMCU. UMCU will also provide strong statistical expertise, in particular on development, validation and implementation of prediction models. This organization has a strong network in this area, with participation in AIrelated working group, i.e. TRIPOD-AI (Transparent Reporting of a multivariable prediction model of Individual Prognosis Or Diagnosis) and PROBAST-AI (statement and the Prediction model Risk Of Bias Assessment Tool). Also, the UMCU statistician involved in ARTILLERY was member of the committee who created the Dutch Guideline for high-quality diagnostic and prognostic applications of AI in healthcare, commissioned by the Dutch Ministry of Health, Welfare and Sport. This guideline outlines good professional conduct in the development, testing and implementation of an Artificial Intelligence Prediction Algorithm (AIPA) in the medical sector.
