Foundation models represent a paradigm shift in AI, exhibiting remarkable capabilities across multiple tasks. Their true potential lies in generalizing across diverse domains and modalities, a largely untapped frontier. DVPS advances this frontier by focusing on multimodal foundation models (MMFM), aiming to harness their capabilities across various application domains. DVPS emphasizes three core benefits of MMFM: label efficiency, compute reusability, and engineering efficiency. However, achieving these benefits in multimodal settings presents challenges such as modality-specific architecture and cross-modal alignment. To overcome these, DVPS aims to develop generalizable methods that work across diverse modalities and domains, creating a unified framework for MMFM development and integrating new modalities into existing models. The project focuses on generating foundational knowledge, delivering tested methods, and creating algorithms to expand MMFM capabilities across domains like cardiology, geo-intelligence, and language communication. DVPS also includes two "surprise domains" to drive innovation by challenging initial assumptions. Key objectives include the development of AutoDVPS, a toolkit for automated MMFM design, and the creation of DVPSBench, a benchmarking suite for evaluating MMFM across tasks and domains. DVPS aims to foster a European ecosystem for MMFM research, promoting transparency, fairness, and ethical compliance in line with European values. Through collaboration and open-source contributions, DVPS seeks to standardize and advance MMFM as a scientifically rigorous discipline.

Gallbladder cancer (GBC) is a neglected disease with huge potential for prevention. This project aims at significantly improving the accuracy of risk estimation and early detection of GBC by identifying and adequately considering geographical, environmental, lifestyle, ethnic, gender and molecular differences. We plan to generate the information needed to establish and refine current prevention programmes, including the primary, secondary and tertiary prevention of GBC. We will (1) build a unique European–Latin American GBC biorepository integrated into a tailored IT platform, (2) identify, validate and functionally characterize novel GBC biomarkers, (3) develop a multifactorial risk score that integrates established and newly identified epidemiological and molecular risk factors, (4) improve the understanding of the causal mechanisms that link lifestyle, cultural and behavioural factors to GBC development, (5) unravel novel opportunities for the targeted therapy of incidental GBC, (6) exploit existing and

In rapidly changing health care systems, digitalization, e-health and robotisation are gaining influence. Due to the existing global nurse shortage in Europe, a demand for healthcare and therewith nurses will continue to grow, whilst the supply of available nurses is projected to drop. Therefore, it is expected that the shortages will accelerate in the coming decade and will be more serious than the cyclical shortages of the past. This nursing shortage will ultimately constrain health system reform and innovation, and contribute to escalating costs. ICT, AI and robotization are one way to support health care professionals, enhance interprofessional cooperation and patients` safety. This introduction of ICT, robotisation and other technologies in nursing care will create a disruptive change in the provision of health and nursing care. Furthermore, research shows, that the usage of ICT is still limited within the health care professions and thus in nursing. For that external and internal factors have been identified, e.g. infrastructure not being suitable or the lack of interoperability of different computer and ICT systems, the limited awareness and understanding of ICT concepts. Health care professionals who use ICT complain about the lack of skills and tailored trainings for their needs. Usually nurses have to learn ICT related skills on the job within their working duties. As ICT is rapidly changing and developing towards robotization and AI, the resistance and skepticism towards technology among nursing professionals are expected to grow. The NursingAI project will analyze and forecast the types of skills and competencies needed by health care professionals, especially nurses. By gaining insight of needed competencies and skill, curriculums for trainings and education programs can be enhanced to the actual needs concerning ICT competencies. NursingAI will work towards an assessment and training tool for skills related to AI, robotisation, digitalization and e-health in nursing sectors of Germany, Hungary and the Netherlands. The tool prototype will be tested and evaluated in these countries in order to make them available for local and European VET curriculums and further education programs. These efforts are critical, since 1), nurses should be able to understand and work with novel AI and Information and Communication Technologies (ICT) in order to improve the general quality of care; 2) the current offer of assessment and training methods on AI, robotisation, digitalization and e-health skills in nursing in Europe is very limited, and 3) in order to have a significant amount of AI and robotization skilled nurses in place in 5-10 years time in Europe, investments and changes in the VET curricula need to be initiated now. With the transnationally project, needed competencies in future workplaces will be multiplied and progress made in VET and health care.