Crowdsourcing AI solutions in healthcare using sensitive data in accordance with regulatory guidelines for translational medicine

Background: The uptake of new digital and AI based technologies in the health care setting, including digital diagnostics, has been comparatively slower than in other sectors. This is a consequence of the complex legislature, lack of routine procedures for the secondary use of sensitive medical data. Inadequate level of education and incentives for different stakeholders prevents overcoming strong barriers, such as clinical workflow integration, and need for comprehensive eval uation of utility of interventions which requires multi-disciplinary collaboration effort. The paper presents a Re-hospitalization Challenge, organised by the European Digital Innovation Hub (EDIH)- AI4Health.Cro, a co-creation activity and an effective tool for overcoming the mentioned barriers for implementation of new AI technologies and overall innovation ecosystem build-up. Methods: Crowdsourcing challenges or hackathons are R&D strategies in which ad-hoc assembled competing teams collaborate on early-stage technology devel opment or research problem solving. Re-hospitalisation challenge, in our case, has had multiple facets: as a co-creation activity tasked with construction of an AI predictive model with the explanatory support and plausible business model for its deployment; it involved also extensive organisers effort: data anonymisation, provision of secure processing environment, and comprehensive assessment of solutions. The paper details the challenge structure and processes, from problem inception to execution and comprehensive evaluation of developed solutions. Results: As a co-creation effort in digital healthcare, the challenge provided results on multiple levels: (i) through tailored solutions based on real evi dence data, serving as benchmarks or prototypes for later deployment in practice; (ii) through sandboxing EHDS principles to enable secondary data use; (iii) as an ecosystem building event yielding ad-hoc collaborative teams and cross-disciplinary participative learning experience. Conclusions: Crowdsourcing innovation challenges are valuable digital health care ecosystem building tool that provides a number of direct and indirect 2 impacts, from providing valuable diagnostic prototypes for innovation elicitation, creation and transformation of startups, to streamlining secondary use of clinical data for research and innovation. Overall impact is also enhanced through raising the awareness and education of all stakeholders relevant for the translation of AI technologies and into routine clinical setting.