According to the European Research Data Landscape – Final report, a survey involving almost 9,898 responders, highlighted some of the main barriers to management and sharing of research data: time, effort, storage, skills required, and the lack of recognition and data protection. RAISE Suite will develop a system specifically designed to remove barriers to data sharing, replacing technological achievements that do not influence researchers’ attitude towards sharing data. To do so, RAISE Suite will develop the solutions required to automate the process from data collection to dataset generation, guided by a FAIR-by-design principle to remove barriers such as perceived effort, time, as well as skills required for data sharing. At the same time, EOSC-RAISE will be integrated into RAISE Suite, for a platform which supports simple dataset sharing and exploitation, mitigating the sense of lack of recognition and data protection among researchers. Furthermore, RAISE Suite will implement a DMP-guided data collection and management policy. In particular, RAISE Suite will not only adopt a Machine Actionable Data Management Plan (ma-DMP), but further extend it to support designated actions, τurning the persistent identifier DMP-ID into the main reference point for the whole data lifecycle, following research activities, making the connections with underlying algorithms and data, and updating the DMP accordingly from collection, depositing and storing, to discovery, management, processing, reusing and exploitation. RAISE Suite capitalises on the results of a previously funded EC initiative. To this end, RAISE Suite will leverage work done by the EOSC-RAISE project, incorporating its technical platform that moves from open data to data open for processing, introducing the technology required to cover the data lifecycle from the data collection to the dataset generation.

PREVENT improves upscaling of primary interventions for weight control management during childhood and adolescence to reduce cancer risks in adulthood. This relies on current evidence that relates excess body weight with increased cancer risk. Towards this end, PREVENT applies a series of implementation research actions in the following directions. First, it identifies barriers to current interventions and policies preventing them from upscaling to different geographical, socio-economic, and cultural settings. Then, it introduces new multi-actor and context-aware interventions along with new user engagement strategies to face the current upscaling bottlenecks; multi-actor in the sense that they target different types of users (e.g., students, family, educators, policymakers) and context-aware in the sense that PREVENT interventions are tailored to the specific implementation places (class, canteen, sports fields, labs, outside school). The PREVENT new policies are adapted, piloted, and scaled up within the schools’ communities of three European countries facing different epidemiological settings on childhood obesity, geographic, socio-economic and cultural attributes. The pilots are designed to be holistic end-to-end ecosystems, including users, medical professionals, policymakers, public authorities, and civil communities. They focus on the whole school communities of Greece, Sweden, and Spain-Catalonia, that is, PREVENT outreach to more than 3.3 million students, required for guideline provisioning, large-scale implementation, multi-parameter assessment, and scaling-up. Co-creation, active behavioral change, self-evaluation through user empowerment, motivational interviewing, social innovation, digital-assistive engagement, health apps, and multi-domain assessment are implementation research aspects of PREVENT to advance user acceptability and compatibility with existing policies, and thus improve sustainability and upscaling. This action is part of the Cancer Mission cluster of projects on "Prevention and Early Detection".

Ovarian cancer (OC) is the most lethal of female cancers, often termed a “silent killer”. DISARM’s overall approach to tackle the significant gaps in hereditary OC management lies in tackling both key elements of risk assessment and early detection. The project will investigate multifactorial risk assessment versus standard practices in 4 EU Member States (MS) (Lithuania, Portugal, Czech Republic, and Greece), and will upscale and validate a set of easy-to-use, highly accurate and affordable technologies in five countries (UK, Lithuania, Portugal, Czech Republic, and Greece). Several intelligent digital assets will optimally support and enhance our clinical studies, while a range of multifaceted activities will ensure the future uptake and adoption of DISARM solutions. The project aligns with the Innovation Action character of this topic by focusing on both mature technologies that can be upscaled in routine healthcare and on emerging technologies that have already shown a potential to justify larger scale validation activities. Our ultimate ambition is to holistically investigate the preconditions and set the stage for rolling out proven solutions in routine OC risk assessment, and in parallel to create further evidence for the introduction of novel promising elements in early detection programmes. DISARM gathers 26 partners from 12 countries (10 EU MS, the UK and Canada), thereby exhibiting a significant geographic coverage, strengthening European and international collaboration and ensuring widespread diffusion of the project results. This action is part of the Cancer Mission cluster of projects on ‘Prevention and Early Detection (early detection heritable cancers)

Pancreatic cancer has the lowest survival rate amongst other cancers and is responsible for 95,000 deaths every year in the EU. Its treatment is usually palliative, aiming at slowing tumour progression and at symptom management. The main hypothesis of RELEVIUM is that quality of life (QoL) of advanced pancreatic cancer patients can be significantly improved by reducing pain and cachexia through highly personalised nutrition, physical activity, and pain management strategies, in addition to chemotherapy treatment. To achieve this, RELEVIUM will empower patients with digital tools that facilitate patient-doctor communication and enable them to self-manage their disease. RELEVIUM will use (i) a multi-sensor smartwatch and an innovative remote ultrasound patch, (ii) AI algorithms for continuous remote monitoring of pain and sarcopenia, as well as for decision support, and (iii) patient and caregiver applications. Combined, these tools will provide a stream of evidence on symptom progression and will enable physicians to apply personalised care plans. RELEVIUM brings together an interdisciplinary team of experts and will also involve patients and their caregivers in an iterative co-creation process. The project will initially conduct a feasibility and data collection study (RELEVIUM-FDC, n=130). The study aims at optimizing patient adherence and compliance, and at collecting data for the development of the intervention. A five-centre randomized clinical trial (RELEVIUM-RCT) will then evaluate the efficacy of the proposed personalised care plans for advanced pancreatic cancer patients (n=132) in terms of their QoL. Several secondary outcomes will be investigated, such as the cost-effectiveness of the intervention, its potential in increasing health equity and in relieving the stress burden on the patient families. The study outcomes will result in recommendations for integrating remote monitoring and improving QoL outcomes in palliative care for advanced pancreatic cancer

Parkinson’s disease (PD) is the most common neurodegenerative movement disorder, with a multifactorial aetiology, heterogeneous manifestation of motor and non-motor symptoms, and no cure. PD is often missed or misdiagnosed, as early symptoms are subtle and common with other diseases, allowing for considerable damage to occur before treatment. Moreover, selecting the optimal medication regimen is usually a lengthy, “trial and error” process, leading to critical, costly non-adherence. Following a trustworthy and inclusive approach to AI development and based on multidisciplinary expertise and broad stakeholder engagement, AI-PROGNOSIS aims to advance PD diagnosis and care by: 1) developing novel, predictive AI models for personalised PD risk assessment and prognosis (in terms of time to higher disability transition and response to medication) based on multi-source patient records and databases, including in-depth health, phenotypic and genetic data, 2) implementing a system of biomarkers informing the AI models by tracking key risk/progression markers in daily living, and ultimately 3) translating the models and digital biomarkers into a validated, privacy-aware AI-driven toolkit, supporting healthcare professionals (HCPs) in disease screening, monitoring and treatment optimization via quantitative, explainable evidence, and empowering individuals with/without PD with tailored insights for informed health management.