The SHIELD project seeks to revolutionise early detection of pancreatic cancer, focusing on individuals with high heritable genetic risk. Pancreatic ductal adenocarcinoma (PDAC) has a 5-year survival rate of less than 10%, primarily due to late-stage diagnosis. Consequently, 85% of PDAC cases are identified too late for curative treatment. However, early detection can significantly improve outcomes, increasing the survival rate to 42% with surgical intervention. There is a pressing need for better early detection methods, especially for those with familial or genetic predispositions. The only FDA-approved biomarker, CA19-9, is limited to monitoring treatment response due to its lack of sensitivity and specificity, while imaging methods ofter fail to detect early-stage cancers and cause a strain to the healthcare system due to their cost and limited availability. SHIELD aims to validate a new blood-based diagnostic test designed for early PDAC detection in high-risk individuals and pilot an early detection programme in Greece, Slovenia and Lithuania. Developed by partner Reccan, this test uses a 5-plex multiple immunoassay to analyze protein readouts and provides a probability score for pancreatic cancer. Initial studies with over 450 samples showed excellent performance with >91% sensitivity and >96% specificity. The project will validate the test's clinical performance in a prospective multi-center study across seven EU countries, targeting individuals with familial or genetic predispositions. It will also identify new protein biomarkers for other high-risk indications, such as new-onset diabetes (NOD). Collaboration with national screening authorities will help integrate this test into existing programs, and partnerships with patient organizations will enhance recruitment. SHIELD envisions transforming pancreatic cancer diagnostics by increasing the 5-year survival rate to 30% by 2035 in Europe. This action is part of the Cancer Mission cluster of projects on “Prevention & early detection (early detection heritable cancers)

Lung Cancer (LC) is the biggest cancer killer worldwide, with five-year survival following diagnosis varying between 5% to 25%. Though tobacco smoking has long been recognized as the major risk factor for LC, many cases (incl. LC patients that are non-smokers) cannot be explained by this reason. In this sense, LUCIA aims to establish a novel toolbox for discovering and understanding new risk factors that contribute to LC development. The toolbox encompasses the analysis of three aspects: (i) personal risk factors, which include a persons exposure to chemical pollutants and behavioural and lifestyle factors; (ii) external risk factors, such as urban, built and transport environments, social aspects and climate; and (iii) biological responses to the personal and external risk factors, including changes in genetics, epigenetics, metabolism and aging. Key components of the toolbox for analysing personal and external risk factors include retrospective and prospective cohort databases, AI models, wearable devices, novel non-invasive sensors, and multi-omics. Together, these tools will be used to identify the effects of a wide range of environmental, biological, demographic, community and individual-level risk factors associated with the formation of LC. Molecular changes associated with the risk factors identified by this set of tools will then be validated by cell and molecular biology methods and through in vivo analysis. The impact of the identified personal and external risk factors and the associated biological responses will be then validated in three clinical use cases: general population risk assessment and screening, precision screening of high-risk populations, and digital diagnostics. The resulting evidence within LUCIA will be translated into policymaking recommendations, with the aim to implement them in a screening program for LC. This action is part of the Cancer Mission cluster of projects on Understanding'.

Dementia is caused by a range of illnesses and disorders that damage the brain either directly or indirectly. With the rise of the ageing population in the EU, dementia is becoming a serious problem. Digital health interventions have the potential to improve the accessibility and effectiveness of palliative care. Palliative care is an area where these technologies are increasingly being evaluated for education (e.g. online learning, mobile applications or Virtual Reality tools), symptom management, care planning, decision-making, and interaction (e.g. professionals and caregivers using phones, internet and computer systems). However, most studies focus on a specific intervention with heterogeneous outcomes and are exposed to professional gatekeeping and biased samples consisting of patients who are mostly well and without considering cultural impacts. Due to improved understanding and treatment, more effective and innovative health technologies, improved patient safety and better ability and preparedness to manage epidemic outbreaks, along with priorities related to quality of life of dementia patients and survivors, treatment and dementia data monitoring should be crucial. This project will focus on: i) better understanding of dementia, focusing on their consequences, including pain, distress and causative links between health determinants, disease and interventions in order to provide evidence-base for policy-making, ii) identification of holistic intervention (treatment and care) and assessment of health outcomes, iii) innovative digital tools to optimize clinical workflows and iv) scientific evidence for improved/tailored policies and legal frameworks and to inform major policy initiatives at EU and global level. We target exactly those aspects of value by integrating digital interventions as palliative care of patients with poor prognosis of dementia and evaluating the impact of digital health interventions using Artificial Intelligence.

Along the whole value chain in using data for economic purposes, guidelines and tools are required to make the business of the different stakeholders successful, and the end-users confident that none of their rights are endangered. CERTAIN addresses these needs and delivers solutions for data holders, dataspaces and AI systems providers, and AI systems deployers, which are the primary actors of the data and AI value chain. They must be compliant with applicable European regulations, must reach this compliance in a timely manner, and at reasonable cost. CERTAIN delivers guidelines and technical tools to help with compliance, to assess data quality, to measure biases in datasets, and to protect privacy. CERTAIN sets the foundation of AI certification: it translates the regulations to business terms, builds a directory of certification entities per business, develops a platform to streamline the certification process, and tools for AI system providers and certification entities so that they could respectively prepare and run a certification process. In case of security breach, not only privacy may get compromised, but also AI models may become useless and lead to extremely damageable decisions. To make sure that AI-based products are of high quality and reliability, CERTAIN develops security tools and methods, specifically suitable for dataspaces and AI systems. CERTAIN addresses the environmental footprint of the AI value chain. Innovative techniques are elaborated to reduce energy consumption when building and running AI systems. This is beneficial not only for the green deal but to reduce cost for AI stakeholders. As importantly, CERTAIN considers the end-users perspective, and provides templates and guidelines that may be used by AI systems deployers to reassure end-users on the use of their private data. The project tests its results on seven operational pilots in six different business areas, considering all the actors along the AI value chain.

Generative adversarial networks (GANs) are a class of AI models able to create media contents audio and video resembling reality. Although there are different promising areas of application of GANs e.g. audio-graphic productions, human-computer interactions, satire, artistic creative expression their current and foreseen misleading uses are just as numerous and worrying. The main concern is related to the so-called deepfakes, fake images or videos simulating real events with extreme precision. If trained on a face, GANs can make it move and speak in a hyper-realistic way. This technology poses an urgent political threat since GANs could be and have already been used to spread fake news and disinformation. This raises an urgent challenge to democratic governance and regulation: to improve GANs accountability, transparency, and trustworthiness. Nevertheless, GANs also constitute an opportunity to enhance democratic awareness and expand active and inclusive citizenship. SOLARIS reacts to these challenges in two ways. On the one hand, we analyse political risks associated with these technologies, to prevent negative implications for EU democracies. As a result, SOLARIS will establish regulatory innovations to detect and mitigate deepfake risks. On the other hand, we assess the opportunities raised by GANs for reinvigorating the democratic engagement of citizens. We will co-create, involving citizen science, value-based GANs contents to enhance democratic engagement. SOLARIS involves three use cases: the first aims at understanding the psychological aspects of GANs perceived trustworthiness. The second simulates the circulation of threatening GANs contents on social media, to detect risks and design mitigation strategies. The third co-creates value-based GANs contents to boost awareness on key global democratic topics (e.g: climate change, gender dimension, human migration), to ultimately enhance active and inclusive digital citizenship.