Radiotherapy is a widely used cancer treatment, however some patients suffer side effects. In breast cancer, side effects can include breast atrophy, arm lymphedema, and heart damage. Some factors that increase risk for side effects are known, but current approaches do not use all available complex imaging and genomics data. The time is now ripe to leverage the huge potential of AI towards prediction of side effects. This project will use rich datasets from three patient cohorts to design and implement an AI tool that predicts the risk of side effects, including arm lymphedema in breast cancer patients and provides an easily understood explanation to support shared decision-making between the patient and physician. The PRE-ACT consortium combines the expertise in computing (MDW, AUEB-RC), AI (HES-SO, CENTAI), radiation oncology (MAASTRO, UNICANCER), medical physics (THERA), genetics (ULEIC), psychology (CNR) and health economics (UM) that is necessary to tackle this problem. The project will integrate data from the three cohorts and build AI predictive models with built-in explainability for each of the key side effects of breast cancer radiotherapy. These AI models will be incorporated into an existing commercial radiotherapy software platform to create a world-leading product. The extended platform will be validated in a clinical trial to support treatment decisions regarding the irradiation of lymph nodes. The trial will adopt an innovative design in which the patients and medical team in the test arm will receive the risk prediction, but those in the control arm will not. A communication package built with a co-design methodology will ensure that AI outcomes are tailored to stakeholders effectively. The trial will evaluate whether using the AI platform changed the arm lymphedema rate and impacted treatment decisions and quality-of-life. Generalizability of the AI models for other types of cancer will be sought through transfer learning techniques.

Networks and graphs have been fundamental in modelling complex systems, yet their focus on pairwise interactions limits their ability to fully capture the dynamics of systems like the brain, where coordinated activity among multiple neurons is essential for functioning. Higher-order interactions (HOIs), which represent the collective interplay of groups of nodes, have become increasingly recognised as crucial for understanding both brain function and other complex systems. However, while HOIs have shown promise at the mesoscopic level, their relationship to microscale neural mechanisms remains largely unexplored. This project aims to address this gap by introducing a mathematical framework designed to characterise the temporal dynamics of HOIs in neuronal activity. By reconstructing higher-order networks from simulated neuronal dynamics, the project will model these interactions to offer a novel perspective on how the brain processes information over time. Validation of the framework will be carried out using high-resolution neuronal recordings, such as Neuropixels data, which provide unparalleled accuracy in observing "genuine" higher-order interactions within neural circuits. Given the challenges associated with direct neuronal data, we will also develop methods to infer HOIs from indirect data sources, such as calcium imaging. This approach will be fine-tuned to ensure that the inferred interactions closely align with the statistical patterns observed in Neuropixels recordings. This dual strategy enhances the robustness and generalisability of the framework, making it applicable across various data types. By offering a comprehensive characterisation of HOIs in brain dynamics, this project will not only deepen our understanding of neural processing but also open new avenues for cross-disciplinary research. Upon completion, an open-source software package will be released, ensuring the methods and tools developed are accessible to the broader scientific community.

Europe is facing unprecedented challenges, such as the health, migration, economic, climate, energy, and political crises, leading to a sharp increase in emergency public spending and relaxation of due diligence checks. This has resulted in a rise in corruption and fraudulent activities, which have significant negative impacts on the European economy, society, environment, and democracy. Despite emerging technology’s potential to become a powerful tool in the fight against corruption and fraud, the public sector has been slow to adopt digitalization, resulting in data NOT being shared, harmonized, or properly analysed, making evidence-based decision-making almost impossible. Governments are slowly adopting new approaches to ensure a more data-driven, transparent, and accountable public governance, but several fundamental data-related issues remain unresolved. With a team of 9 excellent research institutions and universities, 12 technology, business, and standards, developing companies, 7 public end users, and 3 domain-relevant, industry-exposed NGOs, CEDAR will: (1) Identify, collect, fuse, harmonise, and protect complex data sources to generate and share 10+ high-quality, high-value datasets relevant for a more transparent and accountable public governance in Europe. (2) Develop interoperable and secure connectors and APIs to utilise and enrich 6+ Common European Data Spaces. (3) Develop innovative and scalable technologies for effective big data management and Machine Learning (ML) operations. (4) Deliver robust big data analytics and ML to facilitate human-centric and evidence-based decision-making in public administration. (4) Validate the new datasets and technologies (TRL5) in the context of fighting corruption, thus aligning with the EU strategic priorities: digitalisation, economy, democracy. (5) Actively promote results across Europe to ensure their adoption and longevity, and to generate positive, direct, tangible, and immediate impacts.

Many systems that govern our everyday lives—from communication networks to the human brain—can be seen as networks of interconnected units. Traditionally, networks are equated with graphs where edges give pairwise relations between two units. However, in network dynamical systems, nonlinear higher-order interactions between more than two units often play a critical role in shaping the collective dynamical behaviour of all units: For example, the spread of a disease depends not only on our behaviour as pairs of individuals but also how we behave in groups of more than two. Thus, elucidating the role of these higher-order interactions is critical to understand and control the dynamics of complex systems that determine our lives and livelihoods, whether it is the spreading of a disease or the proper functioning of the human brain as a network of billions of neurons. The doctoral network BeyondTheEdge will identify the role of nonpairwise higher-order interactions in the emergence of complex dynamical behaviour of networks of interacting units. BeyondTheEdge brings together key researchers in an international network that is interdisciplinary (from mathematics to neuroscience) and intersectorial (including academia, private research institutes, and industry) to develop new mathematical insights relevant for real-world problems. BeyondTheEdge will train a cohort of 10 PhD students through research, education, and complementary skills training. This will enable the PhD students to innovate, collaborate, and become leading professionals in academia, industry, or the public sector: Innovative training activities will ensure that all PhD students can apply their skills beyond the academic context and put them in perspective of the wider world. Supervisor training activities ensure that the more junior project partners can shape the PhD education of the future. Thus, BeyondTheEdge will make a lasting contribution that will far outlive the duration of the project.