CHAIMELEON aims to set up a structured repository for health imaging data to be openly reused in AI experimentation for cancer management. An EU-wide repository will be built as a distributed infrastructure in full compliance with legal and ethics regulations in the involved countries. It will build on partner´s experience (e.g. PRIMAGE repository for paediatric cancer and the Euro-BioImaging node for Valencia population, by HULAFE; the Radiomics Imaging Archive by Maastricht University; the national repository DRIM AI France, the Oncology imaging biobank by Pisa University). Clinical partners and external collaborators will populate the Repository with multimodality (MR, CT, PET/CT) imaging and related clinical data for historic and newly diagnosed lung, prostate, colon and rectal cancer patients. A multimodal analytical data engine will facilitate to interpret, extract and exploit the right information stored at the Repository. An ambitious development and implementation of AI-powered pipelines will enable advancement towards automating data deidentification, curation, annotation, integrity securing and images harmonisation, the latest being of the highest importance for enabling reproducibility of Radiomics when using large multiscanner/multicentre image datasets. The usability and performance of the Repository as a tool fostering AI experimentation will be validated, including a validation subphase by other world-class European AI developers, articulated via the organisation of Open Challenges to the AI Community. A set of selected AI tools will undergo early on-silico validation in observational (non-interventional) clinical studies coordinated by leading experts in Gustave Roussy (lung cancer), San Donato (breast), Sapienza (colon and rectal) and La Fe (prostate) hospitals. Their performance will be assessed, including external independent validation, on hallmark clinical decisions in response to some of the currently most important clinical end points in cancer.

The complex interactions between genetic and non-genetic factors produce heterogeneities in patients as reflected in the diversity of pathophysiology, clinical manifestations, response to therapies, disease development and progression. Yet, the full potential of personalized medicine entails biomarker-guided delivery of efficient therapies in stratified patient populations. MultipleMS will therefore develop, validate, and exploit methods for patient stratification in Multiple Sclerosis, a chronic inflammatory disease and a leading causes of non-traumatic disability in young adults, with an estimated cost of €37 000 per patient per year over a duration of 30 years. Here we benefit from several large clinical cohorts with multiple data types, including genetic and lifestyle information. This in combination with publically available multi-omics maps enables us to identify biomarkers of the clinical course and the response to existing therapies in a real-world setting, and to gain in-depth knowledge of distinct pathogenic pathways setting the stage for development of new interventions. To create strategic global synergies, MultipleMS includes 21 partners and covers not only the necessary clinical, biological, and computational expertise, but also includes six industry partners ensuring dissemination and exploitation of the methods and clinical decision support system. Moreover, the pharmaceutical industry partners provide expertise to ensure optimal selection and validation of clinically relevant biomarkers and new targets. Our conceptual personalized approach can readily be adapted to other immune-mediated diseases with a complex gene-lifestyle background and broad clinical spectrum with heterogeneity in treatment response. MultipleMS therefore goes significantly beyond current state-of-the-art thereby broadly affecting European policies, healthcare systems, innovation in translating big data and basic research into evidence-based personalized clinical applications.

Coronavirus disease 2019 (COVID-19) caused by infection with SARS coronavirus 2 (SARS-CoV-2) has reached pandemic proportions with more than 7 million people infected and 0.4 million people killed worldwide. Death rates are accentuated by cardiovascular comorbidities and arrhythmias leading to unexpected major cardiovascular events. Being able to identify COVID-19 patients at risk of developing cardiovascular events leading to death would allow improving surveillance and care. Currently, there is no accurate method to predict outcome of COVID-19 patients. COVIRNA is a patient-centered Innovation Action aiming to satisfy this urgent and unmet need. COVIRNA will complete and deploy a prognostic system based on cardiovascular biomarkers of COVID-19 clinical outcomes combined with digital tools and artificial intelligence analytics (i.e. prediction model). Complementary expertise of 15 EU partners from the healthcare sector, academia, association and industry will allow conducting a large retrospective study on existing cohorts of COVID-19 patients. By upscaling the already validated and patented research use only FIMICS panel of cardiac-enriched long noncoding RNA biomarkers into an in-vitro diagnostic test (COVIRNA) adapted to COVID-19 patients, the project will quickly deliver a minimally-invasive, simple yet robust and affordable prognosis tool that can be used in the context of the current COVID-19 crisis as well as in further major health issues. By tackling the cardiovascular complications in COVID-19, known to contribute significantly to mortality, the project outputs are expected to have a major impact on the pandemic outcomes. The COVIRNA test will be CE-marked and prepared for commercialization, allowing to risk stratify patients, adapt therapies and to inform drug design.

The prevalence of neurodegenerative disorders, including Alzheimer’s disease, Parkinson’s disease, Amyotrophic lateral sclerosis and frontotemporal dementia, continues to rise, partly due to increasing life expectancy. The diagnosis of these disorders remains a significant challenge due to overlapping symptoms, delayed recognition of early symptoms often mistaken for normal aging, and variability in symptom presentation across patients. METNEDIA will tackle these challenges by proposing a new framework for the development of a diagnostic tool. METNEDIA will utilize metabolomic analysis and artificial intelligence to develop a diagnostic tool for the diagnosis of neurodegenerative diseases. A discovery phase will be initially performed using untargeted metabolomic approaches to identify most relevant biomarkers. The project will then develop of a diagnostic kit based on mass spectrometry and artificial intelligence for the diagnosis of widely diffuse neurodegenerative diseases. A multicenter validation of the kit will be also performed. Neurotoxic evaluation of molecules identified as relevant for each disease will be evaluated in vitro. Finally, bioinformatic and machine learning will be used to gaining insight on the biology of neurodegenerative disorders using in vitro and in vivo data.