A federated paradigm of real-world data sources utilization for the empowerment of diagnosis, prognosis and risk assessment of cardiovascular conditions

HealthHORIZON-RIAID: 101137278
EC Contribution
€96,735
Consortium Size
20 orgs
Start Year
2024
Summary

In the EU more than 6 million new cardiovascular disease (CVD) cases are reported yearly, along with 1.8 million related deaths, posing a substantial burden on the national healthcare systems and society in general. Development of effective preventive interventions, adopted for each individual and population, will not only reduce the overall cost of patient management, but will also justify the assertion that CVDs could be ultimately prevented and controlled. The exploration of existing clinical, genetic and real-world data sources can contribute to this direction, however several challenges related to the data availability, management and processing remain open. The 48-month project CVDLINK aims to tackle these challenges by implementing a privacy-by-design European-wide federated platform-as-a-service (PaaS) for the delivery of effective data-driven human-centric interventions and the advancement of research and management in the CVD domain. CVDLINK is based on two major offerings: (1) the seamless and legally compliant linking and integration, secure sharing and automated curation of existing data; and (2) a set of AI and data-enabled precision medicine tools and pipelines, for better diagnosis, risk stratification and treatment. In the context of the project, 7 different cardiovascular conditions will be examined, making use of different retrospective datasets, cohort studies and biobanks from 7 counties, aiming to set a paradigm of the how heterogeneous data sources, can be effectively exploited for building comprehensive AI-driven tools, in order to bring substantial benefits for health systems, patients, industry and EU citizens. The developed tools will be prospectively validated in 5 countries, demonstrating the impact of CVDLINK. Additionally, a set of best practices will be generated, which along with a cost-effectiveness analysis, and systematic raising awareness campaigns will promote its wide adoption in the mid-term.

Consortium (20)

Project Results (7)

Source: CORDIS, the EU research results database.

Publications (3)
Privacy-preserving multicenter differential protein abundance analysis with FedProt
Nature Computational Science· 2025DOI
Yuliya Burankova, Miriam Abele, Mohammad Bakhtiari, Christine von Toerne, Teresa K. Barth, Lisa Schweizer, Pieter Giesbertz, Johannes R. Schmidt, Stefan Kalkhof, Janina Müller-Deile, Peter A. van Veelen, Yassene Mohammed, Elke Hammer, Lis Arend, Klaudia Adamowicz, Tanja Laske, Anne Hartebrodt, Tobias Frisch, Chen Meng, Julian Matschinske, Julian Späth, Richard Röttger, Veit Schwämmle, Stefanie M. Hauck, Stefan F. Lichtenthaler, Axel Imhof, Matthias Mann, Christina Ludwig, Bernhard Kuster, Jan Baumbach, Olga Zolotareva
Enhancing Cardiac AI Explainability Through Ontology-Based Evaluation
2024 15th International Conference on Information, Intelligence, Systems & Applications (IISA)· 2024DOI
Nikos Tsolakis, Christoniki Maga-Nteve, Stefanos Vrochidis, Nick Bassiliades, Georgios Meditskos
Predicting long-term risk of sudden cardiac death with automatic computer-interpretations of electrocardiogram
Frontiers in Cardiovascular Medicine· 2024DOI
Minna Järvensivu-Koivunen, Antti Kallonen, Mark van Gils, Leo-Pekka Lyytikäinen, Juho Tynkkynen, Jussi Hernesniemi
Deliverables (3)
Other Results (1)
Periodic Reporting for period 1 - CVDLINK (A federated paradigm of real-world data sources utilization for the empowerment of diagnosis, prognosis and risk assessment of cardiovascular conditions)