GenoMed4All advanced beyond the state of the art by delivering the first federated learning infrastructure specifically tailored to rare haematological diseases, combining secure-by-design deployment across multiple hospitals with novel methods for multimodal data integration (genomic, imaging, clinical). The project generated new AI pipelines for survival prediction, relapse risk stratification, and imaging biomarker extraction, validated across international cohorts in a privacy-preserving federated setting. These methods contribute novel insights into disease mechanisms, treatment outcomes, and genotype–phenotype associations, while demonstrating that AI models can be clinically validated without centralising sensitive patient data.
By project end, GenoMed4All consolidated 26 Key Exploitable Results (KERs), covering the federated learning platform and services, disease-specific AI pipelines, synthetic data generation, harmonisation tools, clinical decision support prototypes, and training and dissemination outputs. Exploitation strategies for these KERs are under discussion, with several already feeding into initiatives such as ERN-EuroBloodNet, HARMONY, SYNTHEMA, and SYNTHIA. Dissemination and communication were extensive: 25 peer-reviewed articles, 26 conference papers/posters, 27 Zenodo records, 39 blog entries, and 39 videos, alongside 39 major events, 14 webinars/workshops, and 2 EuroBloodNet training waves with over 300 participants. Online visibility reached ~1.8k social followers, 1.2k+ posts, nearly 5k website visitors, and 20k page views.
GenoMed4All’s achievements contribute to better patient stratification, earlier diagnosis, and more informed treatment choices in rare and complex haematological diseases. By lowering the barriers to collaborative research while ensuring GDPR compliance, the project strengthens trust in AI adoption in healthcare. Its federated approach paves the way for sustainable European infrastructures where hospitals and research centres can cooperate without data leaving their premises. This has socio-economic implications in reducing research costs, accelerating therapeutic development, and enabling more equitable access to precision medicine. At the societal level, GenoMed4All fosters patient empowerment through involvement of patient organisations, raises awareness of rare diseases, and supports Europe’s leadership in ethical, secure, and impactful use of AI in health.
