Periodic Reporting for period 3 - GenoMed4ALL (Genomics and Personalized Medicine for all though Artificial Intelligence in Haematological Diseases)
Berichtszeitraum: 2024-01-01 bis 2025-06-30
GenoMed4All is a European initiative to transform the response to haematological diseases by seizing the power of Artificial Intelligence (AI) and standardized interoperable sharing of cross-border data. For doing so, the project will support the pooling of genomic, clinical data and other “-omics” health data through a secure and privacy respectful data sharing platform based on the novel Federated Learning (FL) scheme, to advance research in personalised medicine.
GenoMed4All makes use of the existing infrastructures and initiatives, including powerful High-Performance Computing (HPC) facilities, hospital registries, data processing tools, and pre-existing repositories towards facilitating personalised medicine in common, rare and ultrarare haematological diseases to demonstrate the versatility and utility of the solutions. The strategy is defined to start to integrate the 10 clinical partners to later enlarge it to the overall 66 relevant clinical repositories in 15 Member States that ERN-EuroBloodNet members involve, besides 20 repositories not present in EuroBloodNet.
GenoMed4All aims to demonstrate the potential and benefits of trustable and explainable AI technologies, with a novel approach to AI models and algorithms (deep learning, variational autoencoders, generative models, besides combining with advanced statistical and Machine learning) to exploit the powerful set of “-omics” data which will be at researchers’ disposal leading to more reliable and meaningful outcomes for advancing research and personalised medicine, with 3 use cases covering oncological and non-oncological Haematological Diseases (HD). It will allow for identifying new knowledge, to support clinical research and decision making by linking Europe's relevant genomic repositories in haematological diseases, while ensuring full compliance with data protection legislation and ethical principles and increasing the AI trust for personalized medicine and impact.
GenoMed4All makes use of the existing infrastructures and initiatives, including powerful High-Performance Computing (HPC) facilities, hospital registries, data processing tools, and pre-existing repositories towards facilitating personalised medicine in common, rare and ultrarare haematological diseases to demonstrate the versatility and utility of the solutions. The strategy is defined to start to integrate the 10 clinical partners to later enlarge it to the overall 66 relevant clinical repositories in 15 Member States that ERN-EuroBloodNet members involve, besides 20 repositories not present in EuroBloodNet.
GenoMed4All aims to demonstrate the potential and benefits of trustable and explainable AI technologies, with a novel approach to AI models and algorithms (deep learning, variational autoencoders, generative models, besides combining with advanced statistical and Machine learning) to exploit the powerful set of “-omics” data which will be at researchers’ disposal leading to more reliable and meaningful outcomes for advancing research and personalised medicine, with 3 use cases covering oncological and non-oncological Haematological Diseases (HD). It will allow for identifying new knowledge, to support clinical research and decision making by linking Europe's relevant genomic repositories in haematological diseases, while ensuring full compliance with data protection legislation and ethical principles and increasing the AI trust for personalized medicine and impact.
Over its full duration, GenoMed4All has built and validated a secure Federated Learning platform enabling privacy-preserving AI development across distributed clinical data in rare haematological diseases. Clinical partners contributed extensive datasets covering more than 2,000 patients across Myelodysplastic Syndromes (MDS), Multiple Myeloma (MM), and Sickle Cell Disease (SCD), which were harmonised and integrated into the platform. On this basis, the consortium developed and validated multiple AI pipelines for tasks such as survival prediction, risk stratification, imaging biomarker extraction, and genotype–phenotype correlations. These were tested in real-world federated settings across clinical sites, demonstrating feasibility.
Results have been widely disseminated through more than 20 peer-reviewed publications, over 40 conference presentations, and targeted communication to clinical and patient communities. Two online training programmes were delivered with EuroBloodNet, supporting knowledge transfer to clinicians and researchers. Exploitation activities focused on sustaining the federated platform beyond the project, with use cases and tools feeding into ongoing initiatives (e.g. EuroBloodNet registries, partner-led developments such as SYNTHIA and SYNTHEMA). The project also engaged with industry and public stakeholders to pave the way for sustainable uptake of federated AI in healthcare. and clinical plausibility.
By the end of the project, GenoMed4All demonstrated that federated AI approaches can be effectively applied to rare and complex diseases while respecting data protection constraints. The results provide a robust foundation for continued clinical validation, broader disease coverage, and integration into European infrastructures, reinforcing Europe’s leadership in trustworthy, collaborative AI for health.
Results have been widely disseminated through more than 20 peer-reviewed publications, over 40 conference presentations, and targeted communication to clinical and patient communities. Two online training programmes were delivered with EuroBloodNet, supporting knowledge transfer to clinicians and researchers. Exploitation activities focused on sustaining the federated platform beyond the project, with use cases and tools feeding into ongoing initiatives (e.g. EuroBloodNet registries, partner-led developments such as SYNTHIA and SYNTHEMA). The project also engaged with industry and public stakeholders to pave the way for sustainable uptake of federated AI in healthcare. and clinical plausibility.
By the end of the project, GenoMed4All demonstrated that federated AI approaches can be effectively applied to rare and complex diseases while respecting data protection constraints. The results provide a robust foundation for continued clinical validation, broader disease coverage, and integration into European infrastructures, reinforcing Europe’s leadership in trustworthy, collaborative AI for health.
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.
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.