Pre-prints

Rare haematological diseases (RHD) pose significant clinical challenges due to their heterogeneity, limited patient populations, and fragmented datasets. To overcome these limitations, improve access to, and use of real-world multimodal data for scientific and clinical purposes, the GenoMed4All Consortium developed an open-source Federated Learning (FL) platform. This platform enables collaborative, privacy-preserving AI model training without the need to centralize sensitive patient information.

The FL platform was deployed within EuroBloodNet, the European Reference Network for RHD, across multiple use cases, including myelodysplastic syndromes (MDS), acute myeloid leukemia (AML), chronic myelomonocytic leukemia (CMML), and multiple myeloma (MM). Multimodal datasets (including clinical, genomic information together with histopathological and radiological extracted features) were utilized. Predictive models (DeepSurv and SAVAE) and generative Artificial intelligence (AI) algorithms (CTGAN, Bayesian Networks, and VAE-BGM) were trained using a federated approach. A dedicated data harmonization pipeline based on the FHIR standard ensured consistency across participating centers.

Federated models achieved performance comparable to centralized approaches, with highest benefit for institutions with smaller datasets. The platform enabled integration of multimodal data demonstrating flexibility across diverse data types and clinical endpoints. The inclusion of multimodal information improved predictive accuracy over currently available prognostic schemes. Generative models successfully created synthetic datasets that preserved both clinical and statistical fidelity while ensuring patient privacy; this allows extraction of insights from real-world data that can be used beyond the boundaries of FL, as a source for accelerating the conduction of clinical trials. A preliminary implementation within the EuroBloodNet clinical network demonstrated feasibility for broader scale-up.

This study validates FL as a robust, privacy-compliant approach to enable AI-driven precision medicine in RHD. The platform facilitates real-world data integration and model scalability, providing a foundation for multicenter collaboration, regulatory-grade evidence generation, and innovative trial designs in rare diseases.

Onco-hematological studies are increasingly adopting statistical mixture models to support the advancement of the genetically-driven classification systems for blood cancer. Targeting enhanced patients stratification based on the sole role of molecular biology attracted much interest and contributes to bring personalized medicine closer to reality. In particular, Dirichlet processes have become the preferred method to approach the fit of mixture models. Usually, the multinomial distribution is at the core of such models. However, despite their advanced statistical formalism, these processes are not to be considered black box techniques and a better understanding of their working mechanisms enables to improve their employment and explainability. Focused on genomic data in Acute Myeloid Leukemia, this work unfolds the driving factors and rationale of the Hierarchical Dirichlet Mixture Models of multinomials on binary data. In addition, we introduce a novel approach to perform accurate patients clustering via multinomials based on statistical considerations. The newly reported adoption of the Multivariate Fisher’s Non-Central Hypergeometric distributions reveals promising results and outperformed the multinomials in clustering both on simulated and real onco-hematological data.