Posters & Abstracts

Sickle cell disease (SCD) is a hereditary, multi-systemic disorder characterized by hemolytic anemia and recurrent vaso-occlusive events (VOEs), significantly impacting patients’ health. Hydroxyurea (HU), the most widely prescribed disease-modifying therapy, shows variable efficacy due to differences in drug metabolism, pharmacokinetics, and adherence. This study evaluated HU blood metabolite levels in a large European sickle cell anemia (HbSS) cohort within the Genomed4all consortium, providing insights into HU response and personalized SCD management. The aim of this poster is to analyze association between HU blood metabolite levels, laboratory indices, and acute complications (VOE, acute chest syndrome [ACS]) in HbSS patients aged <10 and >10 years.

Multi-omics have the potential to pave the way for a holistic AI-based decision support system (AI-DSS) built upongenomics, transcriptomics, cytogenetics, radiomics, deep features, and clinical parameters to assess treatmentstrategies and patient stratification. The integration of invasive -omics with routine radiomics into a common feature space has the potential to yieldrobust models for inferring the drivers of underlying biological mechanisms. Multi-omics can be employed to: I. combine multi-omic data for improving the robustness and predictive power of AI-DSS, and II. match the imaging with genomic/transcriptomic/cytogenetic markers.

A machine learning analysis was employed to predict the expression of key chromosomal alterations and the cytogenetic risk of multiple myeloma patients. The proposed machine learning analysis based on sacrum and pelvis radiomics achieved the highest performance with an AUC of 0.76±0.03 among other radiocytogenetic models.

A clustering technique was adapted to identify the bone marrow pixels and morphological operations were employed to refine the segmentation mask. The qualitative analysis performed by experienced radiologists shows promising results. The proposed segmentation pipeline allows accurate and fast annotation of the whole-body bone marrow in multiple myeloma patients, achieving an IoU of 0.79±0.05 on the available cohort with femur bone annotations.

Sickle cell disease (SCD) is a hereditary disorder characterized by the production of structurally abnormal hemoglobin S (HbS) in red blood cells (RBCs). Under low oxygen saturation, HbS polymerizes, causing RBCs to deform, leading to hemolytic anemia, recurrent vaso-occlusive episodes (VOE) and organ damage. VOE are unpredictable and result in long-term morbidity and early mortality.
RBC deformability and sickling tendency can be assessed ex vivo using oxygen gradient ektacytometry (oxygenscan). Key patient specific parameters are RBC deformability at normoxia (EImax), deformability upon deoxygenation (EImin), and pO2 at which sickling is initiated (PoS). In this study we developed two novel parameters: Slope that reflects how rapidly RBCs sickle during deoxygenation and the EI20 that is RBC deformability measured at a fixed pO2 of 20mmHg. Within GenoMed4ALL project clinical and laboratory data is integrated with oxygenscan parameters to enable early recognition of disease severity and individualize treatment options, addressing a critical need for precision medicine in SCD.
The aim is to explore how 2 novel parameters (Slope, EI20) perform compared to key oxygenscan parameters (EImin, EImax, PoS) in a multi-national cohort study in regard to correlations with laboratory markers of SCD severity.

Recent advancements in genome characterization have transformed the study of myelodysplastic syndromes (MDS). Accordingly, there has been a shift from traditional classification and prognostication methods, which relied mainly on morphological and clinical data, to next-generation systems that incorporate genomic features. However, genetic abnormalities account for only part of the overall risk related to survival, disease progression, and individual response to hypomethylating agents (HMA), indicating that a significant portion of these risks is still tied to clinical and non-mutational factors. Increasing evidence suggests that transcriptomics, immune dysfunctions, and high-dimensional tumor morphology data extracted by Artificial Intelligence (AI) may play a crucial role in predicting clinical outcomes in human cancers, thereby improving the implementation of personalized medicine programs.
In this scenario, we developed MEGAERA, an innovative, deep learning-based framework for multimodal analysis of hematological malignancies. MEGAERA integrates clinical, multi-omics, and histopathological data, using specific strategies to ensure full clinical explainability and interpretability of predictions. This study was conducted by the GenoMed4All and Synthema EU consortia, with MDS included as use case, to improve personalized predictions of patient outcomes.

In hematology, leveraging real-world multimodal data at large scale is crucial for developing personalized medicine to address unmet clinical needs, particularly for rare diseases. Generative AI in healthcare shows great promise by generating multimodal synthetic data (SD) to improve patients’ diagnosis and prognosis while accelerating clinical research (PMID: 34131324). The challenges in generating SD include accessing complete real-world datasets for model training, maintaining intrinsic relationships among different data layers, and ensuring clinical accuracy and privacy protection.
This project conducted by GenoMed4All and Synthema consortia, aimed to: 1) implement an innovative approach for generating high-fidelity multimodal SD from patients with myeloid neoplasms (MN); 2) develop a comprehensive multimodal Synthetic Validation Framework (SVF) to assess the SD clinical and statistical fidelity and privacy preservation; 3) verify the SD technology capability to accelerate research and enhance predictive models through multimodal data integration.

Personalized medicine in hematology requires extensive real-world and comprehensive data, including clinical and genomic information. However, integrating, processing and managing such complex data layers in large populations presents significant challenges. Development of patient-tailored models by Artificial Intelligence (AI), known as Digital Twins (DT) offers a novel approach to precision medicine. DT are virtual representations of patients created from multimodal information that can be used to improve diagnosis, prognosis and treatment outcome, improving clinical decision-making. This project aims to advance research by using AI to develop a DT platform for personalized medicine in hematology, with myelodysplastic syndromes (MDS) as case study. MDS are hematological diseases with high clinical and genomic heterogeneity, presenting a challenging scenario for new technologies implementation.

Most oncological and non-oncological hematological conditions fall under the category of rare diseases. Rare diseases present unique challenges due to the limited availability of data, which impacts diagnostic rates and the generation of clinical evidence. Overall, they constitute a public health concern, highlighting the urgent need to develop new methods for improving data accessibility. In this context, Federated Learning (FL) is a Machine Learning approach that allows multiple centers to collaborate on complex research questions without the need to centralize or share data.
This project was conducted by the Genomed4all and Synthema consortia with the goal of developing an innovative FL platform for rare hematological diseases. This platform enables the development of novel Artificial Intelligence (AI) models for personalized medicine without data sharing, to be implemented in the referral centers of EuroBloodNET, the European Reference Network for rare hematological diseases. The aims of the project were: 1) to develop robust federated models for personalized prediction using multicentric, real-world datasets; 2) to protect patients’ privacy; and 3) to enhance collaboration between institutions while avoiding the creation of centralized data repositories.

Bone marrow (BM) cytology and histopathology images are crucial for diagnosing and prognosticating myeloid neoplasms (MNs), but their high-dimensional data are underused. Artificial Intelligence (AI) applied to tumor morphology (digital pathology, DP) has improved the use of tumor biopsies’ data for various types of malignancies, accurately detecting patterns and converting complex image information into numerical features. Here, we explored the potential of AI-based DP to improve personalized medicine in MNs which are characterized by high heterogeneity and a significant proportion of patients with unmet clinical needs.
This project was conducted by the GenoMed4All and Synthema consortia, to build AI-based features extraction tools from BM histopathological and cytological Whole Slide Images (WSI). High-dimensional data were used to 1) assess diagnostic accuracy in MN patients; 2) elucidate the association between morphologic features, clinical variables and molecular genetics, and 3) create an innovative tool for personalized risk assessments integrating morphological features with clinical and genomic information.