Three SYNTHIA presentation at the 67th American Society of Hematology Annual Meeting & Exposition (ASH2025), taking place December 6–9, 2025, in Orlando, Florida.

SYNTHIA Partner Eleonora Iascone from Humanitas Research Hospital will present the abstract (abs25-11629) “SAFE: A multimodal, scalable and clinically-oriented comprehensive framework for synthetic data validation in hematology”.

Date/time/room: Saturday, December 6 / 05:15 PM to 05:30 PM EST / Room: Hyatt - Regency Ballroom R.

  • Link to the abstract > 

  • About the abstract: The emergence of Generative AI is transforming the use of synthetic data in healthcare, enabling applications such as digital twins and synthetic control arms for clinical research. However, the adoption of these innovations has been slowed by the absence of robust, standardized validation frameworks. To address this challenge, the study introduces SAFE (Synthetic vAlidation FramEwork) — a comprehensive, multimodal tool designed to evaluate synthetic data based on statistical fidelity, clinical utility, and privacy preservation. Developed within the SYNTHEMA and SYNTHIA consortia, SAFE has been validated using the extensive TITAN cohort of over 20,000 cases in Myeloid Neoplasms (MN), including clinical, genomic, transcriptomic, and histopathological data.SAFE integrates clinically driven analyses across multiple data modalities, ensuring that synthetic data are both accurate and useful for research while safeguarding patient privacy. Its demonstrated performance in replicating disease patterns, genomic and transcriptomic profiles, and prognostic outcomes marks an important step toward the regulatory and clinical validation of synthetic data in hematology.

SYNTHIA Partner Mattia Delleani from TRAIN will present the abstract (abs25-11508) “AI-based, secure and privacy-preserving synthetic data generation platform in transfusiondependent β-thalassemia applied to the Webthal® dataset”

Date/time/room: Sunday, December 7 / 06:00 PM - 08:00 PM EST / Room: OCCC - West Halls B3-B4.

  • Link to the abstract >
  • About the abstract: While AI technologies for synthetic data (SD) generation are well-developed, their direct application in clinical settings remains challenging. Key issues include privacy and security concerns, which necessitate the use of closed, third-party models with sensitive patient data. Furthermore, many generative models lack adequate clinical validation, often failing to understand and replicate the complex correlations between clinical variables. These barriers are particularly acute in rare diseases like βthalassemia, where data is already scarce. Our work addresses these specific challenges by implementing a secure, transparent platform to generate a high-fidelity synthetic cohort of patients with transfusiondependent β-thalassemia (TDT). This work aims to implement an AI-based SD generation platform within the locally secured, privacy-preserving environment of the Webthal® dataset; to demonstrate its secure integration and efficacy in generating high-quality synthetic clinical data, suitable for clinical research, creation of digital twins and synthetic control arms for clinical trials.

SYNTHIA Partner Gianluca Asti from Humanitas Research Hospital will present the abstract (abs25-11506) “Development and validation of synthetic data generation over a federated learning computing framework to accelerate innovation and boost personalized medicine in hematological diseases”

Date/time/room: Sunday, December 7 / 06:00 PM - 08:00 PM EST / Room: OCCC - West Halls B3-B4.

  • Link to the abstract >
  • About the abstract: This work explores how combining synthetic data generation with federated learning can overcome key barriers in rare hematological disease research, where data availability and sharing are often limited. By enabling institutions to collaboratively train generative models without exchanging sensitive patient information, the study demonstrates a privacy-preserving approach to producing high-fidelity synthetic datasets. The abstract outlines the methods, validation strategy, and results achieved within the Synthema and SYNTHIA consortia, highlighting the potential of this framework to support scalable, secure, and clinically meaningful research.

About the American Society of Hematology

The American Society of Hematology (ASH) is the world’s largest professional society of clinicians and scientists dedicated to conquering blood diseases. Since its founding in 1958, ASH has led the development of hematology as a discipline by promoting research, patient care, education, training, and advocacy in the field.

The ASH2025 abstracts were made available online since November 3, 2025 - please take note of the ASH embargo regulation