As SYNTHEMA nears its conclusion, we’re meeting in Padua to present and discuss the project’s work and results, from rare-disease data and synthetic cohorts to federated research, privacy and responsible health data use. Full agenda attached 🗓️ 3 Nov 2026 👉 Register: docs.google.com/forms/d/e/1F...

Rare disease data is scarce. Fragmentation makes it even harder to use. Vincent malcor deydier de Pierrefeu from AP-HP explains why connecting data across European hospitals can provide a broader view of rare haematological conditions. synthema.eu

Subscribe to the SYNTHEMA newsletter to receive key project updates and announcements about important activities, all in one place. Clear, relevant, and focused on what matters. Choose the format: 📩 by email: f981d420.sibforms.com/serve/MUIEAH... 💼 on LinkedIn: linkedin.com/newsletters/...

“We designed in data protection considerations at the very beginning of the project, from day zero.” Nathan Lea from i~HD explains why privacy, ethics and GDPR compliance were built into SYNTHEMA from the start, especially when working with small rare disease cohorts. youtu.be/DCWf6Ig4O6k

Responsible AI in Healthcare: Privacy, Ethics and GDPR in SYNTHEMA

YouTube video by SYNTHEMA

youtu.be

Synthetic data is only useful if it can be trusted, validated and reused. In the latest SYNTHEMA: The Final Stretch feature, Vicomtech reflects on the technical advances developed in the project and how they could extend beyond rare haematology. Read more: synthema.eu/2026/09/16/p...

Synthetic data can improve data access, AI development and privacy-preserving research in healthcare. The BDVA white paper Synthetic Data in Healthcare, co-edited by SYNTHEMA’s Sofia Tsekeridou (Netcompany), looks at the opportunities, gaps and next steps. 📄 zenodo.org/records/2279...

“Sickle cell disease presents every challenge in rare diseases.” In the next SYNTHEMA | The Final Stretch interview, Maria del Mar Mañú Pereira from Vall d’Hebron explains why Sickle Cell Disease was selected as a clinical use case. Watch the interview to hear more: youtu.be/Kcj1kAw97rU

How is SYNTHEMA protecting patient confidentiality while ensuring synthetic data remains suitable for scientific use? Rudolf Mayer and Daniela Martinez-Duarte from SBA Research explain the approach.

Save the date: 3 November 2026. Our partner UNIPD is organising a SYNTHEMA Symposium in Padua on real-world data, federated learning, synthetic data and data-driven medicine. 📍 Palazzo della Salute – MUSME More details soon

Access our complete four-part training series on synthetic data in rare haematology. Technical and clinical experts share hands-on approaches covering EU AI Act compliance, OMOP standardisation, and clinical use cases in SCD and AML. 👉 Free access: www.youtube.com/playlist?lis...

Subscribe to the SYNTHEMA newsletter to receive key project updates and announcements about important activities, all in one place. Clear, relevant, and focused on what matters. Choose the format: 📩 by email: f981d420.sibforms.com/serve/MUIEAH... 💼 on LinkedIn: www.linkedin.com/newsletters/...

How does synthetic data perform in actual clinical practice? Session 4 examines real-world applications in haematology, showing how synthetic cohorts predict kidney injury in Sickle Cell Disease and replicate survival curves in Acute Myeloid Leukaemia. 👉 youtu.be/cGzTBoTFmD4

Session 4: Opportunities of Synthetic Data Generation in Rare Haematological Diseases

YouTube video by SYNTHEMA

youtu.be

SYNTHEMA deliverable D1.2 defines how SCD and AML data are mapped to the OMOP Common Data Model, creating a common structure for data integration, synthetic data generation and federated AI training. 👉 synthema.eu/public-deliv...

Data fragmentation halts collaborative medical research before it even starts.Session 3 explores how mapping clinical records to the OMOP common data model and leveraging 3D image synthesis unlock true interoperability across multi-centre networks. 👉Watch today or keep it saved youtu.be/Ep4juTDnLb4

Session 3: Data Quality, Standardisation, Data Generation, Anonymization and Interoperability

YouTube video by SYNTHEMA

youtu.be

SYNTHEMA deliverable D1.3 documents how multimodal data for SCD and AML were collected, pseudonymised, harmonised and mapped to OMOP, creating GDPR-compliant datasets for synthetic data generation and federated AI validation. 👉 synthema.eu/public-deliv...

Building AI for digital health? Compliance cannot be an afterthought. Session 2 breaks down EU AI Act high-risk classifications, GDPR requirements, and how tools like Differential Privacy keep patient records safe. 👉Watch now or save for later: www.youtube.com/watch?v=RZbz...

Session 2: Regulatory on Medical Devices, AI Act, Privacy-Preserving and Ethical Considerations

YouTube video by SYNTHEMA

youtube.com

How should source and synthetic health data be protected, managed and reused? SYNTHEMA deliverable D5.4 updates our Data Management Plan, covering FAIR principles, security, privacy risks, ethics, interoperability and sustainability. 👉 synthema.eu/public-deliv...

How do you train healthcare AI when patient data cannot leave local hospital servers? In this session we demonstrate how federated learning and synthetic data generation create secure, privacy-compliant pipelines for rare disease research. 👉 Watch now: www.youtube.com/watch?v=S9-S...

Session 1: SYNTHEMA – Infrastructure for SDG in ERN-EuroBloodNet

YouTube video by SYNTHEMA

youtube.com

Cancer research often works with limited data, while many synthetic data models need thousands of samples. This paper explores how transfer learning and meta-learning can improve synthetic tabular data generation in low-data medical scenarios. Access it via SYNTHEMA: synthema.eu/publications/

🔬How do we safely validate synthetic data for clinical research? Our new deliverable (D4.1) outlines a rigorous three-tiered framework—testing VAEs, GANs, and diffusion models on leukaemia and sickle cell disease datasets. 👉Access the full report: synthema.eu/public-deliv...

In the latest issue of our newsletter, we have compiled the outcomes and resources of our complete training programme on synthetic data in haematology into one accessible guide. Access the full material and webinar recordings here: 👉 zenodo.org/records/2139...

Cybersecurity risk assessment gets harder when assets, threats and consequences are deeply connected. This paper presents an automated, knowledge-based approach for cyber-physical systems, implemented through the open-source Spyderisk project. 👉 synthema.eu/publications/

Healthcare data cannot always be centralised, but treatment effects still need to be estimated. A paper by Alejandro Almodovar, Juan Parras and Santiago Zazo explores federated learning for causal inference using deep generative disentangled models. Access the paper: synthema.eu/publications/

What does it really mean for synthetic data to be private? This systematic review digs into 105 studies to map how privacy in SDG is defined, evaluated & applied, spotlighting differential privacy, GANs & healthcare use. 👉Available at: synthema.eu/publications/

#SYNTHEMA is building the foundations for a future where synthetic, privacy-preserving data supports progress in rare diseases. Beyond its two use cases, its flexible design can benefit other rare and underrepresented conditions. More 👉 synthema.eu

In 1 hour, we are starting the final session of the SYNTHEMA and @erneurobloodnet.bsky.social training programme. Today’s session will explore how synthetic data can support research in Sickle Cell Disease and Acute Myeloid Leukaemia. 👉 Register, it’s free: synthema.eu/training/

New publication from the SYNTHEMA project 👇 Researchers developed a two-stage framework to assess privacy risks in Federated Learning and generative AI, showing when client updates remain detectable and can be linked to private data. Access the paper: synthema.eu/publications/

In 1 hour, we are starting the third SYNTHEMA and @erneurobloodnet.bsky.social session. Today’s discussion will focus on interoperability, synthetic data and how health data can be standardised, shared and reused across systems. 👉 Register, it’s free: synthema.eu/training/

Interested in synthetic data and AI-powered breakthroughs in hematology? Visit SYNTHEMA’s publications section to explore the latest advancements by our team in data privacy, federated learning, AI for rare blood diseases, and more. 👉Start reading: synthema.eu/publications #SYNTHEMA #SyntheticData

Starting in 1 hour! Today’s SYNTHEMA and @erneurobloodnet.bsky.social session will focus on the regulatory and ethical context for AI in healthcare, including MDR, the EU AI Act and privacy-preserving federated learning. 👉 Register, it’s free: synthema.eu/training/