Imagine wanting to study a rare disease but not having enough patients in one hospital. Instead of moving sensitive records, this system lets researchers send their questions to the data, rather than bringing the data to them. It also creates 'fake' but realistic patient data that looks and acts like the real thing, so companies can build tools without ever seeing a real child's private information.
Accessing pediatric health data for research is slow and risky due to strict privacy laws and different national interpretations of GDPR. This prevents SMEs and pharma companies from getting the data they need to develop life-saving treatments.
A Pediatric Health Data Space featuring a permission management system and tools for generating synthetic, anonymized datasets.
If you are a drug development firm dealing with small patient cohorts for rare pediatric diseases — this project developed a Pediatric Health Data Space that allows you to validate clinical trial feasibility across 6 countries without compromising patient privacy.
If you are an AI Health Software SME dealing with the lack of high-quality training data for sepsis prediction — this project developed synthetic data generation capabilities that provide shareable, anonymized datasets for algorithm development.
If you are a hospital network operator dealing with complex GDPR interpretations across borders — this project developed a permission management system and governance tools to enable secure cardiology benchmarking between institutions.
Based on available project data, no specific pricing or cost information is provided as this is a Horizon-RIA research project.
Yes, the project uses three clinical use cases as a proof of principle with the explicit potential to scale across other clinical areas and hospital networks.
Based on available project data, specific IP and licensing terms are not listed, though it establishes a structured contractual and governance framework for collaboration.
It provides a decentralized ecosystem and governance tools that allow data controllers to collaborate without losing control over GDPR, national legislation, or internal policies.
The project utilizes the OMOP CDM (Common Data Model) to standardize data and provides a permission management system for access control.
The consortium is heavily weighted toward commercial application, with a 46% industry ratio including 6 industry partners and 4 SMEs. This mix of 13 partners across 6 countries suggests a strong focus on market viability and cross-border interoperability, balancing academic research (2 universities, 4 research centers) with practical industrial deployment.
Contact HUS-YHTYMA in Finland
Contact us to explore licensing for synthetic health data generation tools.
