Imagine trying to solve a puzzle where the pieces are scattered across different hospitals and countries, but you aren't allowed to move the pieces because they are too sensitive. This project builds a digital 'viewing room' where researchers can analyze the data without ever actually taking it away from the hospital. It helps doctors find genetic markers to predict how a child will recover after a kidney or liver transplant.
Medical research for rare pediatric transplants is stalled because sensitive genomic data is fragmented across different countries and locked behind strict privacy laws.
A Zero-Trust federated data ecosystem and a Common Data Model based on OMOP standards for secure, cross-border health data analysis.
If you are a medical AI software developer dealing with strict GDPR rules for sensitive pediatric data — this project developed a Zero-Trust architecture that allows AI workflows to run at the data-holder's site. This means you can train models on 19 partners' data without moving the files, reducing legal risk.
If you are a precision medicine biotech firm dealing with fragmented genomic datasets for rare diseases — this project developed a common data model aligned with OMOP standards. This allows you to integrate multi-source genomic and methylomic data to identify biomarkers for transplant outcomes.
If you are a PET provider dealing with the requirements of the European Health Data Space (EHDS) — this project developed EHDS capsules and secure processing environments. This provides a blueprint for compliant, cross-border health data reuse.
Based on available project data, no specific pricing or cost information is provided as the EU contribution is not listed.
The project is designed for a multicentric pilot across 9 countries and 19 partners, indicating a design intended for European-scale deployment within the European Reference Network.
Based on available project data, specific licensing terms are not mentioned, though the project focuses on EHDS and GDPR compliance for data reuse.
It implements a Zero-Trust architecture and is fully compliant with GDPR, the Data Governance Act, the AI Act, and emerging EHDS requirements.
The project uses a Common Data Model (CDM) mapping clinical variables to the OMOP standard to ensure interoperability across multi-source platforms.
The consortium is well-balanced for a translation project, featuring 19 partners across 9 countries. With a 26% industry ratio (5 companies, including 3 SMEs), there is a clear bridge between the 7 universities and 5 research centers and the commercial market. The inclusion of HPC centers and legal experts ensures the technical and regulatory feasibility of the product.
Contact the Universidad Politecnica de Madrid
Contact us to connect with the PROTECT-CHILD consortium for pilot integration.
