Imagine you want to study a rare disease, but the patient records are locked in different hospitals across Europe for privacy reasons. Instead of moving the sensitive data to one place, this system sends the AI 'brain' to each hospital to learn from the data locally. It's like sending a chef to different kitchens to learn recipes without the kitchens ever having to share their secret ingredients.
Healthcare research is stalled because patient data cannot be moved across borders or institutions due to strict GDPR privacy laws. This limits AI training to small, single-center datasets, slowing down the discovery of treatments for rare diseases.
A distributed AI platform that fuses PADME and Vantage6 technologies. It includes 'BETTER Stations' for local data access and a central coordination node for federated learning.
If you are a drug discovery firm dealing with fragmented genomic data across different countries — this project developed a distributed analytics platform that allows AI to train on data where it resides. This enables faster identification of risk factors for rare diseases without moving sensitive patient files.
If you are an AI diagnostic software provider dealing with GDPR restrictions on data centralization — this project developed a federated learning ecosystem that ensures compliance. This allows you to improve diagnosis accuracy and speed by accessing larger, multi-source datasets.
If you are a hospital network dealing with high clinical investigation times — this project developed a secure data fusion strategy that integrates clinical and genomics data. This can lead to better health outcomes by reducing hospitalization and investigation time.
Based on available project data, specific pricing or commercial costs are not mentioned; the project is funded by an EU contribution of EUR 9,553,530.
The project is designed for industrial scale, involving 16 partners across 9 countries and fusing two mature implementations, PADME and Vantage6, to handle multi-source health data.
Based on available project data, specific licensing terms are not provided, though the project establishes legal and ethical data governance for cross-border processing.
The platform uses a distributed analytics approach where data remains in its original location, ensuring full compliance with GDPR privacy guidelines through pseudonymisation.
The project period runs from 2023-12-01 to 2027-05-31, with core components and local stations already deployed and tested.
It uses a common data schema and FAIRification efforts to ensure interoperability, deploying 'BETTER Stations' for secure local data access.
The consortium is well-balanced for a technical-medical project, consisting of 16 partners from 9 countries. With a 19% industry ratio (3 SMEs), the project is heavily supported by 7 universities and 5 research institutions, indicating a strong focus on scientific validation before commercialization. The leadership by an Italian SME (DATRIX SPA) suggests a drive toward practical, deployable software solutions.
Contact DATRIX SPA in Italy for partnership opportunities regarding the BETTER platform.
Contact us to identify potential licensing opportunities for federated learning in healthcare.
