Privacy-compliant health data as a service for artificial intelligence (AI) development.
The PHASE IV AI project advances the current state of data synthesis methods towards a more generalized approach to synthetic health data generation. The initiative develops metrics for testing and validation, as well as protocols that allow the generation of synthetic data without access to real-world data through multi-party computation.
The objectives of PHASE IV AI are:
- Provide improved methods and technical pipelines for the synthesis of privacy-preserving data, including different data formats such as electronic health records (EHRs) and medical images.
- Provide easy-to-use and configurable data services to enable AI developers to access larger pools of decentralized de-identified data through multi-party computation.
- Provide anonymous data on demand or from a temporary repository.
- Establish a data market facilitating data sharing and monetization, including multi-party computation.
- Integrate the data market and the data service ecosystem as a health data hub in the European Health Data Space.
- Validate the results with real-world use cases focusing on high-impact diseases, cancer types in particular.
Distributed storage and limited access to healthcare data pose a barrier to innovation, as the development of reliable AI systems requires large datasets for training and validation.
Additionally, the availability of anonymized data sets would increase the adoption of AI-powered tools in supporting health technology assessments and education. The use of secure and privacy-compliant data is key to unlocking the full potential of AI and data analytics.
Eurecat participates in the PHASE IV AI project through its Digital Health Unit, which leads the tasks on data as a service and risk and quality management, also contributing to the development of synthetic data and anonymization services. For its part, the Audiovisual Technologies Unit is in charge of the development of synthetic data and anonymization services.
The PHASE IV AI consortium is made up of 20 partners from 10 different countries.
General details
Project
PHASE IV AI – Health data anonymization and generation based on AI for the disease prediction as clinical tools for medical specialist assistance
Project reference
101095384
Programme and call for tender
Project funded by the European Union’s Horizon Europe programme under the HORIZON-HLTH-2022-IND-13-02 – Scaling up multi-party computation, data anonymisation techniques, and synthetic data generation
Related ODS