A sustainable platform for federated health data access, AI innovation, and regulatory acceptance in alignment with the European Health Data Space principles
Abstract
The IDERHA ( I ntegration of Heterogeneous D ata and E vidence towards R egulatory and H TA A cceptance) project aims to enhance medical research by establishing one of Europe’s first pan-European, disease-agnostic health data spaces. Aligned with the European Health Data Space (EHDS) principles, IDERHA addresses critical challenges in data quality, standardization, and governance, ensuring compliance with GDPR, the AI Act, and emerging EHDS regulations. Its ambition is to enable secure, federated access and analysis of health data, fostering data-driven collaboration and innovation in healthcare. IDERHA’s technical infrastructure employs a ‘privacy-by-design’ approach, leveraging federated analytics and learning to maintain data sovereignty and reduce privacy risks. The project focuses on lung cancer as a high-impact use case, utilizing AI and machine learning to improve early detection, diagnosis, and personalized care. It also aims to develop policy recommendations for the acceptance of real-world evidence (RWE) for regulatory decision-making through multi-stakeholder engagement and public consultations. However, challenges remain, including semantic interoperability, and scaling federated AI methods across borders. IDERHA’s modular, standards-based architecture and emphasis on ethical, legal, and FAIR compliance provide a robust framework for addressing these issues. By collaborating with other initiatives in the health data domain to drive compatibility, IDERHA seeks to…
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.