Synthetic data in healthcare: Benefits and opportunities; technological, clinical regulatory gaps & challenges; ways ahead for impact maximisation

Abstract

Synthetic data is rapidly emerging as a transformative enabler in digital health innovation, offering new pathways to unlock data access, strengthen Artificial Intelligence (AI) development and advance inclusive research and care. Realising the significant potential of synthetic data, the Healthcare Task Force of BDVA has formulated a working group with relevant expertise to author this white paper that explores how synthetic data can strategically benefit and boost innovation in eight key domains: virtual patients, data scarcity and bias mitigation, data sharing and collaboration, clinical trial innovation, AI fairness & performance, privacy-respecting research addressing ethical, legal and business barriers, system readiness and reliability and health workforce training. Drawing from a wide range of use cases and state-of-the-art assessment, the paper demonstrates how synthetic data addresses long-standing challenges in healthcare, such as data scarcity, regulatory barriers and underrepresentation, while also enabling new forms of secure, scalable and ethically aligned collaboration. The paper maps current capabilities to real-world applications and identifies persistent research and policy gaps, from limited access to representative seed data to uncertainties around legal governance, benchmarking standards and sustainable regulated infrastructure. To fully realise the potential of synthetic data, the paper proposes a coordinated set of recommendations spanning regulation, scientific and technical development, data governance and funding in the healthcare domain, many of which are further applicable in other sectors. These include establishing shared assessment benchmarks and sandboxes, developing multimodal and explainable AI models, clarifying and advancing legal frameworks and policies and investing in inclusive and privacy-enhancing technologies, as well as secure federated data and learning ecosystems. The European funding programs Horizon Europe, EU4Health and Digital Europe have a pivotal role to play in supporting synthetic data initiatives that align with the European health equity and innovation goals. Together, these actions offer a strategic blueprint for embedding synthetic data into the European digital health ecosystem and infrastructure—building more inclusive, privacy-preserving and future-ready digital health systems.

Ähnliche Arbeiten