AI Centre and deepc Launch FLIP, an Open-Source Platform to Enable Health AI Innovation at Scale, in Partnership with OneLondon and Flower Labs

London & Munich — February 26, 2026 - The AI Centre for Value-Based Healthcare at King’s College London and Guy’s and St Thomas’ NHS Foundation Trust, together with strategic partner deepc, today announced the launch of FLIP, a fully open-source federated learning interoperability platform designed to support large-scale, collaborative development of healthcare AI while ensuring patient data remains local and under institutional control. Developed within the NHS ecosystem in collaboration with OneLondon and Flower Labs, FLIP is designed to enable secure, multi-institutional AI collaboration across health systems.

Developed, governed, and maintained within the NHS, FLIP addresses a longstanding challenge in healthcare AI: the tension between the need for large, diverse data sets to train clinically robust models and the ethical, regulatory, and societal imperative to protect sensitive patient data. As modern AI increasingly relies on foundation models and multimodal learning approaches, this challenge has become a limiting factor for progress across clinical research and innovation.

FLIP enables AI models to be trained across one or multiple institutions while data stays within secure local environments. By allowing models to learn from a wider range of data, it has the potential to improve patient care by increasing the accuracy of diagnosis, supporting earlier detection of disease, and helping bring new innovations into care more quickly - all while maintaining high standards of privacy and data protection.

“Healthcare AI has reached a point where meaningful progress depends on collaboration at scale,” said Prof. Sebastien Ourselin, Head of the School of Biomedical Engineering and Imaging Sciences at King’s College London. “With FLIP, we are creating an open, NHS-led resource that allows clinicians and researchers to safely harness data across institutions, accelerate innovation, and position the NHS as a global leader in responsible AI development.”

Unlike centralized, vendor-controlled AI research platforms, FLIP is designed to give participating organizations full control over their data, approvals, and ethics processes. Institutions can deploy FLIP locally to develop AI models using only their own data, while federated collaboration across sites remains an optional extension rather than a requirement. This approach reduces duplication of effort, mitigates vendor lock-in risk, and reinforces transparency around data ownership and reuse.

The initiative reflects a long-term strategic collaboration between the AI Centre for Value-Based Healthcare and deepc to build open infrastructure to accelerate AI innovation as well as its clinical use. In this partnership, the AI Centre provides clinical leadership and research excellence, Guy’s and St Thomas’ NHS Foundation Trust serves as steward and long-term operator of the platform at NHS scale, and deepc contributes infrastructure expertise and experience in secure, vendor-neutral AI lifecycle operations.

“FLIP provides the foundational infrastructure needed for the next generation of healthcare AI,” said Franz Pfister, CEO of deepc. “As foundation models and multimodal approaches become central to medical innovation, open and interoperable platforms are essential to ensure innovation translates into earlier diagnoses, more personalized treatment decisions, and better patient outcomes.”

The platform has benefited from an open-source collaboration with Flower Labs to implement their industry-standard framework for enterprise-scale federated learning within FLIP. “Working with the FLIP team has been a deep and meaningful collaboration, and we share their vision for making federated learning practical for healthcare research at scale, focusing on what matters most: building better models that can translate into improved patient outcomes,” said Prof. Nicholas Lane, CSO of Flower Labs.

The platform has also benefited from contributions by NVIDIA’s NVFlare teams and cloud infrastructure support from AWS, enabling scalable orchestration across distributed environments.

Initial programs running on FLIP are demonstrating federated AI capabilities across diverse clinical applications, including radiology, multimodal inflammatory diseases, and the development of digital biomarkers. In partnership with St. John’s Institute of Dermatology, researchers are developing digital biomarkers for inflammatory skin disease using multimodal data. A further program is building a biomarker for muscle mass and sarcopenia to inform cancer treatment decisions and improve outcomes prediction in critically ill patients. These projects combine imaging with structured and unstructured clinical data, illustrating how federated infrastructure can enable more comprehensive, real-world model development across institutions.

Released under an Apache 2.0 open-source license and maintained by the AI Centre for Value-Based Healthcare, FLIP is now available for research on multi-modal data, reflecting real-world NHS requirements for information governance and cybersecurity from its inception. Healthcare providers, researchers, and innovators worldwide are invited to adopt, contribute to, and build upon the platform.