11 Oct 2024
The European research project "Federated Secure Computing" presents a new approach that allows patient data from different institutions to be analyzed securely and anonymously.
The Federated Secure Computing research project, funded by the Stifterverband, evaluates the data of patients with cancer in the European Health Data Space across national borders. Thanks to the modern cryptographic method "Secure Multiparty Computation", data no longer needs to be exchanged. In addition to LMU scientists, the European team includes researchers from the Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Italy, and cryptography experts from Cybernetica, Estonia.
In a new pilot study, the researchers have now presented and tested an approach that overcomes the technical and legal challenges in the demanding context of clinical research on cancer patients while complying with strict European regulations on the protection of patient privacy and data protection. The results of the study were recently published in the journal npj Digital Medicine.
Hendrik Ballhausen, the initiator of Federated Secure Computing at LMU, explains how several partners form a secure computer network: "Neither party has access to the data of the other. In an end-to-end encrypted network, calculations can still be carried out jointly. The network is constructed in such a way that only the result of the joint calculation is known in a mathematically verifiable way, but never the data of the individual patients."
The health data of patients at the LMU Clinic and the Policlinico Universitario Fondazione Agostino Gemelli in Rome served as the data set. Specifically, the procedure benefits patients with adrenal gland tumors who have to undergo radiotherapy. “Through joint evaluation, we can better understand the risk factors and develop a targeted therapy with few side effects, which increases the survival and quality of life of patients,” summarizes Professor Stefanie Corradini, Deputy Clinical Director of Radiotherapy at the LMU Klinikum.
“Our clinics offer state-of-the-art magnetic resonance-guided radiotherapy,” adds Luca Boldrini, physician at the Advanced Radiation Therapy Center ‘Gemelli ART’. “We are just starting to see data. By joining forces in this innovative and not yet widespread radiotherapy technology, our two institutions are collecting data twice as fast as would be possible without the cooperation agreement.”
The team has built an architecture around Sharemind MPC, the industrial solution for secure computing from Estonian company Cybernetica. “Secure multiparty computing can greatly improve privacy protection and interoperability in the healthcare sector,” says Dan Bogdanov, Chief Scientific Officer at Cybernetica. “If you need strong end-to-end security and need to meet guidelines and compliance in a provable way, then cryptography provides the right tool.”
Close cooperation with Data Use and Access Committees and the data protection officers was an important part of the project. It was supported by a specialist law firm and secured by a cooperation agreement between the three partner institutions, ethics votes and written consent from patients. “In the future, we want and need to make better and easier use of health data for research. This is precisely the aim of the Bavarian Cloud for Health Research as part of the Highmed Agenda Bayern,” says Professor Markus Lerch, Medical Director of LMU University Hospital, supporting the project.
The team is already working on further use cases. Hendrik Ballhausen encourages industry, science and the public sector: “We are happy to provide advice if anyone wants to transfer our approach to other areas. Our project stands for modern European data protection, which makes data more valuable and does not slow down cooperation, but facilitates and accelerates it.”
Hendrik Ballhausen et al.: Privacy-friendly evaluation of patient data with secure multiparty computation in a European pilot study. npj Digital Medicine 2024