Fraunhofer Institute for Toxicology and Experimental Medicine
Fraunhofer Institute for Toxicology and Experimental Medicine

Project "PrivacyUmbrella"

PrivacyUmbrella: Anonymizing medical data

© stock.adobe.com, Rumi X
For data analysis in the context of personalized medicine, it is important to protect the patient data while also ensuring that the data being shared is sufficiently informative.

Health data is becoming more detailed all the time and is accessible to many parties. However, this means it is also vulnerable to attacks that breach the privacy of individual patients. Anonymization processes can protect patient privacy by ensuring it is no longer possible to identify individuals in data sets. However, protecting data is not the only challenge here; it is also important to ensure that the data being shared is sufficiently informative for data analysis processes in the context of personalized medicine — and to enable machine learning on a large scale.

In the PrivacyUmbrella project, Fraunhofer ITEM scientists are collaborating with the university hospitals in Frankfurt and Mainz and MCS Data Labs GmbH with the goal of achieving more reliable anonymization using a combination of different established techniques, while also maximizing usability for data analysis at the same time. The project is being financed by the German Federal Ministry of Education and Research (BMBF) and through NextGenerationEU funding.

PrivacyUmbrella covers the following concepts:

Mobile health

The concept of smart healthcare — and thus the idea of continuously monitoring the health of individuals — has become an important part of modern life for many people. The new anonymization processes ensure that medical data is usable for analyses and give patients the option of willingly sharing their data via mobile devices for the purposes of medical research.

Standardized formats for medical data

The researchers are also addressing the lack of standardization for anonymization applications by establishing connections with data integration initiatives that cover data formats such as Fast Healthcare Interoperability Resources (FHIR), which is supported by Health Level Seven International (HL7) with an open CC0 license.

Data usability

When determining the level of generalization for identifiable information, it is important to find a balance between data protection and data usability. However, the search for a suitable level of generalization for identifying information in the data is an inherently difficult task. This complexity is due to the development of hierarchical generalization trees, which results in a large search space that needs to cover the optimal combinations of generalized identifiers across different trees with different degrees of generalization.

Federated learning and data protection metrics

Formal data protection metrics play a major role in assessing and evaluating how effective technologies are in reducing data protection risks. Differential privacy is a mathematical framework that makes it possible to guarantee the protection of privacy in a system and also to quantify its level of privacy. The researchers are using the federated learning framework Flower (Das, P. P. et al., 2023: DOI 10.1007/978-3-031-49187-0_2) to run the system on the device, which reduces bandwidth, energy use and costs.

The consortium

This interdisciplinary project consortium, led by Fraunhofer ITEM, has many years’ experience relating to the secure evaluation of medical data in compliance with data protection regulations. Here is an overview of the relevant preliminary work, as well as the infrastructure required for the secure storage and evaluation of personal data.

Expand all Close all

Preliminary work at Fraunhofer ITEM

  • Lena Wiese, Tim Waage and Michael Brenner. CloudDBGuard: A Framework for encrypted data storage in NoSQL Wide Column Stores. Data and Knowledge Engineering. Elsevier, 2020.
  • Ferdinand Bollwein and Lena Wiese. Keeping Secrets by Separation of Duties while Minimizing the Amount of Cloud Servers. Transactions on Large-scale Data and Knowledge-Centered Systems. Springer, 2018
  • Ferdinand Bollwein and Lena Wiese. On the Hardness of Separation of Duties Problems for Cloud Databases. TrustBus. Springer, 2018.
  • Ferdinand Bollwein, Lena Wiese. Closeness Constraints for Separation of Duties in Cloud Databases as an Optimization Problem. BICOD 2017: 133-145. Springer, 2017. 

Preliminary work at the University Medical Center Mainz

  • MIRACUM: This project brings together ten university hospitals, two universities and one industry partner from seven German states.
  • Mainzelliste: Web-based service for pseudonymization, fiduciary storage of identity data and record linkage.
  • Riegel J, Ben Amor M, Brenner T, Drepper J, Franke M, Grün M, Hamacher K, Hund H, Knopp C, Kussel T, Lemmer M, Parciak M, Rahm E, Rohde F, Sax U, Schepers J, Sehili Z, Suhr M, Panholzer T, Lablans M. Chancen von Open-Source-Software am Beispiel der Pseudonymisierungslösung "Mainzelliste". 2021 doi: 10.3205/20gmds204
  • Lablans, M., Borg, A., Ückert, F. A RESTful interface to pseudonymization services in modern web applications. BMC medical informatics and decision making. 2015; 15(1), 1-10.

Preliminary work at University Hospital Frankfurt

  • Schaaf, J., Sedlmayr, M., Schaefer, J., & Storf, H. (2020). Diagnosis of Rare Diseases: a scoping review of clinical decision support systems. Orphanet journal of rare diseases, 15(1), 1-14.
  • Storf, H., Stausberg, J., Kindle, G., Quadder, B., Schlangen, M., Walter, M. C., ... & Wagner, T. O. (2020). Patient registries for rare diseases in Germany: Concept paper of the NAMSE strategy group. Bundesgesundheitsblatt, Gesundheitsforschung, Gesundheitsschutz, 63(6), 761-770.
  • Storf, H., Schaaf, J., Kadioglu, D., Göbel, J., Wagner, T. O., & Ückert, F. (2017). Register für seltene Erkrankungen. Bundesgesundheitsblatt-Gesundheitsforschung-Gesundheitsschutz, 60(5), 523-531.

Preliminary work at MCS Datalabs

  • ONCORELIEF 
  • DECIDE 
  • Scherrer A, Zimmermann T, Riedel S, Mousa F, Wasswa-Musisi I, Zifrid R, Tillil. H, Ulrich P, Kosmidis T, Reis J, Oestreicher G, Möhler M, Kalamaras I, Votis K, Venios S, Plakia M, Diamanopoulos S. (2022). Digitally assisted planning and monitoring of supportive recommendations in cancer patients. In: Maglogiannis I, Iliadis L, Macintyre J, Cortez P (eds). Artificial Intelligence Appliations and Innovations. AIAI 2022 IFIP WG 12.5 International Workshops. AIAI 2022. IFIP Advances in Information and Communication Technology, vol 652. Springer, Cham, pp 401-411. DOI: 10.1007/978-3-031-08341-9_32

Your contact person

Lena Wiese

Contact Press / Media

Prof. Dr. Lena Wiese

Manager of the Working Group on Bioinformatics & Head of Attract Group IDA

Phone +49 511 5350-303