Motivation

Modern artificial intelligence (AI) methods offer the opportunity to fundamentally support and even revolutionize knowledge-intensive activities in many disciplines. While AI applications have already triggered significant changes in business and many scientific disciplines, medicine is still in the early stages of using AI. Medical data is highly complex and at the same time particularly sensitive and worthy of protection. This complicates the use of AI in development and research activities. The "AI-AIM" project is intended to help overcome these hurdles and, through anonymization, help make medical data more usable for research and industry.

Goals and procedure

Within the project "AI-based Anonymization in Medicine" (AI-AIM), the team is developing an anonymization platform to provide large amounts of real-world data. These data have no personal reference and can therefore be used more easily in terms of data protection. This should facilitate access to data for research and commercial development of data-based medical solutions. Important research topics addressed by the project are methods for the flexible combination of anonymization methods for sensitive patient data and synthesis methods for the genesis of data sets. The potential transferability to different medical specialties is also in the focus of the developers. In addition, the researchers assess risks to privacy using innovative models and evaluate the realism of output data for anonymized as well as synthesized data.

Innovations and perspectives

Within the framework of "AI-AIM", innovative methods for anonymizing personal data will be developed and evaluated, taking into account residual risks, using a concrete use case from oncology. The availability of verifiably anonymous data will facilitate both research in the field of AI and the development of AI-based commercial products for medical institutions. In perspective, this will enable further innovations in the field of AI applications. By making the developed platform available as open-source software and building a community of users, there is the possibility of creating a locational advantage for Germany and Europe in the medium to long term through the improved availability of data.

Contact: Dr. Michael Storck

Project number: 16KISA115K