European test infrastructure for AI and robotics in healthcare

The Fraunhofer Heinrich-Hertz-Institut (HHI) is part of the EU project TEF-Health (Testing and Experimentation Facility for Health AI and Robotics), which aims to establish a test infrastructure for artificial intelligence (AI) and robotics in healthcare. The infrastructure will facilitate comprehensive and rapid testing of innovative methods and enable them to reach market maturity.

Led by the Berlin Institute of Health (BIH) at Charité Berlin, TEF-Health involves 51 partners from nine European countries. The project started in January 2023 and will run until December 2027 for a total of 5 years. The European Union and the member countries represented in the project are funding the project with 60 million Euros. Fraunhofer HHI will receive 1.2 million Euros of this amount.

Before integrating new technologies into the healthcare system, it is crucial to comprehensively test their safety, robustness, and reliability. In the case of AI and robotics, quality requirements in the European Union are high, but the current testing infrastructure for developing standards, testing innovations, and certifying new products remains insufficient.

The TEF Health consortium aims to improve this process and accelerate the validation and certification of AI and robotics in medical devices. To this end, the research team is developing a test infrastructure (both virtual and physical) that can evaluate various technologies in realistic environments, including hospitals and laboratories. For instance, software for patient care or diagnostics, as well as surgical or nursing robots can be tested by users.

To design this test infrastructure, the project partners are developing new regulatory and ethical requirements such as standardized test protocols and agile certification processes for AI-based technologies or a specific code of conduct for their applications. Additionally, it is essential to develop the necessary technical and regulatory procedures. For this reason, TEF-Health encompasses not only leading hospitals, universities, and clinical research institutions, but also governmental testing organizations such as “TÜV”, the German “Physikalisch-Technische Bundesanstalt” and its French counterpart, the “Laboratoire national de métrologie et d’essais” with whom Fraunhofer HHI works in close collaboration for this project.

Fraunhofer HHI is joining TEF-Health with its research groups “Applied Machine Learning” and “Explainable Artificial Intelligence” within the Artificial Intelligence department. The AI experts will develop methods and tools for the quality assurance of AI technologies. Furthermore, they will work on the conception and development of the virtual test infrastructure and contribute their expertise in the areas of time series analysis, application of explainable AI methods, and standardization.

The Fraunhofer HHI team has already gained experience in the domain of AI standardization on both a national and international level. Since 2021, they have been organizing the annual workshop series “Towards Auditable AI Systems” together with the TÜV Verband and the German Federal Ministry for Information Security (BSI), producing groundbreaking white papers. Internationally, Fraunhofer HHI researchers are working on the development of methods for the standardization and quality assessment of AI systems in healthcare in the ITU/WHO Focus Group “AI for Health”, which is chaired by the institute.

The evaluation resources and infrastructure developed in the project will become available to industry in the form of fee-based services upon completion. Through these comprehensive testing and evaluation tools, the TEF Health team also aims to increase public confidence in innovative AI and robotics technologies.

Wissenschaftliche Ansprechpartner:

Martina Müller
Head of Corporate Communications
Phone +49 30 31002-242
Email martina.mueller@hhi.fraunhofer.de

Dr. rer. nat. Jackie Ma
Head of Applied Machine Learning Group
Phone +49 30 31002 461
Email jackie.ma@hhi.fraunhofer.de

Originalpublikation:

https://www.hhi.fraunhofer.de/en/news/nachrichten/2023/fraunhofer-hhi-develops-e…