Hands-on Training Artificial Intelligence (AI) in Medical Devices

Artificial intelligence (AI)-based medical devices are subject to the Regulations (EU) 2017/745 (MDR) or 2017/746 (IVDR) and in Germany to the Medical Devices Implementation Act (MPDG). The Regulation (EU) 2024/1689 EU (Artificial Intelligence Act, AIA) creates even higher barriers to market access. In addition, many AI-specific standards and guidelines are currently being published (e.g., by IG-NB/Team NB), and best practice methods for developing AI models are constantly being updated. The first challenge for manufacturers is to implement the development and evaluation of the AI model as processes in their quality management system in accordance with the relevant requirements. Other regulatory processes, such as software lifecycle and risk management, clinical evaluation, and usability, also need to be adapted to take account of AI-specific features. In our hands-on training, we first get to know a fictitious company and its AI-based medical device software. We consider the training and testing of a simple artificial neural network as an AI model, as far this is required for the regulatory handling of the product. Using this real and publicly available AI model with a medical purpose as an example we apply various AIA- and MDR-ready regulatory templates (in English) step by step, which can later be transferred to your product. Participants of this hands-on training will receive all presented documents as PDF and also a list of requirements for medical devices as high-risk AI systems according to the provisions of the AIA.