Info

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 the Notified Bodies alliances IG-NB and 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 risk management, clinical evaluation, post-market surveillance 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.

Target group

The event is intended for employees in MedTech companies who deal with the regulatory compliance of AI-based medical devices. No (programming) technical knowledge is required for the AI model presented here. It merely serves to learn the procedure on a real product.

Agenda

08:45

Welcome and introduction
Thorsten Prinz, VDE

09:15

Introduction to the regulatory requirements for AI-based medical devices

  • Software regulatory requirements in the MDR 
  • Requirements in the IG-NB questionnaire "AI for medical devices" 
  • Relevant software and AI standards and guidelines 
  • Important product-related processes in the manufacturer QMS 
  • Requirements in the European regulation Artificial Intelligence Act (AIA) 

10:30

Coffee break

10:45

We get to know our fictious manufacturer “AI Cancer GmbH” and his AI-based medical device software “Breast Cancer Prediction”

  • Presentation of the fictious company
  • Presentation of the manufacturer QMS
  • Presentation of the fictious AI-based medical device and its intended purpose
  • Qualification and classification as medical device software

11:15

Software life cycle and AI development process: procedure and documentation

  • AI-specific adaptations in the software lifecycle processes
  • AI development as a sub-process of the software lifecycle processes
    • Process description 
    • AI model development plan 
    • Data management and AI model development report

12:45

Lunch break  

13:30

AI technical evaluation process: procedure and documentation

  • Process description 
  • Selection of suitable diagnostic accuracy measures 
  • Evaluation plan and report
  • Application of new data

14:15

Transparency of AI-based medical devices

  • Importance of transparency for safety 
  • Technical information AI model 
  • Transparency information AI model

14:30

Robustness and generalizability of AI model 

  • Definition and examples

14:45

Best practice examples of AI model development and transparency

15:00

Coffee break 

15:15

Adaptation of clinical evaluation and usability processes for AI-based medical devices

  • Clinical evaluation checklist AI 
  • Usability checklist AI 

15:45 

Summary and discussion 

16:00 

End of the event 

Preliminary program. Subject to changes / adjustments 


Registration »


The event is organized for between 4 and 12 participants. If the minimum number of participants is not reached one week before the start of the event, we reserve the right to cancel it. For organizational reasons, registration for our events usually closes 2 days before the event date. Thank you for your understanding.

Cancellations can only be made in text form and are possible up to 8 days before the event date. In this case, a cancellation fee of 25% of the ticket price will be charged and retained when the amount paid is refunded. 

This means that 100% of the ticket price will be due in the event of a short-notice cancellation of 7 days or less.


Payment will be processed by eveeno on our behalf:

eveeno
Andreas Bothe
Ellenbogen 8
D-91056 Erlangen
Telefon: +49 157 57 00 00 59
E-Mail: info@eveeno.de
Umsatzsteuer-ID: DE262038183