尊龙凯时人生就是搏

尊龙凯时人生就是搏

Technologie-, und Innovationskonzept
peshkova / stock.adobe.com
2025-06-03 expert contribution

CE conformity for AI-based medical devices with BAIM

AI-based medical devices are subject to numerous regulatory requirements in the EU.聽
Contact
Dr. Thorsten Prinz
Topics
Medical technology
Health
Artificial Intelligence

The regulatory complexity of AI-based medical devices arises not only from the EU MDR and the new legislative framework EU AI Act, but also from the inherent characteristics of the AI technology. The functionalities of AI-based medical devices are determined by the software code (in terms of the model and the application) and, in addition, by the AI model itself and the data used for training. This creates a variety of specific challenges for manufacturers, particularly with regard to generalisability, transparency and representativeness.聽

To support manufacturers of AI-based medical devices to be compliant with the high requirements for market access, the VDE has developed the regulatory approach "BAIM - Boost AI to Market".聽

The BAIM Concept

Every medical device manufacturer needs a quality management system (QMS) as the basis for regulatory compliance with the MDR.

BAIM addresses regulatory requirements originating from the IG-NB/Team-NB questionnaire "Artificial Intelligence in Medical Devices" and the EU AI Act. For implementation purposes, AI-specific standards as well as reports and literature on best practices are continuously analyzed as part of the state-of-the-art and integrated into the regulatory documents.聽

BAIM primarily aims to align聽AI-specific requirements in the following regulatory areas of the manufacturer's QMS:聽

BAIM-Fig4
VDE

Selective adjustments are also made to the QMS processes:聽

  • regulatory compliance strategy,聽
  • human resources,聽
  • information supplied by manufacturer,
  • infrastructure,聽
  • purchase聽and suppliers,聽
  • external processes, and聽
  • information security / data protection.聽


Extension of software lifecycle processes to include AI model development聽

Manufacturers of AI-based medical devices apply the EN 62304 standard on the software lifecycle. If a standalone software is concerned, the EN 82304-1 standard also applies. For this purpose, the manufacturer implements a development process, a release process, a maintenance process and a process for decommissioning the software in its QMS. These processes are supplemented by validation and post-market activities of the manufacturer.聽

BAIM introduces an additional AI development process, which is subordinate to the actual software development process of EN 62304. This includes the collection and analysis of all user and system requirements including the AI-specific ones in the general development process whereas data management and AI model development take place in the AI development process. Moreover, testing of the AI model occurs in the second additional process 鈥淎I model evaluation鈥�.

Adaptation of further central QMS processes

According to the MDR, a risk management system as part of the QMS is mandatory for every medical device manufacturer. The complexity of AI technology is accompanied by special hazards such as various forms of bias, which must be considered in risk management. BAIM extends the necessary risk analysis to include AI-specific risks and thus contributes to increased safety of these products. Risk management聽according to the EN ISO 14971 standard must consider safety (in the sense of operational safety) together with (cyber) security and their interactions. BAIM uses the VDE's ARGOS cybersecurity approach to also analyze AI-specific assets, interfaces and methods of attack and to take appropriate measures.聽

As part of the QMS process "Usability Engineering", formative validations take place during development (or maintenance) as well as summative validations at the end of development (or maintenance). In a process-integrated checklist, BAIM formulates specific requirements for the usability-oriented development of AI-based medical devices. This includes, for example, dealing with transparency, explainability or automation bias.聽

The clinical evaluation serves to demonstrate the safety and performance as well as a positive benefit-risk ratio for the respective medical device. In addition to the relevant guideline MEDDEV 2.7/1 for the clinical evaluation of medical devices, the guideline MDCG 2020-1 must also be applied to software. BAIM supports the manufacturer in the clinical evaluation with a checklist that addresses AI-specific aspects in the corresponding QMS process. This also refers to the use of AI-specific databases for literature searches.聽

The software lifecycle includes post-market surveillance and vigilance by the manufacturer. Especially for AI-based medical devices, a significant level of safety and performance is ensured by comprehensive post-market surveillance by the manufacturer. BAIM extends the post-market surveillance plan to include AI-specific aspects, e.g. regarding the quality of real-life data and timeliness of the ground truth or gold standard. During this, corresponding methods and their frequency in application as well as parameters and limit values to be considered are implemented.聽

Practical Implementation

A typical BAIM project begins with the definition of the intended purpose of the AI-based medical device, taking into account the operating principle of the AI component. Subsequently, the AI development process is integrated into the QMS, and risk management, including cybersecurity, is implemented in accordance with ARGOS. In parallel, activities oriented towards usability will be initiated and the first clinical evaluation will be performed. In the context of monitoring (including post-market clinical follow-up) and vigilance, the performance of the AI-based software is continuously observed, with the collected data being fed back into the clinical evaluation.

In summary, BAIM either extends an existing QMS or is applied when a QMS is established, ensuring the manufacturer's compliance with the specific requirements for AI-based medical devices. The application of BAIM also ensures that the manufacturer's QMS is future-oriented and prepared for new regulatory challenges.聽

Follow Us
漏 2025 VDE Association for Electrical, Electronic & Information Technologies
百度一下 搜索 尊龙凯时人生就是搏