The International Medical Device Regulators Forum (IMDRF) has published Machine Learning-enabled Medical Devices: Key Terms and Definitions (IMDRF/AIMD WG/N67, Edition 1). This foundational guidance establishes a common vocabulary for artificial intelligence (AI) and machine learning (ML) in the medical device sector. Its purpose is to create uniform expectations and understanding, improve patient safety, inspire innovation, and encourage access to breakthroughs in healthcare technology.
Artificial intelligence is broadly defined as the use of algorithms or models to perform tasks, make decisions, or generate predictions. Within AI, machine learning is a subset where models are trained on data, enabling them to learn patterns without explicit rule-based programming. The IMDRF document situates these concepts within a regulatory and clinical context, ensuring clarity when applied to medical devices.
One of the key goals of the guidance is to reduce confusion across jurisdictions. Manufacturers, regulators, and clinicians may use different terms for the same concepts, such as “model,” “training,” or “retraining.” This lack of alignment can complicate regulatory submissions and reviews. The IMDRF’s definitions create a standard set of terms that can be consistently referenced across regulatory frameworks and development programs.
In February 2025, IMDRF released Good Machine Learning Practice (GMLP), which builds on the definitions in N67 by providing ten guiding principles for the development, validation, and monitoring of ML-enabled devices. The link between the two documents is crucial: N67 defines the language, while GMLP sets expectations for practice across the product lifecycle.
IMDRF N67 and N88 at a glance
| Document | Purpose | Practical relevance |
|---|---|---|
| IMDRF N67, published in 2022 | Establishes common terms and definitions for machine learning-enabled medical devices. | Helps manufacturers and regulators use consistent terminology across development, evaluation and regulatory documentation. |
| IMDRF N88, published in 2025 | Sets out ten Good Machine Learning Practice guiding principles. | Applies the terminology across the total product lifecycle, including dataset design, testing, human interaction, user information and post-deployment monitoring. |
N67 provides the common vocabulary. N88 builds on that foundation by describing how good machine learning practices should be applied throughout the medical device lifecycle.
The 10 IMDRF Good Machine Learning Practice principles
IMDRF N88 identifies ten principles for the development and lifecycle management of AI and machine learning-enabled medical devices:
- Define the intended purpose clearly and use multidisciplinary expertise throughout the product lifecycle.
- Apply sound software engineering, medical device design, security and quality practices.
- Use datasets that represent the intended patient population and use environment.
- Keep training datasets appropriately independent from test datasets.
- Select reference standards that are fit for the device’s intended purpose.
- Match the model design to the available data, intended purpose and identified risks.
- Evaluate the human-AI team in the intended clinical environment, not only the model in isolation.
- Test performance under clinically relevant conditions.
- Give users clear information about performance, limitations, data and appropriate use.
- Monitor deployed models and control the risks associated with retraining, bias and dataset drift.
Key Terms and Their Impact
N67 formally defines a machine learning-enabled medical device, or MLMD, and establishes terminology for bias, continuous learning, reference standards, reliability, training and test datasets, and supervised, semi-supervised and unsupervised learning. It also discusses locked states, retraining and changes to the device or its data environment. Dataset drift is addressed later in N88 as part of post-deployment monitoring and retraining risk management, rather than as a formal N67 definition.
Why Uniform Definitions Matter
A harmonized vocabulary enhances regulatory predictability and cross-border alignment. With common definitions, manufacturers can prepare more consistent submissions, and regulators can apply more transparent and standardized review processes. It also helps notified bodies, standards committees, and audit organizations maintain consistent evaluation criteria.
Clear definitions are equally important for clinicians and patients. When a device is described as “continuously learning,” stakeholders need to understand the precise boundaries of its adaptation. This clarity reduces risks of misinterpretation that could compromise patient safety or compliance.
Integration with Regulatory Practice
The IMDRF’s N67 definitions are now referenced in the GMLP principles adopted by multiple regulators, including those in the U.S., UK, EU, and Canada. This reinforces the importance of shared terminology as the basis for regulatory policy. Together, N67 and GMLP create a roadmap for the development and oversight of AI/ML-enabled devices, from design and testing to monitoring and lifecycle management.
For the EU-specific requirements that apply alongside these international principles, see our guide to the EU AI Act for medical devices and SaMD.
Implications for Developers
Manufacturers must integrate IMDRF definitions into their development practices from the outset. Risk management plans, validation strategies, and change-control procedures should explicitly reflect terms such as drift, retraining, and continuous learning. Clinical performance evaluation must be designed using clearly defined training and test sets, while monitoring strategies must track performance shifts aligned with N67 definitions.
Failure to align with this common vocabulary can lead to misinterpretation, regulatory delays, or gaps in safety oversight. By embedding these terms into development and documentation, companies can demonstrate compliance and strengthen the credibility of their devices.
Manufacturers preparing an EU submission should also consider software classification, IEC 62304, clinical evidence and lifecycle documentation. These requirements are covered in our SaMD compliance guide.
FAQ
IMDRF/AIMD WG/N67 is a 2022 document that establishes common terminology for machine learning-enabled medical devices across the total product lifecycle. It defines MLMD and terms related to bias, continuous learning, reference standards, reliability, training and testing datasets, and different machine learning methods. It does not provide detailed development or risk-management requirements.
A machine learning-enabled medical device, or MLMD, is a medical device that uses machine learning, either partly or entirely, to achieve its intended medical purpose. The product must first meet the applicable definition of a medical device before it can be considered an MLMD.
N67 establishes the vocabulary used to describe machine learning-enabled medical devices. N88 builds on that terminology by presenting ten Good Machine Learning Practice principles covering design, datasets, testing, human-AI interaction, user information and post-deployment monitoring.
The ten principles address intended purpose, multidisciplinary expertise, software and security practices, representative datasets, independence between training and test data, reference standards, model design, human-AI interaction, clinically relevant testing, user information and ongoing model monitoring.
The official documents are available directly from IMDRF: Machine Learning-enabled Medical Devices: Key Terms and Definitions, N67 and Good Machine Learning Practice for Medical Device Development: Guiding Principles, N88.
Conclusion
The IMDRF’s Machine Learning-enabled Medical Devices: Key Terms and Definitions guidance represents a milestone in harmonizing global understanding of AI/ML in healthcare. By defining key terms such as model, drift, and retraining, it lays the foundation for safe innovation and regulatory clarity. Together with the GMLP framework, it provides a roadmap for developers and regulators alike as AI-enabled healthcare technologies continue to evolve.
MDx CRO supports manufacturers with AI and machine learning regulatory strategy, software validation, clinical evidence and lifecycle documentation. Explore our Software, Digital Health and AI regulatory services or contact our team to discuss your development programme.
