IMDRF N88 Good Machine Learning Practice for Medical...

What does P10 require?

A deployed model can be monitored on an ongoing basis in real-world use at a level suited to its risk, with a risk-based focus on maintaining or improving safety and performance, and where models are retrained after deployment controls manage the risks of overfitting, unintended bias and degradation such as dataset drift that could affect safety and performance.

Other controls in Section 3: Guiding principles – IMDRF N88 Good Machine Learning Practice for Medical Device Development: Guiding Principles (2025)

P1 Understand the intended use deeply and bring multi-disciplinary expertise across the life cycle
P2 Apply good software engineering, device design and security practice throughout
P3 Evaluate clinically with datasets representative of the intended patient population
P4 Keep training and test datasets independent
P5 Use reference standards that are fit for purpose
P6 Tailor model choice and design to the data and the intended use
P7 Assess the human-AI team in the intended use environment, not the device alone
P8 Test performance under clinically relevant conditions, independent of training data

Query this from an agent

The graph holds this control, the 0 it maps to, and the evidence behind each claim, over MCP and REST.

MCP endpoint All IMDRF N88 Good Machine Learning Practice for Medical Device Development: Guiding Principles (2025) controls