Good Machine Learning Practices for Medical Device Development

Bernhard Kappe
Bernhard Kappe

Many of you probably saw the announcement last week from the FDA on Good Machine Learning Practices for Medical Device Development: Guiding Principles. The document was put out jointly by the FDA and the equivalent regulators in the UK and Canada. Based on our initial reading, it does not cover new ground. In many ways, it can be looked at as a “cliff notes” version of the much more detailed 2018 Xavier Health Whitepaper on Good Practices for AI and Continuous Learning Systems in Healthcare.

FDA Guiding Principles Cover
Xavier AI White Paper Cover

It is important to note that this document is NOT the draft guidance on Marketing Submission Recommendations for a Change Control Plan for Artificial Intelligence/Machine Learning (AI/ML)- Enabled Device Software Functions that is on the FDA’s B list for 2021. We’ve been told that the guidance document has been developed, but the FDA can’t publish it yet, and that this document, along with last month’s virtual public workshop on transparency, are intermediate deliverables.

  • Bernhard Kappe
AI Medical Devices White Paper CTA

Related Posts


Roundup: Bluetooth Medical Devices Cleared by FDA in 2023

White Paper

Software as a Medical Device (SaMD): What It Is & Why It Matters


SaMD Cleared by the FDA: The Ultimate Running List


Help Us Build an Authoritative List of SaMD Cleared by the FDA