Artificial intelligence (AI) technologies, including machine learning, have the potential to transform health care by deriving new and important insights from the vast amount of data generated in health care every day. They use algorithms that can learn from realworld use and potentially use this information to improve the product’s performance.
But they also present unique considerations due to the iterative and data-driven nature of their development. This document establishes a common set of principles for the community to promote the development of safe, effective, and high-quality medical devices that incorporate AI.
The 10 guiding principles for Good Machine Learning Practice (GMLP) presented in this document are a call to action to international standards organizations, international regulators, and other collaborative bodies to further advance GMLP. Areas of collaboration include research, creating educational tools and resources, international harmonization, and consensus standards, to inform regulatory policies and regulatory guidelines. These guiding principles may be used to adopt practices from other sectors, tailor them to the medical technology and healthcare, and to develop novel practices for this domain.
Advances in the medical device field, exemplified by generative AI, highlight the importance of clearly describing a product’s intended use/ intended purpose and identifying its regulatory status. Moreover, generative AI may heighten the role of GMLP, including fundamental software engineering practices. For example, the process of finetuning foundation models for more specific medical purposes may introduce significant quantities of Software of Unknown Provenance (SOUP), as the manufacturer performing the finetuning may only have limited documentation for the base foundation model. AI may also pose a more fundamental challenge with respect to demonstrating device performance. The regulatory science of measuring performance as well as
characterizing and detecting errors in these models is maturing to meet this challenge.
Good machine learning practice for medical device development – Guiding Principles