Continuous Design Control for Machine Learning in Certified Medical Systems
This addresses the problem of integrating continuous engineering into certified medical systems for developers and regulators, though it appears incremental as it builds on existing techniques like model cards.
The paper tackles the challenge of applying continuous development approaches like DevOps in regulated medical systems by introducing an approach that uses pull requests as design controls and model cards for explainability, demonstrating it with an industrial system previously used for continuous medical development.
Continuous software engineering has become commonplace in numerous fields. However, in regulating intensive sectors, where additional concerns needs to be taken into account, it is often considered difficult to apply continuous development approaches, such as devops. In this paper, we present an approach for using pull requests as design controls, and apply this approach to machine learning in certified medical systems leveraging model cards, a novel technique developed to add explainability to machine learning systems, as a regulatory audit trail. The approach is demonstrated with an industrial system that we have used previously to show how medical systems can be developed in a continuous fashion.