Continuous design control for machine learning in certified medical systems
Abstract
Continuous software engineering has become commonplace in numerous fields. However, in regulating intensive sectors, where additional concerns need 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.
Main Authors
Format
Articles
Research article
Published
2023
Series
Subjects
Publication in research information system
Publisher
Springer
The permanent address of the publication
https://urn.fi/URN:NBN:fi:jyu-202210184913Käytä tätä linkitykseen.
Review status
Peer reviewed
ISSN
0963-9314
DOI
https://doi.org/10.1007/s11219-022-09601-5
Language
English
Published in
Software Quality Journal
Citation
- Stirbu, V., Granlund, T., & Mikkonen, T. (2023). Continuous design control for machine learning in certified medical systems. Software Quality Journal, 31, 307-333. https://doi.org/10.1007/s11219-022-09601-5
License
Additional information about funding
The authors wish to thank project AHMED and associated consortium, funded by Business Finland, for supporting this research. Open Access funding provided by University of Helsinki.
Copyright© The Author(s) 2022