New Publication: Engineering Data Architectures for AI/ML Integration in Regulated Manufacturing
Researchers joined forces across WP2 and WP3 of the LifeFactFuture (LFF) consortium on research on the important topics of data architecture, AI integration, and regulatory compliance in regulated pharmaceutical and medical device manufacturing.
Results are now out in a new Open Access conference paper by Viktoriia Shubina, Tuomas Ranti, Anne Juppo & Tuomas Mäkilä.
The paper makes at least three important contributions:
- Evidence on the technical and regulatory barriers to AI/ML adoption in regulated manufacturing, grounded in 20 expert interviews
- Overview of current industry practices
- Conceptual framework to guide the design of AI-driven data architectures that support compliant AI/ML lifecycle management
The findings highlight data silos and legacy infrastructures as primary technical barriers, while evolving regulatory frameworks and uncertainties in AI validation create significant compliance challenges.
Shubina, Viktoriia – Ranti, Tuomas – Juppo, Anne & Mäkilä, Tuomas (2026) Engineering Data Architectures for AI/ML Integration in Regulated Manufacturing. International Conference on Software Business, Lecture Notes in Business Information Processing, LNBIP, vol. 574, p. 41–57.