AI/ML-Based SaMD Framework

The US Food and Drug Administration’s proposed regulatory framework for artificial intelligence- (AI) and machine learning- (ML) based software as a medical device (SaMD) is fascinating in what it exposes about the uncertainty around the near-term future of a lot of industry 4.0 initiatives in pharmaceuticals and medical devices.

While focused on medical devices, this proposal is interesting read for folks interested in applying machine learning and artificial intelligence to other regulated areas, such as manufacturing.

We are seeing is the early stages of consensus building around the concept of Good Machine Learning Practices (GMLP), the idea of applying quality system practices to the unique challenges of machine learning.

Interoperability of Data

Thomas Peither on GMP Logfile in “Industry 4.0 – Inspiration for the Pharmaceutical Industry?” summarizes discussions from the ISPE European Annual Meeting 2018.

There is a lot to unpack in the concept of Industry 4.0. The topic on my mind is data interoperability.

“We identified a struggle with the lack of harmonised and consistent information flows in the industry”, said Volker Roeder

I think this is an understanding that a lot of us, especially from bigger companies that grew from acquisitions and mergers, are grappling with. Decisions made 15+ years ago in the ERP (for example) now has widespread impacts as we start aligning and integrating other systems. It is difficult to align the MES, CMMS, ERP, LIMS and QMS if they all think of master-data differently. Its even harder when one branch of the business deals with master data differently than another branch, but both branches are in the same system.

I don’t have a magic bullet. I just think this is an area that will make Industry 4.0 a great deal more challenging than many of its proponents advocate. And it is becoming a bigger part of my professional life.

Read the article, it is well worth the 10 minutes spent.