The “Secret Sauce” for Artificial Intelligence

The Paperless Lab Academy® is all about digital data management. What could be more representative than the ability to benefit from your data and potentiate algorithms and models to supervise your processes?

The Paperless Lab Academy® has just concluded its 10th European edition with a strong program on Artificial Intelligence in GMP bioprocesses, fully automated workflows in bioburden analysis, cybersecurity awareness, standardisation of global LIMS implementation and several parallel discussions in the numerous workshops.

This is the first article of a series to summarise and share the key outcomes from the recent #PLA2023Europe with the PLA community starting with the discussion about the use of Artificial Intelligence in GMP environment.

And therefore, who could be better than Toni Manzano, CSO and co-founder at Aizon, to introduce us carefully to AI so that we can all appreciate the actual real cases implemented in bioproduction processes?

AI is nowadays rather often routine

Toni always likes to remember his audience that the term artificial intelligence was coined as early as 1950 (1) and to share Tim Menzies statement in 2004:

“Artificial Intelligence is no longer some bleeding technology that is hyped by its proponents and mistrusted by the mainstream. In the 21st century, AI is not necessarily amazing. Rather, it is often routine. Evidence for the routine and dependable nature of AI technology is everywhere.”

This is a fact; AI today is implemented for routine procedures in GMP environments.  As AI industrial expert, Toni is part of a committee coordinated by the AFDO, Association of Food And Drug Officials (2), which includes the FDA, which has the greatest interest in the development of Artificial intelligence in manufacturing processes.

In fact, the FDA is already building artificial intelligence into its own processes for two reasons: first, of course, for the patients, to get a safer, higher quality and more efficient product; and second, because the agency itself needs to coordinate better to cover the entire pharmaceutical industry, which extends to outsourced CMOs. They need to automate their monitoring and control process.

Interestingly, the FDA considers the application of its risk-based regulatory framework to the use of AI technologies in drug manufacturing and has recently released a discussion paper about Artificial Intelligence in Drug Manufacturing (3) identifying areas for which public feedback would be valuable.

The art of data preparation 

Never the message about the need to invest in the quality of data, even more in GMP environment, has been raised so clearly and loudly.

It is all about data, and this is the secret sauce for fruitful outcomes in using AI in manufacturing processes. There is an art in preparing the data that requires of both skilled data scientist and subject matter experts. Data need to be qualified, assesses as per its quality but also validated as per its relevance for the model to be developed.

 

In the end, the use of AI brings quality to the processes where it is used. Example like AI-guide process monitoring shows that a bioreactor fermentation process can be controlled with no manual interventions, supervising, and monitoring multiple relevant factors to detect basically real-time underperforming batches.

it might come a day, that bioprocesses as so perfectly controlled that final product analysis for quality control purposes might not be necessary anymore.

---

References

(1) By the 1950s, a generation of scientists, mathematicians, and philosophers with the concept of artificial intelligence (or AI) culturally assimilated in their minds. One such person was Alan Turing, a young British polymath who explored the mathematical possibility of artificial intelligence. Turing suggested that humans use available information as well as reason to solve problems and make decisions, so why can’t machines do the same thing? This was the logical framework of his 1950 paper, Computing Machinery and Intelligence in which he discussed how to build intelligent machines and how to test their intelligence.

(2) About The Association Of Food And Drug Officials (AFDO). The Association of Food and Drug Officials (AFDO) is a well-recognized national organization that represents state, territorial, and local regulatory. The Association’s principal purpose is to act as the leader and a resource to state, territorial, and local regulatory agencies in developing strategies to resolve and promote public health and consumer protection related to the regulation of food, medical products, and cosmetics. afdo.org

(3) https://www.fda.gov/media/165743/download