CDER chief touts AI potential to reduce quality defects, encourages adoption of AI tools
Using elements of artificial intelligence (AI) in drug manufacturing can confer multiple benefits, including improving product quality and reducing manufacturing defects, said Patrizia Cavazzoni, MD, director of the Center for Drug Evaluation and Research (CDER) in the US Food and Drug Administration (FDA).“Whether we like it not, human error is still very much at the root of the quality problems that we are seeing in manufacturing,” Cavazzoni told a joint workshop of the FDA and the Product Quality Research Institute (PQRI) on 26 September. The two-day FDA/PQRI workshop highlighted discussions among regulators, industry and academia on incorporating AI in pharmaceutical manufacturing.
Cavazzoni called AI an “inherent element and component of advanced manufacturing,” noting that AI has been a priority for CDER since 2019. “We’re very interested in AI for manufacturing drugs and for clinical development in general,” she added.
Among AI’s benefits are the ability to improve designs and scale up with less development time and process waste, Cavazzoni said. “It confers greater control over quality and so paired with advanced manufacturing (AM) this can be a very powerful combination because it removes human error from the equation,” she said. AI can also be a tool to prevent drug shortages, she said, by preventing the types of drug quality issues that can be at the root of shortages.
Cavazzoni encouraged industry to review two external discussion papers on AI, one focused on the use of AI in drug manufacturing and the other on the use of AI in machine learning (RELATED: FDA seeks feedback on artificial intelligence in drug manufacturing, Regulatory Focus, 1 March 2023; FDA publishes discussion paper on AI/ML in drug development Regulatory Focus, 12 May 2023).
Officials also announced at the meeting that the agency is reopening the public comment period on the discussion paper on AI, which was released in March 2023.
Participants from industry and academia discussed how they are incorporating various elements of AI into manufacturing programs. A representative of GSK discussed how AI and “deep learning” can be applied to visual inspections, while a representative from the Massachusetts Institute of Technology explained how it is developing “digital twins” for use in a wide variety of pharmaceutical manufacturing processes, including for small-molecule drugs, recombinant proteins, vaccines and gene therapies.
The pharmaceutical industry appears to be embracing AI. FDA officials told attendees at a meeting earlier this year that they have seen a dramatic uptick in submissions containing AI and machine learning elements, receiving 170 submissions containing these elements in 2022 (RELATED: FDA sees rapid uptick in drug and biologic submissions with AI/ML components, Regulatory Focus 12 July 2023).
PQRI/FDA meeting
×
Welcome to the new RAPS Digital Experience
We have completed our migration to a new platform and are pleased to introduce the updated site.
What to expect: If you have an existing login, please RESET YOUR PASSWORD before signing in. After you log in for the first time, you will be prompted to confirm your profile preferences, which will be used to personalize content.
We encourage you to explore the new website and visit your updated My RAPS page. If you need assistance, please review our FAQ page.
We welcome your feedback. Please let us know how we can continue to improve your experience.