The FDA's Sway On AI

By Louis Garguilo, Chief Editor, Outsourced Pharma

The FDA’s Center For Drug Evaluation And Research (CDER) published a discussion paper titled “Artificial Intelligence in Drug Manufacturing.” The paper is meant to facilitate input from stakeholders outside the agency that it intends to consider in moving towards a future regulatory framework.

As the agency considers “the application of its risk-based regulatory framework to the use of AI technologies in drug manufacturing,” CDER has identified areas derived from a comprehensive analysis of existing regulatory requirements applicable to the approval of drugs manufactured using AI technologies.

The areas of consideration and hoped for feedback in this discussion paper are:

• optimizing process design
• advanced process control
• “smart” monitoring and maintenance
• trend monitoring (to drive continuous improvement)

The report also resurrects the “Industry 4.0 paradigm.”

In 2019, I quoted Outsourced Pharma board member Darren Dasburg, then VP and head of learning and development global operations at AstraZeneca, on this term:

“Today, our internal network of professionals at pharmaceutical companies drives a supply plan through our partners. But in the not-too-distant future, that same information may be allowed to flow directly to a service provider’s machines. This will engage and then lock production for our needs, as well as for dozens of other clients of the CDMO.

“This real evolution to Industry 4.0 — the interconnection of all locations, machines, and computers — allows real-time decision making in every capacity, from determining whether the product meets a spec, to whether the production line even needs to run because sales are low … the flow of information will inherently change the way we work and create new opportunities for valuable internal resources.”

I added:

The change, thinks Dasburg, will lead to soaring productivity and profitability. Regarding the latter, this technolution (my contribution to the English language), will include “a relentless financial assessment of risk-reward and the make-versus-buy decision when it comes to outsourcing drug development and manufacturing.”

If readers know better, let me know, but it appears that over these past years, little about the realization of Industry 4.0 has been relentless.

I’m not sure it’s been consistent.

Yes, there is more tech in our facilities, and that new technology often resides at CDMOs.

While unlike Dasburg and Outsourced Pharma, the CDER paper does not focus on outsourcing; the discussion applies to every development and manufacturing entity in our industry.

Says the report:

“The use of AI to support pharmaceutical manufacturing can be deployed with other advanced manufacturing technologies to achieve desired benefits. AI is an enabler for the implementation of an Industry 4.0 paradigm that could result in a well-controlled, hyper-connected, digitized ecosystem and pharmaceutical value chain for the manufacturer.”

Through interactions with industry, FDA has already received “valuable feedback, including potential AI use cases in pharmaceutical manufacturing.” This new CDER document specifically targets four “AI use cases in pharmaceutical manufacturing.”

Four Uses

Here are the four areas where AI is bubbling up from the minds of our drug development and manufacturing practitioners and regulators, and where CDER would like further input.

1. Process Design and Scale-up: AI models such as machine learning—generated using process development data—could be leveraged to more quickly identify optimal processing parameters or scale-up processes, reducing development time and waste.

2. Advanced Process Control (APC): APC allows dynamic control of the manufacturing process to achieve a desired output. AI methods can also be used to develop process controls that can predict the progression of a process by using AI in combination with real-time sensor data. APC approaches that combine an understanding of the underlying chemical, physical, and biological transformations occurring in the manufacturing process with AI techniques are expected to see increasing adoption and have already been reported by several pharmaceutical manufacturers.

3. Process Monitoring and Fault Detection: AI methods can be used to monitor equipment and detect changes from normal performance that trigger maintenance activities, reducing process downtime. AI methods can also be used to monitor product quality, including quality of packaging (e.g., vision-based quality control that uses images of packaging, labels, or glass vials that are analyzed by AI-based software to detect deviations from the requirements of a product’s given quality attribute).

4. Trend Monitoring: AI can be used to examine consumer complaints and deviation reports containing large volumes of text to identify cluster problem areas and prioritize areas for continual improvement. This offers the advantage of identifying trends in manufacturing-related deviations to support a more comprehensive root cause identification. AI methods integrated with process performance and process capability metrics can be used to proactively monitor manufacturing operations for trends. These methods can also predict thresholds for triggering corrective and preventive action effectiveness evaluations.

Four Concerns

The discussion paper also mentions “Areas of Consideration Associated with AI.” I’ve listed those, and summarized a main point for each.

1. Cloud applications may affect oversight of pharmaceutical manufacturing data and records.

While FDA allows the use of third parties for CGMP functions under oversight by the manufacturer, existing quality agreements between the manufacturer and a third party (e.g., for cloud data management) may have gaps in managing the risks of AI in the context of monitoring and control leading to challenges for data safety and security.

2. The IOT may increase the amount of data generated during pharmaceutical manufacturing, affecting existing data management practices.

Digitization of manufacturing controls may generate more information about a process and product … however, if the raw data collected increases significantly, there may be a need to balance data integrity and retention with the logistics of data management.

3. Applicants may need clarity about whether and how the application of AI in pharmaceutical manufacturing is subject to regulatory oversight.

Applicants will need to understand the applications of AI in manufacturing operations that are subject to regulatory oversight for such areas as s monitoring and maintaining equipment, identifying areas for continuous improvement, scheduling and supply chain logistics, and characterizing raw materials.

4. Applicants may need standards for developing and validating AI models used for process control and to support release testing.

There are limited industry standards and FDA guidance available for the development and validation of models that impact product quality, which can create challenges in establishing the credibility of a model for a specific use.

----------

Would you like to weigh in? Click here for Docket No. FDA-2023-N-0487.

We are marching forward with AI, fast or slow … let’s get it right.