Adam C. Fisher, Phd, is Director of Science Staff, Office of Pharmaceutical Quality, Center for Drug Evaluation and Research, FDA.

Adam C. Fisher, PhD

Cyborg hand holding a Medical icon and connection 3d rendering  |©Production Perig - stock.adobe.com

This article was previously published in 

Hollywood has long presented artificial intelligence (AI) as a futuristic concept far from reality, but technology has now eliminated the gap between science fiction and science fact. AI is here and here to stay; 50% of global healthcare companies plan to implement AI strategies by 2025 (1). For pharmaceutical manufacturers, AI has the potential to revolutionize process design and control, and thus bring benefits to patients and challenges to regulators.

The Future is the Present: Artificial Intelligence in Pharmaceutical Manufacturing

Regulating Innovation, Quality, and Risk eBook January 2024

Owing to its fictionalized past, the term AI can mean wildly different things to different people. FDA’s Center for Drug Evaluation and Research (CDER) describes AI rather inclusively as “a branch of computer science, statistics, and engineering that uses algorithms or models that exhibit behaviors such as learning, making decisions, and making predictions” (2). The National Academies of Sciences, Engineering, and Medicine issued a report on innovations in pharmaceutical manufacturing that highlighted AI’s potential role in the measurement, modeling, and control used for pharmaceutical manufacturing (3).

Adam Fisher, PhD is Director of Science Staff and Immediate Office within the Office of Pharmaceutical Quality at the Center for Drug Evaluation and Research at FDA.

Pharmaceutical Technology/Pharmaceutical Technology Europe Regulating Innovation, Quality, and Risk

Articles

FDA is anticipating how AI may advance manufacturing and improve supply chain security.

Artificial Intelligence in Pharmaceutical Manufacturing

Cyborg hand holding a Medical icon and connection 3d rendering | Image Credit: ©Production Perig - stock.adobe.com

AI offers potential benefits to pharmaceutical manufacturers in the form of optimized process design and control, and smart monitoring and maintenance, to drive continuous improvement. AI in concert with other innovative technologies might advance pharmaceutical quality, build more resilient supply chains, and improve the availability of medicine for patients (4). In anticipation of these benefits, FDA is proactively preparing for the arrival of AI technologies in pharmaceutical manufacturing.

AI is an enabler of Industry 4.0, the fourth industrial revolution characterized by integrated, autonomous, and self-organizing production systems (5). The Industry 4.0 paradigm brings the hope of a well-controlled, hyper-connected, digitized ecosystem and supply chain. The COVID-19 public health emergency seems to have accelerated the development of Industry 4.0 technologies, such as AI, that might respond to rapidly changing supply and demand and reduce dependence on human intervention.

So how might manufacturers deploy AI in process design and control?

 AI models employing machine learning might use process development data to more quickly design and identify optimal process parameters or scale-up strategies, reducing development time and waste.

Advanced process control might allow for dynamic control of a manufacturing process which, in combination with real-time sensor data, might be used to develop process controls that can precisely predict the trajectory of a process. Pharmaceutical manufacturers are expecting to adopt advanced process control approaches that combine AI techniques with chemistry and physics knowledge to improve manufacturing efficiency and output.

 AI methods might be used to better monitor equipment and detect changes from optimal performance. AI-detected deviations might trigger maintenance activities in a manner that minimizes process downtime.

AI methods integrated with process performance metrics might offer better trend monitoring, even across products or locations, and consequently allow for proactive corrective and preventive actions to address manufacturing discrepancies before they impact the supply chain, or worse, cause drug shortage.

The potential use of AI to monitor quality doesn’t even end at the process. AI might also be used to monitor a product’s quality after manufacturing, for example, for the integrity of its packaging or presence of particulates. A vision-based quality control system might use AI to analyze images of packaging, labels, or glass vials to detect deviations (6). Beyond the product itself, AI might be used to identify cluster problems from consumer complaints and deviation reports that might contain large volumes of unstructured text. Though the potential applications of AI in pharmaceutical manufacturing will continue expanding, whether a manufacturer employs AI or not, high-quality drugs should be consistently available to patients.

CDER established a Framework for Regulatory Advanced Manufacturing Evaluation (FRAME) initiative to prepare a regulatory framework to support the adoption of advanced manufacturing technologies that could benefit patients, such as AI. FDA recognizes potential benefits, and risks, of AI throughout the drug product lifecycle. As some manufacturers look to employ AI in their manufacturing processes, the regulatory framework will need to enable the timely adoption of these technologies while also keeping patients safe. CDER recognizes the need to better understand how this new manufacturing paradigm could impact pharmaceutical operations and regulation. The regulatory strategies of the past might not work as effectively in an AI-enabled Industry 4.0. However, regulators do not develop and implement manufacturing technologies. There is a need for the stakeholders developing these technologies to provide FDA a better understanding of where and how AI innovations might be used in drug manufacturing. Industry and regulators will not be able to address the issues related to AI by working separately; true innovation requires science-based collaboration.

In March 2023, CDER released a discussion paper to solicit public and stakeholder input on AI in drug manufacturing to better identify areas of policy consideration for AI technologies (2). This discussion paper proposed areas of consideration based on CDER’s evaluation of the existing regulatory framework: standards for developing and validating AI models, clarification on regulatory oversight for AI in pharmaceutical manufacturing, maintenance of cloud applications and continuously learning AI systems that adapt to real-time data, and data management practices commensurate with the volume of data generated.

FDA’s public workshop on the use of AI in drug Manufacturing on September 26–27, 2023, in conjunction with the Product Quality Research Institute, was designed to provide another opportunity for stakeholders to discuss key topics with regulators, such as:

Artificial Intelligence in Process Development, Process Monitoring, and Commercial Batch Trend Monitoring

Artificial Intelligence and the Use of Big Data and Data Management within the Pharmaceutical Quality System

Lifecycle Approaches to Management of Artificial Intelligence.

Discussions on topics like these will help further inform the evaluation, development, and implementation of a regulatory framework that considers the benefits and risks of AI.

Like industry, regulators can employ AI to improve processes. In fact, FDA currently uses AI for translating documents, screening adverse event reports, and forecasting the volume of incoming regulatory submissions. In the future, both manufacturers and regulators might benefit from the extensive data and analysis provided by the expanded use of AI. International regulators have projected using AI to detect false or misleading drug information, scan scientific literature, identify safety signals, and respond to public inquiries (7).

While there are potential benefits of AI, there are also risks. Access to high-quality data is a fundamental requirement for effective AI training or learning. AI can be particularly sensitive to the characteristics of the data used for training, testing, and validation. The process analytical technologies providing data to AI systems must be accurate and representative. For learning purposes, data must represent not only process successes but also process failures. It will be critical to ensure that data used for AI training or learning are fit for use based on quality, reliability, and representativeness.

Humans, and not machines, are ultimately responsible for assuring that high-quality drugs are available to patients. Humans must be able to interpret the information generated by AI enough to ensure, for example, adherence to current good manufacturing practice requirements. Even with the best intentions, there are risks for unintended consequences. Might some even use AI for unethical outcomes?

Still, continued technology advancement is undeniable. There’s already talk of an Industry 5.0 paradigm which focuses on man and machine working together, instead of separately, and considers the manufacturer’s impact on the workforce and environment (8). In looking ahead, it feels only appropriate to ask the uber popular AI chatbot, ChatGPT, how things will turn out, “Will AI improve pharmaceutical manufacturing?” “Yes, AI has the potential to significantly improve pharmaceutical manufacturing.”

The combined efforts of regulators, industry, and scientists can now help to realize this potential while safeguarding against risks to patients.

USM. Top 5 AI Use Cases in Pharma & Bio Medicine. 

FDA. Artificial Intelligence in Drug Manufacturing. 

National Academies of Sciences, Engineering, and Medicine. Innovations in Pharmaceutical Manufacturing on the Horizon: Technical Challenges,
Regulatory Issues, and Recommendations. The National Academies Press online, DOI:10.17226/26009 (2021).

Arden, S. et al. Industry 4.0 for Pharmaceutical Manufacturing: Preparing for the Smart Factories of the future.

FDA. Artificial Intelligence/Machine Learning Assisted Image Analysis for Characterizing Biotherapeutics. 

International Coalition of Medicines Regulatory Authorities. Horizon Scanning Assessment Report–Artificial Intelligence (2021).

https://research-and-innovation.ec.europa.eu/research-area/industrial-research-and-innovation/industry-50_en


Vol. 47, No. 9
September 2023
Pages: 32–34

When referring to this article, please cite it as Fisher, A. The Future is the Present: Artificial Intelligence in Pharmaceutical Manufacturing. 

Human medicine arguably began when early healers created simple botanical preparations to treat a small number of people living near them. The large-scale electrical machines of the Industrial Revolution turned human medicine into the global pharmaceutical industry of today. This revolution exploded drug availability for patients; most adults in the United States now use at least one prescription drug every year. But some are now asking whether this large-scale, fixed-location manufacturing paradigm benefits patients as much as it could. Could a return to the roots of smaller-scale, localized manufacturing for some medicines offer benefits to patients?

The COVID-19 global pandemic revealed the limitations and rigidity of the traditional manufacturing paradigm. Because building a new brick and mortar facility takes time, manufacturers of drugs to treat patients with COVID-19 relied heavily on moving their processes among existing facilities to meet a rapidly changing and nonuniform global demand. It became a challenge for manufacturers to export and ship certain drug products due to human safety and other precautions. Technologies that enable more localized manufacturing would avoid these supply chain problems and allow for a rapid and focused response to patient demand.

Distributed and point-of-care manufacturing

Several pharmaceutical manufacturers are now developing smaller, more mobile drug manufacturing processes that can be deployed to multiple locations, including at the site of patient care. These distributed and point-of-care manufacturing technologies have the potential to improve the drug supply chain by providing enough flexibility and agility to address local patient needs. In the future, distributed manufacturing units might be deployed at a site during a public health emergency to meet local demand or at a healthcare facility to meet the specific needs of its patients.

Similar technologies may aide soldiers on a battlefield. The US Defense Advanced Research Projects Agency (DARPA) has long made investments in innovative pharmaceutical technologies to address the logistical obstacles of manufacturing and delivering drugs to soldiers on the front lines. The process of manufacturing, storing, and airlifting pharmaceuticals to soldiers on a battlefield can range from weeks to months. The military recognizes the potential value of a quicker and more agile approach to manufacturing near the point of care for frontline soldiers. The ultimate vision for their investments is effective small-batch pharmaceutical production without the need for stockpiling, cold storage, and complex logistics.

If a future with distributed and point-of-care manufacturing doesn’t look like traditional brick and mortar manufacturing, what might it look like? Prefabricated, mobile, modular manufacturing units might move frequently between different geographical locations. Manufacturing units at multiple locations, perhaps even 3D printers at patients’ bedsides, may operate under a single remote quality management system. This is no longer science fiction. FDA has seen some of these technologies from developers of distributed manufacturing processes.

While FDA’s Center of Drug Evaluation and Research’s (CDER) does not have any approved drugs in its current purview made with distributed or point-of-care technology, experts know they are coming. A paper in the

 co-authored by representatives of four pharmaceutical companies tells of the “move toward adoption of point-of-care manufacturing to support on-demand patient access to medicine” (1). To glean more, CDER funded and participated in a series of workshops held by the National Academies of Sciences, Engineering, and Medicine (NASEM) to identify potential technologies FDA may see in the future. Distributed and point-of-care technologies featured prominently in NASEM’s resulting report, which predicts that mobile, end-to-end systems, “are becoming mature and robust enough to push the regulatory envelope within five to 10 years” (2).

CDER established an Emerging Technology Program (ETP) in 2014 to work collaboratively with companies wanting to implement innovative manufacturing technologies in advance of regulatory submissions. Companies developing distributed and point-of-care technologies are now actively working with CDER’s ETP and preparing regulatory submissions. Sau “Larry” Lee, senior scientific advisor to the ETP explains, “The ETP brings together FDA staff focused on application review, inspection, and policy to work with companies prior to submitting an application. Some of the needs of these companies relate to science and technology, but many relate to the policy framework.”

Of course, policymakers created the existing regulatory framework for pharmaceutical manufacturing while manufacturers were creating the modern brick-and-mortar manufacturing industry. As some manufacturers now evolve toward these smaller and more distributed manufacturing paradigms, the regulatory framework may need to similarly evolve to enable the timely adoption of these technologies while keeping patients safe.

To meet this need, CDER developed the Framework for Advanced Manufacturing Evaluation (FRAME) initiative to establish such a regulatory framework that considers new possibilities for how drugs are made and provides clarity for manufacturers developing advanced technologies. A regulatory framework is complex because it encompasses many different elements including guidance, regulations, statutory authorities, application requirements, and standards. Many of these elements impact stakeholders beyond CDER. A key regulatory challenge is addressing both current and future technologies by considering how any framework change would affect existing technologies regulated across FDA. Ashley Boam, director of CDER’s Office of Policy for Pharmaceutical Quality, shares, “As CDER has navigated through the various components of the regulatory framework, it has by necessity turned into a highly collaborative FDA-wide effort.” The first, and arguably most difficult, step is identifying the existing areas of policy that FDA may consider addressing.

CDER is now increasing outreach to public stakeholders and asking for their input to better identify these areas of policy consideration for distributed and point-of-care technologies. CDER released a discussion paper to solicit public input on distributed and point-of-care manufacturing by Dec. 13, 2022 (3). This discussion paper presents areas of consideration for policy development based on CDER’s evaluation of the existing regulatory framework. Interested stakeholders were also invited to a public workshop held by the Product Quality Research Institute to share input on key questions related to these technologies, such as:

How can manufacturers ensure location changes do not impact product quality?

How could a new paradigm consisting of a “centralized quality system” at one location and multiple manufacturing units at others comply with current good manufacturing practice (CGMP) regulations?

What type of business relationships are envisioned between health care facilities and companies developing point-of-care manufacturing platforms?

Answers to questions like these will help guide the development and implementation of an appropriate regulatory framework. In the future, CDER plans similar efforts to capture public input on the use of artificial intelligence in drug manufacturing.

FDA is not alone in preparing for advanced manufacturing technologies. The United Kingdom’s Medicines and Healthcare products Regulatory Agency (MHRA) is considering a new regulatory framework to enable the safe development of point-of-care products. Similar to CDER’s FRAME initiative, the MHRA’s new point-of-care regulatory framework aims to adapt regulations that do not create barriers for the implementation of advanced technologies yet ensure that drug products adhere to good manufacturing practices. Like FDA, MHRA has also sought public input to clarify if and how the point-of-care framework will impact other types of manufacturing and provide a level of flexibility that is absent from the current state.

While the advancement of these innovative technologies on a large scale might increase the robustness of pharmaceutical manufacturing and reduce local drug shortages, a distributed and point-of-care manufacturing paradigm is not a panacea. For example, the ability to meet localized demand will require raw or starting materials that are distributed efficiently to the sites of manufacture. Still, if realized, Boam believes the future could be bright, “I could envision a scenario in which patient care and access to medicines are vastly improved because of these innovative approaches to manufacturing.” For his part, Lee posits, “I think pharmaceutical manufacturing is on the verge of reconstruction; we have reached the point where change is necessary to improve quality and access.” Patients are ready for the benefits of a more reliable and robust drug supply chain, and FDA is ready to make sure that the US regulatory framework doesn’t keep patients from realizing these benefits.

Innovations in Pharmaceutical Manufacturing on the Horizon: Technical Challenges, Regulatory Issues, and Recommendations 

(National Academies Press, Washington, DC, Feb 24, 2021).

Distributed Manufacturing and Point-of-Care Manufacturing of Drugs


Volume 46, Number 12
December 2022
Pages: 28-29

When referring to this article, please cite it as A. Fisher, “Nurturing Manufacturing Agility," 

Some manufacturers are developing smaller, more mobile drug manufacturing processes for point-of-use patient care. 

Nurturing Manufacturing Agility

Pharmaceutical manufacturers employ sophisticated strategies to shorten the time to product launch, but how many consider adopting an advanced manufacturing technology as a strategy to do so? It turns out that manufacturers who have adopted continuous manufacturing have shortened their time to FDA approval and their time from approval to product launch. Might this strategy work for others?

When Stelios Tsinontides joined FDA as director of the Office of Pharmaceutical Manufacturing Assessment in October 2019, he saw the full landscape of global pharmaceutical manufacturing for the first time. He noted there were only six FDA-approved applications using continuous manufacturing for solid oral drug products. Despite his 29-year career in the pharmaceutical industry, he was puzzled as to why so few manufacturers had embraced continuous manufacturing. “I just assumed that many more pharma manufacturers would have embraced this technology given its widespread adoption in other industries,” he explains. Then he set out to understand why. “I heard through our engagements with manufacturers that they had concerns about FDA’s application review delaying their product launches as well as some concerns related to postapproval changes and inspections,” he says.

Now concerned himself, Tsinontides initiated an internal audit of applications to FDA’s Center for Drug Evaluation and Research (CDER), and the findings surprised even his most seasoned colleagues. Rather than delaying product launches, the audit found that FDA had approved applications employing continuous manufacturing three months faster than those employing traditional batch manufacturing. What’s more, these products also hit the market faster after approval. Based on the sales figures for these drugs, these continuous manufacturers enjoyed $100 million–$500 million of earlier revenue based on their shortened launches. “Once I saw these numbers, I knew based on my industry experience that this story needed to be shared broadly with pharma decision-makers,” he says.

Tsinontides wasn’t the only one curious about the slow adoption of continuous manufacturing for pharmaceuticals. In 2020, Clifford Rossi, a professor at the University of Maryland School of Business and a financial risk expert, began to explore the financial aspects of continuous pharmaceutical manufacturing. “For decades, it’s been significantly cheaper to manufacture overseas, especially in China,” he says. “I assumed that pharma manufacturers were not investing in continuous manufacturing due to the financial risks and economics, and perhaps even due to tax rates.”

To investigate further, Rossi developed a stochastic financial model that also showed him something different than expected. Continuous manufacturing in new facilities provided economic benefits and even an economic advantage for US manufacturers as compared to batch manufacturers abroad. He found the contribution of continuous manufacturing to the expected net present value over the life cycle of a drug to be nearly $500 million. “When comparing investments in continuous or batch strategies for a new US facility, the results clearly suggest that the lower costs associated with continuous manufacturing should lead to more investment in it—even for generic firms,” he says. “It seems that continuous manufacturing may not only be worth the investment, but its adoption could also help to reshape global pharmaceutical supply chains.”

As the data from CDER’s audit and the University of Maryland study began to trickle in, Tsinontides started to wonder how FDA had approved applications with advanced manufacturing technology so fast. He reached out to his colleague Sau “Larry” Lee, PhD, senior scientific advisor to CDER’s Emerging Technology Program, to understand. “For those wishing to adopt a new technology, CDER created an Emerging Technology Program to allow early engagements with the agency, even prior to filing a regulatory submission,” informs Lee.

Formed in 2014, the program allows an organization to meet with FDA experts from review and inspection programs to discuss and resolve potential regulatory issues prior to filing a submission. It turns out that all of the FDA-approved continuous manufacturing applicants had engaged with CDER’s Emerging Technology Program. “We’ll engage with those adopting new technologies, and our early interactions do not even need to be product-specific,” says Lee.

The application to participate in the Emerging Technology Program is a straightforward document with a five-page limit that includes basic items such as a description of the technology and an explanation as to why it is substantially novel. “It’s very important that applicants to the program describe how their proposed new technology could potentially improve product quality,” Lee notes. “We try to develop familiarity and internal expertise on their technology so we can carry that forward to the application assessment and facility inspection.”

Pharmaceutical manufacturers that move toward adopting advanced manufacturing benefit from increased support from FDA in the short term and can reap the rewards of using an advanced technology in the long term. The Emerging Technology Program has not only been effective in helping manufacturers expedite their product launches, but it is also well-received by participants who rate their satisfaction with the program an 8.9 out of 10 in exit interviews. Of course, a technology cannot remain emerging forever. This high level of regulatory engagement on continuous manufacturing will not continue indefinitely as technologies mature and adoption becomes more widespread.

Engagements with the program may explain how continuous manufacturing applications were approved quickly, but Tsinontides still wondered how these products had hit the market faster after approval. Most pharma manufacturers employ batch manufacturing, a process in which material is manually moved from one unit operation to the next, and product is made one batch at a time. Drug manufacturing has largely been conducted this way since the middle of last century. “After approval, batch manufacturers typically need to complete scale-up transfer, which can involve qualifying larger equipment, updating processes, and completing performance qualification for the commercial-scale process,” explains Tsinontides. “All of this takes time and effort.”

Many industries such as commodity chemicals and food processing have embraced continuous manufacturing as their default means of production, due to advantages including shorter processing times, reduced waste, and a smaller footprint. Continuous manufacturing uses an unbroken flow of material from one unit operation to the next with no stops in between, bringing opportunities for improved efficiency and fewer errors. “Continuous manufacturing also allows for agility related to production timing and rate, and is not necessarily a 24/7 production,” says Tsinontides.

While multiple factors can determine the time between drug approval and marketing, manufacturing scale-up by increasing equipment size is often the bottleneck. Continuous operations, by design, require fewer process and equipment changes to reach commercial-scale operations. Changes to accommodate the commercial scale in continuous processing typically involve simply increasing the run time on the same equipment and with the same controls. The decrease in time to market after approval, alone, accounted for $50 million–$125 million of the early revenue for continuous manufacturers.

FDA’s audit also looked at the regulatory burden for those adopting continuous manufacturing, related to making postapproval changes and being subject to pre-approval inspections. The FDA audit found that there was not a substantial difference in the number of process changes reported by batch and continuous applicants. However, continuous applicants reported no changes related to equipment, processing conditions, or batch-size range. Tsinontides says, “This observation aligns with the fact that continuous processes are often designed to have inherent flexibility to tailor production to demand.”

An FDA pre-approval inspection was conducted for the majority of batch products and all of the continuous products. “While continuous applications had more process-related issues observed during inspections than batch applications, it stands to reason that as FDA’s confidence in continuous manufacturing increases, the need for pre-approval inspections and the number of process-related issues should lessen,” contends Lee. The most important finding for continuous manufacturers was that pre-approval inspections did not adversely impact application approval timelines, as all were approved in the first FDA review cycle ahead of the goal date.

Owing to his engagements with technology developers in the Emerging Technology Program, Lee found another issue faced by manufacturers wanting to adopt continuous strategies. Many had faith in FDA’s willingness and ability to approve continuous manufacturing applications but had doubts about that of other global regulators. Often manufacturers deal with dozens of global regulators for a single international product launch.

To address this problem, Lee initiated an international effort to describe harmonized scientific and regulatory considerations for continuous manufacturing. The result was an international guideline on continuous manufacturing dubbed ICH Q13. “The goal of ICH Q13 is to commit regulators to consistent adoption of consensus-based guidelines to realize the benefits of continuous manufacturing for patients as well as industry,” says Lee. The ICH Q13 guideline has undergone global public consultation and is expected to be finalized before the end of the year. FDA’s hope is that manufacturers will have more confidence in the global regulatory support for continuous manufacturing adoption.

As continuous manufacturing transitions from the innovators to the early adopters in pharma, it seems the question is when, not if, pharma will broadly embrace continuous manufacturing. The rapidly changing demand caused by COVID-19 displayed the value of manufacturing agility and the problems caused by long, tangled supply chains and time-consuming manufacturing technology transfers. Many saw continuous manufacturing as a potential solution to these problems.

As continuous manufacturing hit the spotlight in 2020, so did its funding. The federal government alone awarded nearly $500 million to companies developing domestic continuous manufacturing technologies. Some of these technologies now approach maturity and regulatory filings, leaving FDA in a challenging but promising position.

Adam C. Fisher, PhD is Director of Science Staff, Office of Pharmaceutical Quality, Center for Drug Evaluation and Research, FDA.

FDA backs the benefits of adopting continuous manufacturing, a strategy which has accelerated approval and launch timelines, and its Emerging Technology Program could be a helpful tool.