AI, digital twins find their footing in pharma manufacturing: report

With artificial intelligence well-established in drug discovery, AI is increasingly being utilized in pharmaceutical manufacturing as drug manufacturers look to make production faster, more reliable, and easier to manage, according to a new report from data and analytics firm GlobalData.

“Rather than replacing established manufacturing practices, AI is being harnessed to strengthen them,” Edita Hamzic, analyst at GlobalData, said in a statement. “Companies that see AI as part of their operational model, not as a standalone technology project, are most likely to benefit.”

Using digital twins, a virtual representation of a physical system that is continuously updated with real-world data and used to simulate, predict, and optimize performance, manufacturers run simulations that can identify potential errors and optimize processes before committing to a physical run.

Digital twins, predictive maintenance, and real-time quality monitoring are being used to minimize downtime, reduce waste, and improve batch consistency, according to GlobalData, which contends the industry’s major challenge is to maximize supply for existing assets where manufacturing capacity is limited.

“The primary AI opportunity in pharma manufacturing is to improve the performance of existing facilities without the need to build new infrastructure,” GlobalData said.  

However, the report cautioned that AI remains an emerging capability rather than a fully established one in pharmaceutical manufacturing, with many drugmakers still testing these tools in pilot programs.

“There is an urgency to those assessments because pharmaceutical manufacturing is under pressure to meet increasing demand, particularly in high-value therapy areas such as obesity and diabetes,” according to GlobalData.

At Eli Lilly, digital twins have moved from pilots to production-scale tools. Lilly is leveraging AI to scale manufacturing and optimize operational efficiency to meet the high demand for its medications, including GLP-1s.

Scot Lindsey, Lilly’s senior vice president and information officer for manufacturing and quality, told Pharma Manufacturing earlier this month that the combination of the drugmaker’s domain expertise and the power of AI is translating into real-world success, including the implementation of digital twins to virtually simulate scale-up processes, pinpoint potential bottlenecks, and fine-tune parameters prior to physical production.

While many pharmaceutical companies are investing in AI, implementation remains the biggest challenge, Hamzic warned, with drugmakers facing hurdles with outdated systems, uneven data quality, and problems moving from pilot projects to routine use in highly regulated environments.

“Success will therefore depend on execution and the ability to combine manufacturing expertise with digital infrastructure in day-to-day manufacturing operations,” Hamzic said.

Regulators embrace AI, with caveats

According to GlobalData’s report, AI is starting to be “hardwired” into U.S. and European pharmaceutical manufacturing regulation. Last month, the U.S. Food and Drug Administration (FDA) unveiled a one-day inspectional assessment pilot to complement the agency’s standard inspections.

The pilot, which will continue through the end of September 2026, is being conducted across multiple FDA inspectorates including biologics, clinical research programs, and medical products. The agency is leveraging AI to identify facilities for one-day inspections at both domestic and overseas sites.

The FDA is “exploring the use of AI to identify lower-risk sites so that inspectors can focus on facilities where compliance concerns are most likely to arise, but the criteria behind that is opaque,” GlobalData said. At the same time, the report noted that the European Medicines Agency (EMA) is more focused on safeguards around the use of AI.

EMA “sees AI as a useful tool across the whole medicine lifecycle but only if it’s used in a transparent and human-centered way,” according to GlobalData, which emphasized that the debate in pharmaceutical manufacturing is now on where AI can deliver the greatest operational and regulatory value.

AI is “becoming increasingly important in drug manufacturing as the sector moves towards systems that link production, quality, and regulation more closely than before,” Hamzic concluded.