Jennifer Markarian is a contributing editor for 

Jennifer Markarian

Financial data document graph chart report statistic marketing research development planning management strategy analysis accounting. Financial business technology hologram concept. 3d rendering. | Image Credit: © Chaosamran_Studio - stock.adobe.com

Digital technologies are evolving rapidly and offer benefits for bio/pharmaceutical manufacturers and developers who seek digital transformation. New artificial intelligence (AI) and machine learning (ML) tools help manage, transform, and analyze data—including data coming from process analytical technology (PAT) tools—so it can be better used to develop process insights or for process control. Early adopters of these technologies have been process development laboratories, but implementation in commercial manufacturing is emerging.

“Historically, PAT has been used to define processes and build control strategies, but its integration into manufacturing has often been limited,” says Michalle Adkins, director of life sciences strategy at Emerson. She points to the emergence of inline spectral PAT, which makes it easier to embed spectral waveform data directly into control systems, as a significant advance.

“We’re also starting to see OEMs [original equipment manufacturers] including PAT in their offerings with their bioreactors, which signals a broader readiness to integrate advanced analytics not only in process development but also in commercial manufacturing,” Adkins says. “These initial steps are building the foundations to lead to these technologies rolling out to bigger scale solutions in the future.”

Currently, AI-based tools are often used to create process insights that people on operations teams can use to improve processes, but eventually AI tools will allow more automated control, suggests Ryan Thompson, senior specialist, Industry 4.0 at CRB.

“Huge strides are being made in bioreactor productivity (e.g., higher titers) and chromatography efficiency using these tools,” Thompson says. “The next big step will be [to take] the person out of the middle and have truly AI-based closed-loop control.”

The convergence of AI and ML with advanced process control is helping to address some particularly difficult measurement and control areas, adds Adkins.

“Additionally, regulatory bodies are increasingly open to and encouraging the use of these more automated approaches, particularly as companies are demonstrating success in both process development and targeted projects,” Adkins says. “With early successes demonstrated in bulk drug substance processes such as fermentation and purification, along with pilot-scale manufacturing, broader adoption is expected across the manufacturing lifecycle.”

Challenges and solutions for commercial manufacturing

A recent initiative by the BioPhorum IT Digital and Data collaboration tackled the need to need to improve collaboration and transparency between sponsors and contract manufacturing organizations (CMOs) in the area of deviation management.

“Historically, deviation management has been largely manual and fragmented, leading to inefficiencies, delays, and miscommunication,” says Ciera Clayton, Global Change Facilitator at BioPhorum. “Many companies still operate in the ‘predigital’ stages—where deviation information is exchanged manually, often via email, spreadsheets, or paper-based systems. These methods are prone to delays, errors, and lack of traceability. BioPhorum members recognized that digitizing this process could significantly enhance data integrity, accelerate issue resolution, and foster a more proactive quality culture across organizational boundaries.”

The BioPhorum IT Digital and Data, Digital Integration of Sponsor and Contract Organizations (DISCO) team published a paper in July 2025 to share its vision for digital deviation management (1). The group found that gaps between digital maturity of CMOs and sponsors caused difficulty in data exchange and decision-making.

“We have also learned that interoperability and shared digital standards are key to bridging these gaps,” says Clayton. “Even when one partner is more advanced, establishing common data formats, governance models, and secure exchange protocols can enable meaningful collaboration. Trust and transparenc are key; when partners align on expectations and invest in interoperability, they can overcome maturity mismatches and unlock significant value.”

Next steps from the DISCO team members aim to translate their vision into practical and scalable solutions, Clayton says. For example, one task is to develop standard data structures and integration specifications, with a focus on interoperability, good practice compliance, and scalability across multiple products and sites.

Work by other teams in the BioPhorum IT Digital and Data group will also inform the deviation management project. For example, the AI Validation team is publishing guidance to define frameworks for implementing AI in regulated environments, which will ensure that digital deviation data and other manufacturing insights can be leveraged responsibly, Clayton explains.

Digital Deviations: Improving Sponsor-CMO Collaboration

Moving from process development to commercial manufacturing requires technology to be robust and designed for use by operators on the factory floor.

“If new technologies add uncertainty or additional steps, they’re unlikely to be widely adopted,” notes Adkins. “Historically, that has been a challenge, but we’re starting to get over those complications as the technologies themselves mature. Today’s solutions are far more robust and designed for high-performance environments.”

Technology transfer is another concern. “Teams need to be sure that when they change the scale, it won’t change the outcomes,” Adkins says. “They need collaborative software solutions designed specifically to help navigate scale-up and scale-out.”

Data handling is also a crucial issue. “Process data on the factory floor is generally unstructured and lacks context,” says Thompson. “It takes a lot of time and effort to search, organize, and clean data before [they are] useful for AI/ML algorithms.”

Large quantities of data are needed, however, because AI/ML accuracy and insights improve with the quantity of data.

“Data modeling is a necessary first step to meaningful AI/ML, where process data and modern architectures, such as a unified namespace, should be considered,” Thompson suggests.

“One of the most critical—and often underestimated—elements of effective data analytics in pharma manufacturing is context,” agrees Adkins. “Teams must be empowered to generate and preserve context as data flows across the enterprise. Whenever context needs to be reconstructed, the value of that data diminishes. It becomes harder to use, more expensive to manage, and slower for driving meaningful action. That’s not just a technical challenge—it’s a strategic one.”

Emerson’s new digital platform will enable integration of disparate industrial automation technologies, according to Adkins. A centralized data model will allow teams to collect full context and share the master data across solutions without needing redundant definitions in separate systems (e.g., the distributed control system, the manufacturing execution system, and others), Adkins says.

“The enterprise operations platform will eliminate that fragmentation by creating a common data platform that distributes consistent equipment information across all solutions via a shared data fabric,” Adkins says. “This not only simplifies data management but also strengthens the foundation for more autonomous and scalable operations.”

Using the approach of managing data as a product, the platform is designed to make data findable, accessible, interoperable, and reusable (i.e., the FAIR principles).

“This approach enables scalable, AI-ready data environments that support both operational efficiency and innovation,” says Adkins.

Digital twins are tools that have found success in process development and promise additional benefits in manufacturing control strategies. The integration of PAT data with a digital twin of a process offers multiple benefits, says Andrew Whytock, head of Digitalization for Pharma at Siemens, which supplies digital tools including digital twins and the Simatic Sipat software platform for implementing PAT in pharmaceutical development and manufacturing.

“Integrating PAT enables right-first-time production, as real-time data and predictive models minimize errors and ensure quality from the very beginning,” Whytock explains. “This integration also leads to improved yields, with continuous feedback and optimization enhancing output.”

Whytock says that a digital process twin can minimize physical experimentation and significantly reduce development time through virtual testing and optimization in the digital twin. Although these tools can allow significant efficiency gains and faster time-to-market, a potential hurdle is the initial investment cost for infrastructure, software, and integration of disparate processes into a unified, data-driven approach.

In addition, says Whytock, “Overcoming the reliance on extensive physical experimentation, a long-standing practice in biopharma development, demands a paradigm shift in how processes are designed, tested, and scaled up. This transition also necessitates specialized expertise in data science, modeling, and automation, which may not be readily available internally, requiring significant training or external consultancy.”

Digital twins can be used for batch processes and are fundamental for continuous processes, for which process automation is crucial, suggests Whytock. Continuous manufacturing saves space, reduces costs, and speeds up the path from lab to patient, he says, but the shift from batch to continuous still faces resistance due to perceived risks and question marks about return on investment.

“Ultimately, the challenge lies in navigating the complexities of digital transformation while ensuring compliance, maintaining product quality, and realizing the full efficiency gains offered by these cutting-edge solutions,” he explains.

Although AI tools and digital twins may be used in various ways to improve quality and potentially enable closed-loop control and real-time release, process understanding remains crucial. In a 2024 survey of pharmaceutical and biotechnology companies, CRB found that intelligent devices and smart data (e.g., PAT) are indeed already being used by more than half of respondents for real-time batch analysis (i.e., process understanding) and by 40% of respondents for real-time batch release (1). A smaller segment (24%) reported using in-line or online sensor technology for real-time batch correction.

“Process understanding is a key component of being able to leverage AI into batch analysis, release, and correction,” cautions Thompson. “Relying on AI without a detailed process understanding will lead to implementations that cannot be validated—and of course, the rigor required increases as companies move from analysis, to release, to correction.”

A July 2025 publication from the International Society for Pharmaceutical Engineering (ISPE) GAMP Community of Practice, Software Automation and Artificial Intelligence Special Interest Group offers best practices for approaching AI projects integrated with current regulatory guidance (GAMP was formerly known as the acronym for good automated manufacturing practice) (2). The guide covers a broad range of use cases, including use of AI in data analysis for applications such as real-time release.

“An innovative approach combining PAT and AI models alongside robust control strategies can enable faster and more reliable product disposition by analyzing critical quality attributes in real-time rather than relying solely on end-product testing,” says Brandi Stockton, founder and managing partner of the Triality Group and lead of the ISPE GAMP AI Guide initiative.

“AI has the potential to enhance PAT by capabilities to identify subtle patterns in large amounts of data and support predictive control strategies by dynamic optimization of parameters to reduce process variability,” adds Martin Heitmann, consultant at the Triality Group and co-lead of the ISPE GAMP AI Guide initiative. “In process development, AI may reveal relationships between variables that traditional methods may miss, accelerating scale-up and tech transfer. Several key challenges to consider include data availability and quality, explainability and integration with existing control systems.”

The pharmaceutical industry has a reputation for being slow to change, but the fast pace of AI development may be altering that paradigm. Thompson says that AI has become a strategic necessity in the drug discovery and information technology functions of pharma companies. Although adoption of AI has been slower in the manufacturing side, Thompson predicts rapid adoption will occur as service providers start demonstrating successful implementations and manufacturers see the benefits.

“In the past three to five years, I have seen real changes [from] pharma being an insular industry to one seeking ideas from other sectors,” suggests Thompson. “AI is absolutely being adopted rapidly in pharma, and companies are creating new organizational units to invest in and [obtain] value from AI. It is slower to be adopted directly on the factory floor, but pharma companies are embracing AI more than most other manufacturing sectors, as they have much more to gain than typical companies.”

2. Stockton, B.; Heitmann, M.; Staib, E.; et al. 

Articles

Digital technologies, particularly AI and ML, are transforming bio/pharmaceutical manufacturing by enhancing data management and process control. Early adoption has been seen in process development, with commercial manufacturing beginning to integrate these technologies. AI tools are improving bioreactor productivity and chromatography efficiency, with potential for fully automated control. Challenges include technology robustness, data handling, and technology transfer. Digital twins and PAT integration offer benefits in process control and efficiency. The pharmaceutical industry is gradually embracing AI, with significant potential for innovation and efficiency gains.

Advances in digital technologies offer effective data handling for bio/pharma manufacturing.

Optimizing Data Use for Digital Transformation

Concept health and beauty. Close-up of Medical Ampoule Production Line at Modern Modern Pharmaceutical Factory. Glass Ampoules are being Filled. Medication Manufacturing Process. | Image Credit: ©volodyar - stock.adobe.com

Pharmaceutical manufacturers continue to look to automation for efficient fill/finish of parenteral drugs, and new robotic automation technologies offer the opportunity to further improve flexibility and efficiency. New robotic technologies also aim to eliminate the need to open an isolator to perform interventions to better comply with the European Union’s Annex 1 requirements for closed systems (1).

At INTERPHEX 2024, equipment supplier, Steriline, demonstrated a new robotic filling machine that uses a magnetically levitated system to transport containers (e.g., vials, syringes, cartridges) instead of conventional mechanical transport. The most significant benefit of this planar motor technology is lower particle generation due to the “zero friction” motion as containers are transported from one station to another, the company explains. Robots are used for loading and unloading, which allows a closed system that is designed for flexibility. The robotic arms can handle multiple container formats, which means it needs fewer change parts.

“The filling machine has the flexibility needed for small batches and can be optimized for the requirements of each process,” adds James Rorke, vice-president of North American Operations, Steriline. “Using asynchronous processing, the timing of each step can be adjusted as needed.”

Steriline uses sensors to detect inaccuracies in filling and stoppering, and the equipment is designed with a method to reprocess noncompliant pieces. In the automation system, the containers can move backwards, for example, to fix a stopper that is flagged during the 100% checkweighing and inspection step, Rorke explains. The design is part of what the company calls its zero-loss philosophy, which continues to move toward more efficient production.

All pharma equipment for aseptic manufacturing must be designed in compliance with good manufacturing practice (GMP) requirements and, in Europe, the new, recently approved Annex 1 guideline, asserts Paolo Simonazzi, sales director for Americas at IMA Life, which is one of three pharma divisions of the IMA Group. One of the most important challenges for the management of contamination risk is the first air protection principle, he confirms. Designers use computational fluid dynamics to simulate airflow, and the robotic automation is set up so a minimal amount of steam-sterilized parts, such as the filling needle but not any part of the robot, passes over the top of the open vial or other critical surfaces.

The company’s new Injecta fill/finish system is entirely robotized, allowing flexibility for switching between formats and minimal change over time. Compared to traditional automation, robotic automation has less movement and is therefore cleaner, IMA explains. The fully robotic equipment was installed late in 2023 in a new Bayer facility for parenteral medicines in Germany (2). A key requirement was that the machine automation would generate data for paperless production and integrate into Bayer’s management system.

New technologies in development allow an operator outside of an isolator to use a robotic arm to perform interventions inside the isolator without breaking the barrier. One of the drivers for the new technology is better compliance with Annex 1, explains Irina Rau, regional sales manager for Stäubli Robotics. Another advantage is avoiding opening the isolator, which would mean losing a batch of product. A challenge is to design the robot’s movements to ensure the ease of use for all operators. Flexibility, sensitivity, and making sure the process stays safe for the equipment and operators are all important. Stäubli has worked with telemanipulation technologies from multiple suppliers, including Force Dimension and SRI, and showcased a use case with AST during INTERPHEX 2024.

A telemanipulation system for sterile manufacturing environments from SRI, a nonprofit R&D institute, is a new extension of SRI’s technology that has been used for decades in robotic-assisted surgeries, as well as other remote applications, such as bomb disposal. SRI’s XRGo software is integrated with commercial third-party robots for remotely controlled repair and maintenance functions inside a sterile area, such as an isolator. This technology is particularly useful for infrequent activities that are not easily automated, such as changing a filter, fixing a machine jam, or cleaning up a broken glass vial, specifies Bill Rusitzky, general manager for XRGo at SRI. Today, these activities are performed either through gloves mounted to the isolator or by sending a gowned operator into the sterile environment, both of which present challenges. As an alternative, robot telemanipulation allows a robotic arm that is fitted with an end effector to be controlled from outside the isolator, operating as a remote extension of the operator’s arm and hand. The operator sees the action of the end of the robotic arm through 3D stereo streaming video to a virtual reality (VR) headset, and the handheld controller provides haptic feedback. A VR interface provides an augmented-reality environment and can add additional views or repair manuals. The video recording and other data can be used to document interventions digitally.

Although automation has historically been used for high-volume and large-scale processes, new technologies are driving automation down to smaller volumes. Comecer demonstrated its new semi-automatic system for cell and gene therapy filling, ValueCell FILL, at INTERPHEX 2024. The automated system fills 150–175 bags/h from a large mixing bag to smaller bags, which are thermal welded in preparation for freezing. A controller for the mixer allows flexibility in the parameters and in the fill size of the bags. Automation replaces gowned operators performing manual pipetting, which helps alleviate the problem of workforce shortages.

Catalyx, which specializes in automating pharmaceutical manufacturing, inspection, and packaging processes, sees increasing uses of robotic and artificial intelligence-assisted automation. For example, kitting for clinical manufacturing is a high-mix, low-volume packaging process that benefits from robotic automation, because the robot can be programmed to package whatever is needed (e.g., vials, syringes, pens, and leaflet inserts), with very low error rate, says the company, which delivered a system for this application late in 2023. The system uses Catalyx SmartFactory Machine Vision guidance for picking and placing.

“Telemanipulation adds value because the operator can perform the activity remotely,” says Rusitzky. “The operator doesn’t need to be within feet of the equipment; they can be down the hall or the next building. The stereoscopic camera view adjusts automatically so that the operator always feels directly behind the robotic hand. The precise video provides an intuitive, natural understanding of the scene, and the user interface allows people to use it with very limited training.”

Rusitzky explains that the software restricts where the robotic arm can move, so that it doesn’t damage equipment in the isolator. The robot is also programmed to move at the correct speed to avoid disturbing the air inside the sterile environment. SRI has worked with third-party robotic companies, such as Stäubli and Denso, and the system is available for testing use cases.

As with any process change, use of robotic telemanipulation will need regulatory approval before being used in a commercial, GMP process. FDA regulators are aware of the technology, adds Rusitzky, and see that it can be useful.

“Across the pharmaceutical industry, we hear that adoption of this type of technology is a question of ‘when’ not ‘if’,” Rusitzky claims.

“We expect that robot telemanipulation will play a vital role in ensuring precision, efficiency, and safety in pharmaceutical manufacturing,” Jean-Maxime Guay, senior manager, Manufacturing Intelligence at Pfizer, said in a statement. “By allowing people to manage issues without requiring proximity to the process, this technology would help aligning with the new EU [European Union] GMP Annex 1 revision through contamination risk mitigation, in addition to decreasing operational costs.”

SRI is collaborating with INVITE Research, a nonprofit joint research venture formed by Bayer Pharmaceutical and other companies to allow precompetitive collaboration to introduce technologies that can be broadly adopted across the pharmaceutical industry.

Charly Coulon, head of Future Manufacturing Concepts at INVITE, says that telemanipulation is crucial for keeping people out of the sterile environment. “No matter how much effort you put into automation, there comes a time when something unexpected happens and requires you to utilize the unmatched flexibility of a human,” he explains. “Only telemanipulation will allow you to rectify the situation at that moment without sending a human in and breaking sterility.”

One of the challenges for telemanipulation is having enough space inside the isolator available for greater use of robots. In current designs, the isolator space is kept small, which allows people to reach spaces with a glove. In addition, automation systems increasingly use actuators and material guides to increase reliability and avoid incidents, specifies Coulon. Both of these trends limit space. “In my view, the biggest roadblock [to telemanipulation] is the necessary disruptive rethink to build systems differently and isolators significantly larger,” he says. Coulon suggests the effort to automate can be reduced by programming only the expected standard functions and using telemanipulation of robots for anything outside of standard. “[In these rare cases],” he remarks, “you combine the flexibility and ingenuity of a human with the physical presence of the robot on site from a distance.”

EC. Annex 1 Manufacture of Sterile Medicinal Products. 

IMA. Bayer Chooses Injecta for the Production of Parenteral Medicines. Case Study, 

®
Vol. 48, No. 9
September 2024
Pages: 22–23

When referring to this article, please cite it as Markarian, J. Advancing Robotic Automation. 

New technologies improve efficiency and remove operator intervention.

Advancing Robotic Automation

Drug target identification and lead optimization of hit compound candidates for orphan diseases | ©HYUNGKEUN - stock.adobe.com

Although biopharmaceutical production today generally takes place in centralized manufacturing facilities, industry and regulators are taking a close look at the benefits of decentralized or distributed manufacturing, which involves smaller and flexible-volume manufacturing operations in multiple locations closer to the site of use and even to point-of-care (POC) locations. POC manufacturing is seen as essential for efficiency in producing personalized medicines. In the near-term future, POC production is likely to be in a controlled environment such as a hospital, clinic, or pharmacy, while in the long term, POC production could extend to other locations. Such a model could enable quality drug production anywhere, from the battlefield to remote villages or even outer space, experts suggest.

The impetus for POC manufacturing comes in part from its potential to alleviate pressing problems, such as drug shortages, pandemic preparedness, and equitable availability of treatments. It is also driven by technological advances that promise to allow efficient and consistently high-quality production using new equipment, analytical tools, and quality control paradigms.

These technologies offer the benefit of making drugs much closer to where and when they are needed. “The advantages of making medicines on demand—to solve issues such as the difficulty of predicting demand and the complexity of the supply chain—are compelling,” states Govind Rao, professor at the University of Maryland, Baltimore County (UMBC) and director of UMBC’s Center for Advanced Sensor Technology.

FDA recognizes the need for flexible and agile manufacturing and sees the potential for portable, distributed manufacturing units to be used for POC manufacturing. In October 2022, the Center for Drug Evaluation and Research (CDER) published a discussion paper that highlighted areas to consider for drugs regulated by CDER as well as the Center for Biologics Evaluation and Research and called for public feedback (1). FDA and the Product Quality Research Institute (PQRI) also held a workshop in November 2022 to gather input from stakeholders. For advanced manufacturing technologies—particularly distributed manufacturing, POC manufacturing, artificial intelligence (AI), and end-to-end continuous manufacturing—seeking input is the first step in FDA’s new Framework for Regulatory Advanced Manufacturing Evaluation (FRAME) initiative, according to a presentation by Michael Kopcha, director of CDER’s Office of Pharmaceutical Quality (2).

The European Medicines Agency’s (EMA) Quality Innovation Group is focused on a similar list of advanced manufacturing technologies, which were discussed at a March 2023 focus group meeting (3). That decentralized manufacturing is being discussed is one reason for optimism regarding its uptake in Europe, suggests Celeste Lamm, director of Global Regulatory Affairs, CMC at Merck. In addition, she points to the European Commission’s proposed new directive (4) that includes a pathway for decentralized manufacturing within the European Union and provides an architecture for responsibility between a central site and decentralized sites. “However, the proposal limits decentralized manufacturing to applications where the central site is located within the EU, and it isn’t clear how the regulation would be applied if some of the decentralized sites were outside of the EU,” Lamm says.

Regulatory uncertainty is an ongoing challenge, with unanswered questions around how connected sites that are located in different regions will be regulated and a lack of global harmonization. Agencies in different regions are communicating with each other, and it is hoped that approaches will be similar. Because no final guidance has been released by any regulatory agency, any differences in requirements are still unknown, Lamm cautions.

Change will take time. Lamm sees similarities between the pace of adoption of distributed manufacturing and that of continuous manufacturing. “Both regulators and industry acknowledge the benefits, but adoption has been slow, because existing traditional manufacturing is frequently sufficient, and it can keep costs down to use existing facilities,” Lamm says. “Adoption of innovative manufacturing technology occurs gradually as there is opportunity to replace existing lines, where existing technology isn’t sufficient (for example, when local manufacturing is needed), and where there is enough clarity to calculate the long-term benefit to justify investment.”

A significant hurdle for distributed and POC manufacturing is how to ensure consistent quality of the drug product, but there is a growing availability of technologies that can meet this challenge. For example, prefabricated, portable cleanrooms and automated processes that fit in these spaces meet the need for standardization of equipment, process, and systems that is crucial to consistency. In addition, digital technology and cloud-based systems in use today make it easier to connect the data and quality systems of different locations. With these tools, distributed manufacturing can even reduce risk and contribute to consistency.

“Using enterprise quality systems across distributed sites is the natural extension of how we currently work in a global environment,” says Lamm. She says that regulators accept aspects of digitally connected quality system solutions, but they note that it is important to ensure that all personnel are similarly trained and are following the same practices.

“There are many flavors of distributed manufacturing for consideration when training personnel,” Lamm adds. Variations include the number of sites and the complexity of the manufacturing process. “The conversation regarding appropriate quality approaches for distributed manufacturing is ongoing, particularly for high volumes of sites or complex manufacturing processes. It is critical that we continue the dialogue between industry and regulators to address concerns.”

Quality assurance/quality control (QA/QC) methods for distributed manufacturing will need to be different from those currently used in centralized manufacturing, says Rao. His group at UMBC recently patented a method for using machine learning (ML) to ensure consistent product quality in UMBC’s Biological Medicines On-Demand (Bio-MOD) system, which uses a cell-free method for end-to-end continuous manufacturing of biologic drug substances (5).

“With cell-free manufacturing, one gene produces one protein in a process that is almost more like chemistry than biology in that it can be consistent,” says Rao. “Our ML algorithm can extract enough data from the process sensors and analytic measurements to get a high degree of confidence that everything about the process is consistent. If the process is the same, the product should be same. The algorithm can also identify any deviation from the expected, such as an air bubble or impurity. This automated function raises the safety level to a much higher level than the current method of testing a product after it is made.”

The Bio-MOD system is currently suitcase-sized, but could be scaled-out to larger volumes, says Rao. He adds that the ML approach can also be used in cell-based manufacturing.

Decentralized, POC manufacturing is particularly helpful for autologous cell and gene therapies (CGTs), because it solves some of the problems of long-distance, cold-chain shipping of patient-specific raw materials and finished products. Various technology providers have created closed, automated CGT manufacturing systems that aim to provide scalable throughput to meet the growing demand for CGTs in centralized or decentralized locations (6).

Sterile compounding is already occurring at point-of-care facilities, some of which are regulated by FDA as 503B outsourcing facilities under strict quality and safety guidelines. James Rorke, vice-president of North American Operations at Steriline, predicts that this rigor will, in the future, extend to some or all patient-specific 503A sterile compounding, which often takes place in pharmacies, hospitals, and institutional settings. Steriline’s Intelligent Compounding System (ICS) meets the need for aseptic patient-specific compounding in a compact footprint, Rorke says.

In the ICS, check-weighing provides the data to prove that every single container has been filled to the optimal volume, explains Rorke. “Incorporating 100% check weighing while filling allows us to target the primary fill volume to the lower end of the acceptable fill range, such that variances in the fill volume are more likely to fall in the nominal range or under filled. If under filled, we add the additional volume of product to meet the requirement. This function practically eliminates over-filled rejects, and it tightens the process window to eliminate waste.”

Biotech company Orgenesis has targeted POC CGT manufacturing with its POCare Network and its Octomera Mobile Production Units and Labs (OMPULs). In June 2023, the company and one of its network partners, the University of California (UC), Davis, announced that OMPULs will be installed and operated by Orgenesis at multiple UC medical and academic institutions (7).

Decentralized and standardized manufacturing is crucial for getting CGTs to patients at a reasonable cost, says Vered Caplan, CEO of Orgenesis. She says that the OMPULs are standardized units that are operated with standard procedures.

“We have defined everything—raw materials, disposables, all the process parameters, cleaning parameters, the environment in and around the unit, all the equipment, and procedures,” Caplan explains. “The unit is not just a mobile cleanroom. It is a closed, automated mini-production facility with standardized, validated isolation units inside. These units can then be duplicated and located at different sites, either in a hospital or nearby. Because of their agnostic nature, we can augment them to many modalities and even applications such as apheresis, if needed, to complete the full value chain.”

Comparability testing of products from the different units will demonstrate that standardization produces comparability; the extent of testing is decided using risk analysis. Caplan adds that although product quality is built-in to the standard process, the decentralized sites will also have quality assurance oversight through centralized audits. “Our work is driven by compliance to the most current guidelines, and our flexible nature allows us to be responsive as we start to see [new regulatory guidance] come to fruition,” she says.

Caplan suggests that hospitals are driving demand for decentralized manufacturing so they can meet their patients’ needs. She says standardized manufacturing platforms like the OMPUL will provide consistent quality at lower cost than each hospital creating their own platform. Orgenesis is also working with solution and equipment providers to ensure that the team is aware of the latest technologies and that they can easily be incorporated into the platform, Caplan says.

CDER. Distributed Manufacturing and Point-of-Care Manufacturing of Drugs, Discussion Paper. 

Kopcha, M. A Regulatory Perspective on Innovations in Pharmaceutical Manufacturing. Presentation at the FDA/PQRI Workshop of the Regulatory Framework for Distributed and Point of Care Pharmaceutical Manufacturing (Nov. 14, 2022).

Listen and Learn Focus Group Meeting Report

EC, Proposal for a Directive Of The European Parliament And Of The Council on the Union code Relating to Medicinal Products for Human Use, and Repealing Directive 2001/83/EC and Directive 2009/35/EC (April 26, 2023).

Rao, G. et al. US Patent 11,685,892 B2. “Methods to Incorporate Machine Learning Analytics for Optimizing Protein Purity, Potency, and Quality in an On-Demand Production System for Point-of-Care Delivery” (June 27, 2023).

Markarian, J. Automation Aids Cell and Gene Therapy Production. 

Orgenesis. Orgenesis and University of California, Davis Sign Partnership Agreement for Rollout of Cell and Gene Therapy Mobile Processing Units and Labs Throughout California. Press Release, June 7, 2023.

Jennifer Markarian is manufacturing reporter for 

Volume 47, No. 11
November 2023
Pages: 12–14

When referring to this article, please cite it as Markarian, J. Considering the Promises of Point-of-Care Manufacturing. 

Emergence of advanced manufacturing technology to ensure quality of biopharmaceutical drugs combined with efforts to identify a regulatory pathway indicate that a distributed manufacturing model is within reach. 

Considering the Promises of Point-of-Care Manufacturing

The range of applications for twin-screw extruders as pharmaceutical manufacturing equipment—either as a stand-alone, continuous unit operation or integrated into a continuous manufacturing line—is growing. Hot-melt extrusion (HME), which involves melting and mixing polymeric excipients with APIs in a twin-screw extruder to produce an amorphous solid dispersion, is used commercially in multiple applications, including drug-loaded devices or as a solvent-free alternative to spray drying. Twin-screw granulation (TSG) uses a twin-screw extruder to make granules using dry granulation, wet granulation followed by drying either continuously or in a separate fluid-bed batch process, or melt granulation using a highly viscous binder.TSG was used in early powder-to-tablet continuous manufacturing lines, and commercial use continues to grow. Although direct compression can be used for some formulas in continuous manufacturing lines, TSG is important for others where direct compression isn’t suitable.

“In recent years, TSG processes have been advancing rapidly, particularly towards continuous manufacturing processes becoming standard in the pharmaceutical industry because of the potential benefits TSG offers,” says Hemlata Patil, senior manager for hot melt extrusion technology at Catalent. “Consequently, a thorough understanding of the impact of formulation and process variables on granule quality has become crucial.”

Researchers continue to create new process analytical technology (PAT) for TSG that provides process insight and helps advance the science needed for product and process development using quality by design (QbD). QbD techniques will be especially helpful because the modular design of twin-screw extruders widens the range of possible variables.

“TSG and HME technologies provide a lot of promise for formulations, such as controlled release or poorly soluble drugs,” says Doug Hausner, senior manager of business development for continuous manufacturing at Thermo Fisher Scientific. “There is a large knowledge base in twin-screw granulation, but there is also a large design space. There are many options for screw configuration in the equipment, along with other input variables such as liquid-to-solid ratio. Process design requires know-how as well as statistical analysis for optimization.”

This knowledge is important for both individual and integrated operations. Hausner adds that while Thermo does not currently use TSG or HME in its integrated continuous process for final dosage forms, the continuous manufacturing team provides expertise in feeding and PAT for individual TSG and HME operations. “A multi-step continuous process will require a good stand-alone development activity on the TSG or HME step,” Hausner says.

Patil points out that Catalent can use TSG to create granules with various profiles, such as immediate release, sustained release, delayed release, and taste masking. Twin-screw dry granulation (TSDG) is effective for moisture-sensitive materials and useful for APIs that are not suitable for roller compaction, such as molecules that require higher shear for mixing and agglomeration, she adds. “In addition, TSDG has a unique application for APIs with needle-shaped crystal habit, which have low flow rate and bulk density. These poor physical and mechanical properties make them difficult to process via conventional methods such as roller compaction and slugging. The kneading action of the twin-screw extruder enhances consolidation of powders with needle-shaped API, resulting in better flow and compressibility. For high drug-loading products, this process yields superior granule quality and bulk density.”

TSG is beneficial for both high- and low-dose APIs. “In low-dose products, it is feasible to increase the uniformity by forming granules and preventing demixing,” explains Robin Meier, scientific director at equipment maker L.B. Bohle. In high-dose APIs, TSG offers the ability to improve compressibility. Meier says that a stable and compressible granule can be formed with minimal amounts of binder, in the range of 5%. He reports that compressible granules could be produced with all APIs tested so far on the company’s equipment, once a suitable binder was identified, depending on API solubility, particle size distribution, and partition coefficient.

To build the knowledge base regarding the behavior of materials in twin-screw extrusion equipment, Leistritz Extrusion Technology formed a consortium in 2019 of pharma companies, the University of Texas at Austin, and McMaster University.

“Equipment variables include the ratio of the outer diameter of the screw to the inner diameter, the length-to-diameter ratio, and the screw design,” says Stephen Post, product manager for Life Sciences at Leistritz. “We’re working on gaining more knowledge of the fundamental behaviors of materials and equipment, and we’re looking for trends in material behavior that can be extrapolated to similar formulations.”

For example, consortium researchers have investigated how screw design affects particle size distribution (PSD). Researchers are also performing scale-up experiments to replicate the PSD obtained from an 18-mm diameter screw on a 27-mm diameter screw. Although some drug manufacturers may choose to scale-out by using multiple 18-mm extruders, there are advantages to using a larger extruder to scale-up, such as lower facility footprint and lower utilities cost, explains Post. Better scale-up data are needed, he says.

“We are also developing material-sparing methodologies to assess the feasibility of TSG using various screening tools without running the twin-screw extruder” says Feng Zhang, associate professor in the College of Pharmacy at the University of Texas. “One of the key challenges in TSG is the process-induced chemical degradation and physicochemical transformation during processing.We have developed an in-depth understanding of how these undesired changes can be inhibited via rational selection of formulation composition and process design.”

PAT is being used in TSG processes to measure critical parameters in real-time. Moisture content and PSD, for example, are critical quality attributes (CQAs) of the intermediate product that affect CQAs of the final product.

Near-infrared (NIR) PAT has been evaluated to replace time-consuming loss-on-drying measurements to quantify moisture content in granules, says Patil. “NIR analysis allows for the adjustment of process parameters in real-time, resulting in significantly less material waste and improved process optimization within a shorter timeframe, even during the same extrusion run,” she says.

For PSD, direct imaging is well established, but other PAT types are also being investigated.

“The discrete nature of moving particles makes it harder to understand what’s going on in the machine, because standard monitoring techniques like pressure and temperature monitoring are unreliable as indicators of deviating product specifications,” says Michael Thompson, associate dean and professor of Chemical Engineering at McMaster University, whose research group has studied twin-screw granulation for more than a decade. He adds that while batch granulation often produces a Gaussian PSD, twin-screw granulation typically has a bimodal PSD, which makes real-time analysis even more important. Thompson’s lab has developed an inline particle size analysis PAT using acoustic emissions (AE). The researchers created a digital signal filter to ensure that particles of any size would be represented (1). Next, they created a filter that would also account for inelastic forces by training an artificial intelligence model with an elastoplastic (Walton-Braun) contact force model and a dataset of acoustic emission spectra collected from a broad range of granulated pharmaceutical formulations. The prediction error was as low as 2%, demonstrating its applicability to monitoring particle size distributions in continuous twin-screw granulation (2).“I see the existing optical [imaging] methods and this acoustic method as complementary approaches to particle size analysis,” concludes Thompson. “Both have their strengths and weaknesses in a dusty production environment like the exit chute of a twin-screw granulator.”

In a continuous granulation and drying set-up, such as L.B. Bohle’s QbCon 1, Meier indicates it is most meaningful to measure the residual moisture after the drying process (rather than after granulation) to be able to control and feedback the dryer process parameters. “In this case, we usually apply NIR or microwave resonance measurements. The latter allows univariate calibration,” he says. In the granulation step, Meier explains that solid feeding rate and liquid feeding rate are the crucial parameters used to control mean granule size. He suggests that controlling these rates is more reliable than a method that measures in-line PSD and adjusts liquid addition. Meier reports that the QbCon 1 equipment, as part of a complete continuous manufacturing line, was recently delivered to a large German pharma company for clinical supply of new entities. This line is designed for small-scale throughputs up to 4 kg/h and is capable of handling APIs in occupational exposure band 5.

Twin-screw extrusion aids complex formulation

Researchers at Rutgers University are using a twin-screw extruder as a hot-melt coater and granulator in a unique, patent-pending solution to the ongoing challenge of manufacturing drug products with high doses of poorly soluble APIs. “Poorly soluble drugs are poorly soluble because they dissolve less, but this also is often because they are hydrophobic; they are difficult to wet and so they dissolve more slowly,” says Fernando Muzzio, distinguished professor of Chemical and Biochemical Engineering at Rutgers University. “We solved this problem by using a twin- screw extruder to coat the drug substance particles with a surfactant, which improves solubility. The particles are mixed with a low-melting point surfactant and fed into a twin-screw extruder operating at a temperature low enough to avoid decomposing the API but high enough to partially melt the surfactant and allow it to coat the API particles. The resulting granules flow and compress well, allowing us to make a high-dose (approximately 80% API), immediate release tablet.”

Muzzio says that this twin-screw granulation process is potentially less expensive to operate than more complex processes for high-dose, poorly soluble APIs, such as HME, nanomilling, or spray drying. The innovation is a result of understanding what happens to materials when their surface is modified, combined with an understanding of the twin-screw granulation process that allows accurate control of mechanical and thermal variables, says Muzzio.

Abdulhussain, H.A. and Thompson, M.R. Predicting the Particle Size Distribution in Twin Screw Granulation through Acoustic Emissions. 

As new analytical technologies advance, insight into the twin-screw granulation process is growing.

Exploring Advances in Twin-Screw Extrusion for Solid-Dosage Drugs

As more cell and gene therapies (CGT) advance through clinical trials toward potential approval and commercialization, manufacturers are looking to automated strategies and standardized systems for scaling up production efficiently. Early process designs that came from academic labs were not focused on commercial scale-up and relied, for example, on manual handling steps and complex tubing systems for liquid transfer (1). Automated sampling has helped, but more in-line process analytical technology (PAT) and greater automation and standardization are needed (1). At the same time, the diversity of products—in the case of autologous cell therapy, a different product for each individual patient—means that any manufacturing set-up will need to be highly flexible. New systems would ideally be able to be used in a decentralized, point-of-care location, such as a hospital facility, as well as a conventional, centralized pharmaceutical manufacturing location.

Commercial production of cell therapies is currently less than 5000 doses per year, but global demand is in the millions of doses, reports Jason Arcediano, chief business officer at Multiply Labs, a robotics technology company creating systems for bio/pharmaceutical manufacturing, including an end-to-end, closed manufacturing system for CGT. Existing processes and equipment do not have the throughput needed to meet patient demand. Staffing is also a challenge. “The industry is seeing high attrition rates—over 25%—because there is a huge demand for trained teams that can run these complex processes,” says Arcediano. Complex, manual handling steps limit throughput and increase opportunities for error. “The large cell therapy manufacturers are seeking to reduce failure points, and there is general agreement that automation is the solution,” he adds.

Current manufacturing capacity is inadequate to meet patient demand, and as more new therapies are developed, the unmet need will only increase unless there is a manufacturing paradigm shift, adds John Tomtishen, vice-president of operations at Cellares, which is preparing to launch its proprietary, end-to-end automated system, the Cell Shuttle. “Automation can transform the manufacturing paradigm and help companies scale their therapies effectively to make them accessible to all patients in need,” he says.

The manual and modular approaches used in early development tend to be carried over into commercial manufacturing, but these approaches pose challenges for scalability, adds Dan Strange, CTO, Cellular Origins, a spin-out launched in January 2023 from Cambridge, UK-based technology company, TTP, with a proprietary, automated system for scalable CGT manufacturing.

Cost and drug safety are both prominent challenges for the manufacturing process, which has traditionally been highly manual and complex. “We estimate the cell therapy manufacturing process may have upwards of 40 process steps, which is not only labor intensive but creates opportunities for errors and contamination that lead to failures,” says Betty Woo, vice president of cell, gene, and advanced therapies at Thermo Fisher. “By aseptically closing and automating the manufacturing process, we’re reducing the need for the highly specialized labor required to produce these therapies, thereby eliminating touchpoints, reducing expenses, and ultimately increasing the reproducibility and predictability of the process. Automating in this way will, to some extent, also help alleviate the workforce challenges we’re seeing across the industry particularly in emerging geographies.”

The optimal workflows for CGT are still being developed and processes are not yet standardized, leading to a need for flexible instrumentation, says Woo. “As the field progresses, we expect more standardized workflows to be established, [with] improved consistency, efficiency, speed, and throughput. These improvements will likely be catalyzed by technologies that aid in further scalability—down, up, and out; in-line sensing; and autosampling,” she predicts. “Standardization reduces variability and moves us closer to a more consistent and predictable outcome, while automation provides robustness, consistency, speed, and throughput. Automation in its ideal state will drive efficiency and reduce the cost for manufacturing these life-saving therapies.”

With the current manual or semi-automated manufacturing systems, production space and the need for highly skilled operators are barriers to production capacity. Closed and automated systems address both of these bottlenecks.

“Current, manual systems require ISO 7 or 8 cleanrooms, but a fully closed system can be placed in a controlled not classified (CNC) space,” explains Tomtishen. The Cellares Cell Shuttle platform is a “factory in a box” with all unit operations inside the closed system, which is about the size of a typical cleanroom workstation. Robotics perform material transfer from one unit operation to another. The throughput of the Cell Shuttle depends on the production process, notes Tomtishen. “With a seven-day process, you could manufacture approximately 800 batches per year per Cell Shuttle. Additional Shuttles could be added to scale-out if more capacity is needed,” he explains.

All the software and hardware in the platform has been developed by Cellares over the past four years. “The software enables flexibility to develop the manufacturing workflow. The research scientist has full control over the parameters in the unit operations,” says Tomtishen. He works with users to help them develop workflows and to transfer any processes already developed on other equipment to the proprietary Cell Shuttle equipment.

Partners in Cellares’ Early Access Partnership Program include the Fred Hutchinson Cancer Research Center, PACT Pharma, and Poseida Therapeutics. The partners helped evaluate prototypes and assess product requirements, release criteria, and process workflows. Cellares is continuing to refine the technology and expects the Cell Shuttle to be market-ready in 2024, which will make it available for process development and clinical and commercial manufacturing. In the “single-platform” approach, development and all manufacturing stages take place in the same equipment, which accelerates time to market.

Multiply Labs has designed a fully automated system with robotic handling that offers a solution to the need for increasing throughput, reducing error, and allowing flexibility, Arcediano says. The system has been designed to be compatible with existing equipment through a consortium launched by Multiply Labs in 2021 to tackle the challenge of debottlenecking commercial manufacturing of CGT using robotic automation. Manufacturing development is overseen by the University of California, San Francisco (UCSF) under a sponsored research agreement. Other consortium members are contributing their expertise to bring robotic automation to their equipment within the Multiply Labs’ Robotic Cluster, including Cytiva’s bioreactors, Thermo Fisher Scientific’s incubators, and Charles River Laboratories’ rapid microbial detection platform and endotoxin testing system for automating quality control (2).

“We aim to integrate with all major equipment manufacturers, so that a CGT manufacturer can use the validated equipment and instruments they want in their process,” states Arcediano. “We’ve started with the consortium members, but we are working with other vendors already.” Using validated equipment, process, and software leads to a shorter path forward with regulatory agencies, Arcediano adds. All equipment will be integrated with the robotic handling and Multiply Labs’ in-process control system in a standardized, “plug-and-play” method of information flow that is aligned with best practices from industry organizations, such as the Alliance for Regenerative Medicine. The equipment-agnostic system can use the best currently available instruments as well as be easily updated to use next-generation instruments, Arcediano adds.

Another feature is that all data are captured digitally. Arcediano explains that the end-to-end system could be run with only one operator; the operator loads the materials and then the robots transfer material from step to step through the aseptically controlled, fully closed system. Fluid transfer is handled with a proprietary robotic click connector system that eliminates the need for tube welding.

The automated system has a much smaller footprint than traditional manual processes. Because operators do not need access to the unit operations, the modules can be stacked two to three high and five to six deep. “A ballroom facility might have 1000 to 2000 square feet, while our system requires between 200 to 300 square feet,” says Arcediano. Throughput is also higher than traditional methods. “Instead of one client [i.e., patient product] at a time, our system can prepare up to 36 products at the same time,” he adds. The system can be scaled out as needed by including more modules for greater throughput. It can also be used for product development or commercial manufacturing, eliminating tech transfer.

According to Arcediano, because the process is self-contained, it can be used in a decentralized environment, such as a hospital, which would allow application of cell therapies in other regions of the world that do not have centralized manufacturing capability.

Cellular Origins’ platform is a configurable robotic automation solution that enables scalable, cost-effective, and space-efficient cell therapy manufacture that is designed for adaptability, says Strange. The platform consists of a universal transport system for automated movement of consumables, reagents, and patient materials; a tube-management system that enables automated routing; and a sterile fluid-transfer system that welds tubes, moves fluids, and provides real-time analysis and quality control, he explains. “These tasks are carried out by a combination of autonomous mobile robots with proprietary, future-proofed end-effectors and a configurable automation console that integrates existing third-party equipment. These tasks are all integrated within a data management system to ensure full traceability of every process undertaken,” Strange explains.

“Our platform enables therapy developers to use the tools and technologies from third-party vendors and combine them into a modular factory that can quickly scale to producing 10,000 therapies per year with a fraction of the labor of existing methods. Because the platform is built upon proven familiar technologies, it can potentially be used to scale those therapies currently in late-stage development.”

Strange adds that the company is beginning to work with its first customers to develop system configurations and to deploy these systems at customer sites.

In May 2023, Cellular Origins announced a partnership with ScaleReady, which is a joint venture between Bio-Techne, Fresenius Kabi, and Wilson Wolf with a mission to simplify and standardize CGT manufacturing. The collaboration’s initial task is to standardize and automate the interconnections between ScaleReady’s manufacturing platform modules using Cellular Origins’ robotic system (3).

“Solving the liquid handling problem and proving how amenable a simple, modular, and scalable approach is to automation allows the field to see a path forward to economies of scale,” said Josh Ludwig, commercial director at ScaleReady, in a press release (3). “Through this partnership, we plan to create a viable pathway using cell therapies for larger patient indications and front-line treatments by enabling therapy developers to implement automation when it makes the most sense, and when their products require it.”

Lonza’s platform for autologous cell therapy manufacturing, the Cocoon, is a functionally closed, automated system that is currently being used to support clinical trials in Europe and North America, in both centralized and decentralized manufacturing models, says Tamara Laskowski, head of Clinical Development, Personalized Medicines at Lonza. “With a growing number of clinical-pipeline applications, we are optimistic about the future use of the Cocoon Platform in commercial applications as well,” she adds.

Several unit operations—from starting materials through to final harvest—take place inside the functionally closed, single-use cassette, in processes which are tailored for each product. The Gen2 Cocoon, introduced in April 2022, added magnetic cell separation capabilities, allowing separation of cell types of interest, such as T cells, for processes that require this additional upstream sample preparation step, says Laskowski.

Decentralized manufacturing, which is closer to the patient at the point of care, reduces logistic challenges but can present quality concerns. Automated, closed systems, however, may resolve these concerns. “Producing cell therapies in automated, closed manufacturing systems will help to reduce reliance on manual operations and variability in process performance, improve data management, and may enable the realization of a standardized level of quality across point-of-care sites,” suggests Laskowski.

Allogeneic CGTs aim to use a single source of cells to treat many patients, with manufacturing at a larger scale than autologous CGTs. Automation, however, is expected to be important for these processes as well.

“Given the large-volume productions in allogeneic processes, automated systems that support final product harvest, formulation, and fill/finish are advantageous,” says Laskowski. “Such systems can reduce risks associated with manual processing and human error, ensure proper addition of cryoprotectant, and decrease time requirements to cryopreservation and storage of the product. As additional allogeneic CGT modalities emerge, we anticipate new developments in automated platforms to support culture and expansion of adherent cells and enable multi-stage manufacturing processes involving modified culture regimens and conditions for cell differentiation.”

Spivey, C. Small Footprint Automated Closed Production Platforms for CAR-T and Other Advanced Therapies. 2023 47 (4) 28-30.

Multiply Labs. Multiply Labs Adds Thermo Fisher Scientific and Charles River Laboratories to its Robotic Manufacturing Consortium. Press Release, May 5, 2022.

Cellular Origins. Cellular Origins Partners with ScaleReady to Simplify, Standardise, and Automate Cell Therapy Manufacturing. Press Release, May 11, 2023.

Jennifer Markarian is manufacturing reporter for Pharmaceutical Technology.

When referring to this article, please cite it as Markarian, J. 

Automation Aids Cell and Gene Therapy Production

Manufacturers face the challenge of meeting growing demand for personalized biopharmaceuticals.

Pharmaceutical manufacturing equipment companies and technology providers are exploring how artificial intelligence (AI) can benefit process control systems. Two Italian companies—pharmaceutical machinery manufacturer Luperini and technology start-up Eigengran—partnered to launch AI-enabled equipment for oral solid dosage drugs that they have called Cognitive Pharma Machinery.

Luperini signed a licensing agreement to use Eigengran’s cognitive control technology in December 2022, following 18 months of testing and development. The initial work focused on high-shear wet-granulation (HSWG). In one-pot HSWG equipment, such as that made by Luperini, the entire granulation process, including the drying step, is performed within one unit. This set-up was well-suited for the initial project of developing a cognitive control system using process analytical technology (PAT) sensors to monitor the progression of the granulation process over time.

AI Algorithms Find Use in Pharma Equipment

“Our technology is a key element in the application of PAT guidelines for oral drug production and will be a key step towards achieving Pharma 4.0 practice in the pharmaceutical manufacturing process,” said Marco Luperini, chief technology officer of Luperini, in an announcement of the technology (1). Luperini’s new test center in Chiesina Uzzanese, Italy houses pilot machines for evaluation to simulate conditions that may be encountered in real-world scenarios.

When referring to this article, please cite it as Markarian, J. AI Algorithms Find Use in Pharma Equipment. 

Pharmaceutical Technology Trends in Manufacturing

Machine learning provides real-time data for process control of high-shear wet granulation.