A recent spike in demand for GLP-1 drugs has fueled growth in the ever-expanding $142.58 billion global weight loss market. Championed by some of the world’s biggest celebrities and coupled with a rising prevalence of obesity across the U.S., these drugs, designed to treat conditions such as diabetes and obesity, are having their moment in the spotlight.

 

For pharma manufacturers, the sudden popularity of GLP-1 drugs has placed increased strain on the medical supply chain and subsequent pressure to avoid bottle necks. In response, pharma manufacturing leaders are doubling down on plans to increase manufacturing capacity. However, this task will prove to be a complex one as there are several factors that must be considered when producing these sensitive drugs. 

 

Expanding sensitive biologic production 

Biologic drugs, including GLP-1s, are known for having sensitive and complex structures that can place a hinderance on their storage and administration. Because of their reactivity, drug developers must pay special attention to the primary packaging used or risk reformulation and delays in development. The problem can be caused by interaction between the drug and the surface of the primary container, causing visible flakes or glass lamellae that contaminate the drug itself.

 

To combat this, having effective visual inspection protocols becomes mission critical for scaling up capacity while simplifying compliance. This is especially crucial for an industry with regulatory compliance at the center of its operations. While manual inspection continues to be the gold standard for detecting defects across drug manufacturing, this process has proved itself to be both time and labor-intensive. Drug manufacturers have now invested in automated inspection systems that incorporate advanced vision software and testing machine learning and artificial intelligence (AI) algorithms to meet the high-volume output demanded by the market.

 

Quality control procedures have benefited as a result. These systems can efficiently inspect containers and ensure product integrity at high speeds. More specifically, AI-powered systems could be effective in minimizing the false reject rate that occurs when quality control measures mistakenly reject products. The added layer of validation allows for confidence in the significantly increased manufacturing capacity – all while still maintaining oversight from trained professionals conducting manual inspections.

 

Advancements in machine and deep learning technologies have opened the doors for improved manufacturing performance, accelerating research for drug development and discovery by learning and identifying patterns to form predictions. The foremost priority for the pharma industry is to deliver a final product that is safe. Because of their capacity to detect various types of defects, deep learning models have also been shown to increase defect detection while reducing false rejections, as well as reduce time consuming intervention necessary to re-inspect gray items or parameterize the machine in production. This ultimately helps to reduce the total cost of ownership, allowing pharma companies to realize the economic benefits that come along with it. Thanks to the robustness of the system, the recipe does not need to be adapted as soon as variations within production appear, as is the case with current software vision systems. 

 

To implement AI, cloud options enable data sharing in a completely safe environment, ensuring data integrity and traceability. Additionally, they create an optimized solution for data analysis. To train neural networks needed for proper deployment, thousands of images are needed to cover all the possible container and product variations. This allows the neural network to recognize all possible defects; by feeding the model with thousands of images, it simulates real production, where millions of parameter combinations could come up. Data is always online and available, and these platforms can work with any other cloud-based or on-premises system, reducing the total investment amount for pharma companies. 

 

The promise of AI in pharmaceutical manufacturing has set the stage for increased research and development efforts to increase productivity and meet global market demands – not only for the production of GLP1s but for a wide range of biologic therapies. As we look towards the future, the next step in improving speed to market for sensitive biologics will be to continue investing in digital technologies, all while maintaining the proper infrastructure for handling the increase in manufacturing output.

---

Riccardo Butta is the President of the Americas at Stevanato Group, a global provider of drug containment, drug delivery and diagnostic solutions to the pharmaceutical, biotechnology and life sciences industries. Riccardo was formerly the Senior Vice President of Flex Health Solutions. At Flex, he was responsible for the global commercial organization of a business unit providing contract design, manufacturing and logistics services to the healthcare industry. His primary focus was on medical devices, drug delivery solutions, diagnostics, and life sciences equipment.