Applying Machine Learning to the Visual Inspection of Filled Injectable Drug Products.

With machine learning (ML), we see the potential to better harness the intelligence and decision-making abilities of human inspectors performing manual visual inspection (MVI) and apply this to automated visual inspection (AVI) with the inherent improvements in throughput and consistency. This article is intended to capture current experience with this new technology and provides points to consider for successful application to AVI of injectable drug products. The technology is available today for such AVI applications. Machine vision companies have integrated ML as an additional visual inspection tool with minimal upgrades to existing hardware. Studies have demonstrated superior results in defect detection and reduction in false rejects, when compared with conventional inspection tools. ML implementation does not require modifications to current AVI qualification strategies. The utilization of this technology for AVI will accelerate recipe development by use of faster computers rather than by direct human configuration and coding of vision tools. By freezing the model developed with artificial intelligence tools and subjecting it to current validation strategies, assurance of reliable performance in the production environment can be achieved.

Achieving "Zero" Defects for Visible Particles in Injectables.

The reduction of visible particles in injectable products is an important element in the consistent delivery of high-quality parenteral products. An important part of this effort is the control of particles that may emanate from the primary packaging materials. The Parenteral Drug Association (PDA), with the support of the Pharmaceutical Manufacturers Forum (PMF), has undertaken the task of developing test methods to assess the cleanliness of primary packaging components used in the manufacturing of sterile injectable products. Further work is focused on end-to-end analysis of the supply chain to identify additional points where particles may enter the finished product workflow. This includes shipment, receipt, transfer, and fill and finishing operations. This information and appropriate corrective actions and control methods, coupled with appropriate patient risk-based acceptance limits, are intended to provide better and more consistent supply of injectable products that meet current compendial and good manufacturing practice (GMP) expectations. Aligning control limits between supplier and pharmaceutical manufacturers will offer further improvement. This paper describes the formation of a task force to address these needs and current progress to date.LAY ABSTRACT: Visible particles must be controlled in parenteral products. Such particles come from many sources including the primary packaging materials. The Parenteral Drug Association (PDA), with the support of the Pharmaceutical Manufacturers Forum (PMF), has formed a task force to review and improve particle measurement methods and perform an end-to-end analysis of how particles may enter into parenteral products. These activities are intended to lead to more consistent control limits for visible particles and ultimately more consistent supply of high quality injectable products.