(88b) An Examination of Process Models and Model Risk Frameworks for Pharmaceutical Manufacturing (invited talk)

Process models are a growing tool for pharmaceutical manufacturing process design and control. The Industry 4.0 paradigm promises to increase the amount of data available to understand manufacturing processes and tools such as AI and machine learning that might accelerate process development and allow better prediction of process trajectories. Several examples of the application of process models have shown process improvements can be realized in lyophilization, chromatography, fluid bed drying, bioreactors, and continuous direct compression and wet granulation. An important consideration of implementing a process model is determining the impact of the model on quality of the product and the risks associated with model maintenance over product lifecycle. Several documents address these risk-based considerations, including: (a) the ICH ICH Quality Implementation Working Group Points to Consider (R2), (b) the FDA guidance for industry on Development and Submission of Near Infrared Analytical Procedures, (c) the EMA guideline on the use of near infrared spectroscopy by the pharmaceutical industry and the data requirements for new submissions and variations, (d) ICH Q13: Continuous Manufacturing of Drug Substances and Drug Products and (e) the American Society Mechanical Engineers Verification and Validation 40 standard. In this presentation, hypothetical case studies are to illustrate the implications of applying a framework to determine model risk to facilitate model validation and lifecycle maintenance in the manufacture of pharmaceuticals and biological products.