Pre-Conference Workshops

Synopsis

Quality-by-Design (QbD) and continuous improvement practices play a vital role in enhancing product quality. By evaluating the efectiveness of QbD and continuous improvement this workshop will uncover strategies to achieve hgiher quality standards and

optimize product performance.

Join this interactive workshop to:

• Explore the benefits of leveraging real-time monitoring and control systems to detect the influence of Critical process Parameters (CPPs) on product quality
• Evaluate how Quality-by-Design (QbD) and continuous improvement is used to enhance product quality to meet quality standards
• Leverage real-time monitoring and control to detect how CPPs affect product quality, to reduce cycle times, improve resource utilization and cost savings
• Exploring PAT’s role in the digital transformation of manufacturing
• Optimizing a process map for successful deployment of PAT

Synopsis

In this workshop, participants will gain valuable insights into the application of machine learning in a cross-manufacturing environment (Non GxP and GxP Environment). This knowledge will enable them to develop robust models, ensure compliance, and optimize manufacturing processes for enhanced product quality and operational efficiency.

Machine learning presents valuable opportunities for exploring process performance and

root cause analysis, improving efficiency, reducing errors, and ensuring compliance within GMP settings. Throughout the discussion, essential topics will be covered, including the fundamentals of machine learning for bioprocessing in cross-manufacturing environments effective strategies for data collection and preparation, model development techniques, validation and compliance requirements, data integrity and security considerations, and risk management.

This hands-on session will help you:

• Understand the fundamental concepts and principles of machine learning and its relevance for manufacturing intelligence in bioprocessing
• Learn effective strategies for data collection, data interrogation, preprocessing, and data quality assurance to ensure reliable and accurate inputs for machine learning models
• Explore various machine learning algorithms and techniques suitable for application in bioprocessing, including supervised, unsupervised, semi-supervised and reinforcement learning for tasks of classification, regression, and anomaly detection
• Understand the regulatory requirements for model validation in cross-manufacturing environments, including validation protocols, performance metrics, and documentation
• Uncover how to assess and mitigate risks associated with machine learning models in cross-manufacturing processes including model accuracy, robustness, bias, and interpretability