Machine learning promises to revolutionize cell therapy process development, yet

practical implementation remains limited. This workshop bridges theory and practice

by showcasing real-world machine learning applications from companies successfully

deploying these tools. Explore how machine learning addresses donor variability,

predicts outcomes, enables real-time monitoring, and streamlines data – while learning

which approaches deliver results vs speculations.

Workshop highlights:

• Accelerate and optimize process development by examining successful machine learning implementations in process development through case studies demonstrating practical utility, including tools used, data requirements, and measurable workflow improvements
• Improve product consistency and manufacturing predictability by leveraging machine learning to predict donor variability impacts on manufacturing outcomes and identify patient-specific factors affecting product quality and comparability
• Enable predictive process control without major infrastructure changes by integrating real-time monitoring and AI analytics into existing GMP processes without complete system overhauls to enable predictive process control
• Strengthen data integrity and analytical capability by establishing streamlined, traceable data collection systems that support AI model development while safeguarding against human error and enabling cross-platform analysis