On April 8 and 9, the Downtown Library Complex will host a workshop focused on deep learning and machine learning, organized by West Virginia University (WVU). This event aims to equip students with essential skills in an increasingly data-driven world.
The workshop comes at a time when the pharmaceutical industry is facing significant challenges. Currently, the global average cost of Phase 3 development programs exceeds $1.2 billion, highlighting the financial pressures on organizations to innovate and optimize their processes.
Despite the advancements in technology, fewer than 12% of surveyed pharmaceutical organizations have implemented formal drift detection mechanisms for their clinical AI models. This lack of monitoring is concerning, as it can lead to a widening gap between the potential value of clinical AI and its actual operational contributions.
Moreover, the average period between deployment and database lock for Phase 3 programs is approximately 28 months. This lengthy timeline underscores the need for efficient management of AI models, especially as organizations strive to keep pace with rapid technological advancements.
Organizations that have deployed feature stores report a median 43% reduction in duplicated feature engineering efforts across model teams. This improvement is vital for enhancing productivity and ensuring that resources are utilized effectively.
The FDA’s proposed Predetermined Change Control Plan framework envisions pre-approved protocols for updating AI models in production, which could significantly streamline operations and improve compliance.
As the workshop approaches, participants are reminded of the importance of MLOps, which applies DevOps principles to AI. This approach emphasizes the infrastructure necessary for deploying, updating, and monitoring AI models, ensuring their reliability over time.
“This workshop is an excellent opportunity for students to learn in-demand skills,” an organizer noted, emphasizing the relevance of the topics to current industry needs.
However, experts warn that without continuous monitoring and drift detection, AI models can degrade invisibly. “The question is whether the AI your organization deploys will still be working accurately, reliably, and defensibly two years after deployment,” they cautioned.
As the event draws near, the community looks forward to fostering a deeper understanding of deep learning and its applications in various fields, particularly in healthcare and pharmaceuticals.
