Peter Henstock

This talk will focus on an end-to-end effort AI/ML and natural language processing (NLP) for drug safety teams to extract adverse events from FDA drug labels and their extensions to EMA drug labels. We will discuss some of our key strategies using different aspects of NLP in the extraction process. The talk will also include some of the key challenges that we have encountered including the quest for preclinical terms that are not captured by MedDRA and other standard ontologies.

Peter Henstock is currently the Machine Learning and AI Lead in the Pfizer Statistical Research Innovation group. He is working to push AI methodology across Pfizer to improve drug research and development. He holds a PhD in Artificial Intelligence from Purdue University and 5 Master’s Degrees. He also teaches both Software Engineering and Machine Learning at Harvard University.

This website uses cookies to ensure you get the best experience. Learn more