We’ve gotten used to algorithms making decisions in our daily lives. Yet, statistics and its modern incarnation — artificial intelligence and machine learning — are all inherently probabilistic. Probabilistic processes have the potential for error. Unhandled edge cases and a base error rate are normal parts of any AI solution but present a unique risk when the intended use case is medicine. In this lightning talk, I will discuss the challenge of designing and deploying AI/ML to support biomanufacturing operations, outlining some of the algorithmic constraints and architecture choices Fathom has employed to manage risk while improving the manufacture and distribution of life-saving drugs.
Clare Gollnick is co-founder and CTO at Fathom, modernizing the data infrastructure that supports the manufacture of cell and gene therapies. Clare has a Ph.D. in Biomedical Engineering from Georgia Tech and Emory University. Her doctoral research focused on developing new ways to target drugs to the neural tissue and using pharmacological modulation to increase plasticity in neural networks. Previously she was the Director of Data at NS1, where she led the development of their edge reporting and analytics infrastructure, which processes billions of DNS queries per day. Clare publishes a newsletter on the philosophy of data and theoretical limits of inference.