Responsibly Deploying Machine Learning for Health

Tom Hartvigsen, PhD

Machine learning has been proposed as a promising tool for making healthcare cheap, fast, and accessible. However, despite growing health data and high-performance models, current methods remain surprisingly biased, fragile, and impractical. In this talk, Dr. Hartvigsen will discuss his work on filling these important gaps, taking steps towards machine learning that can be broadly deployed in healthcare. He will focus on his technical work on generating fair datasets using large language models, integrating reinforcement learning into early warning systems, and continually repairing deployed models.

Tom Hartvigsen is a Postdoctoral Associate at MIT's Computer Science and Artificial Intelligence Laboratory, where he works with Marzyeh Ghassemi. Tom focuses on core challenges in deploying machine learning and data mining systems in healthcare settings. His work has appeared at top venues such as KDD, NeurIPS, AAAI, ACL, and ICDM. He also ran the 2022 NeurIPS workshop on Learning from Time Series for Health. Tom received his PhD in Data Science from Worcester Polytechnic Institute in 2021, where he was advised by Elke Rundensteiner and Xiangnan Kong.