Real World Evidence in the Age of LLMs
Tristan Naumann
January 31, 2024, Wednesday, 2:00 PM - 3:00 PM EST
Large language models (LLMs) have seen widespread interest beyond the machine learning community, in part due to their accessibility and capability. Their use in biomedical applications stands to democratize biomedical knowledge work by providing means to rapidly structure data. This talk will provide an overview of biomedical LLMs, with a focus on their use in real-world evidence (RWE) generation.
I am at Microsoft Research's Health Futures working on problems related to clinical natural language processing and machine reading. My research focuses on exploring relationships in complex, unstructured healthcare data using natural language processing and unsupervised learning techniques. Previously, I completed a PhD in the Clinical Decision Making group at MIT CSAIL with Prof. Peter Szolovits, where the research focused on leveraging text representations for clinical predictive tasks, combining structured and unstructured healthcare data. My work has appeared in KDD, AAAI, AMIA, JMIR, Science Translational Medicine, and Nature Translational Psychiatry.

While at MIT, I was an Instructor for HST.953 (Collaborative Data Science for Medicine) and co-authored its textbook, "Secondary Analysis of Electronic Health Records." I served as the General Chair for the NIPS 2018 Machine Learning for Health (ML4H) workshop, and co-organized the NIPS 2017 ML4H workshop, the COLING 2016 Clinical NLP workshop, and several "datathon" events, which bring together participants to address problems of clinical interest. I also served as a mentor for the MIT Summer Research Program (MSRP) and have spent time as a Software Engineering Intern at Intel Corporation. Prior to MIT, I was a Program Manager at Microsoft Corporation, an Associate Product Manager Intern at Google, and received B.S. and M.S degrees in computer science from Columbia University. While at Columbia University, I was a MS-TA fellow and recipient of the Andrew P. Kosoresow Memorial Award for Outstanding Performance in TA-ing and Service.