LLM Mechanics in Research Using Clinical Notes
Large Language Models are increasingly used to analyze clinical notes, but their behavior can be difficult to understand without examining how prompts, context, and outputs interact. In this seminar, Subhadeep Nag, MS, will introduce the mechanics of using LLMs for clinical note research, including how prompts are structured, how clinical text is prepared for LLM input, how outputs can be interpreted, and where caution is warranted when applying these methods in healthcare research. The session will focus on practical examples from EHR-based research and will highlight both the promise and limitations of LLMs in high-stakes clinical settings.
Speaker:
Subhadeep Nag, MS
Research Data Scientist
NC TraCS Institute
Seminars in the NC TraCS Data Science Lab Seminar Series cover a range of topics related to health care data science, clinical data, data engineering, and working in these areas at UNC-Chapel Hill. These hybrid seminars are usually held monthly on the third Tuesday of each month from 12:30-1:30 p.m. in the NC TraCS suite on the 2nd floor of Brinkhous-Bullitt or via Zoom.
This is the second session in the Systematic Review Summer Workshop Series offered by the UNC Health Sciences Library. Thinking about starting a review, but unsure which type is right for you? In this workshop, we will cover the main aspects of several types of reviews (narrative, systematic, scoping, rapid, umbrella, and systematized) and how to identify which review type is appropriate for different questions and contexts.
This workshop is being offered remotely via Zoom only. Registrants will receive a Zoom link; those on the waitlist will not receive a Zoom link unless they are bumped up to a registered spot.
Supporting Grief and Providing Compassion Among Research Professionals: The Forgotten Grievers
Join the UNC Network for Research Professionals (NRP) for a hybrid education session with Lisa L. Williams, MDiv, BCC, BSN, the Clinical Chaplain for Oncology at the NC Basnight Cancer Hospital.
In-person location: Brinkhous-Bullitt room 219