Automating and Evaluating LLM-Generated ED Handoff Notes

Presentation Time: 10:45 AM - 11:00 AM

Abstract Keywords: Large Language Models (LLMs), Documentation Burden, Transitions of Care, Evaluation, Natural Language Processing, Machine Learning
Primary Track: Applications
Programmatic Theme: Clinical Informatics

It has been burdensome for physicians to review and document large unstructured clinical data. We develop a summarization system that automatically generates Emergency Medicine handoff notes using LLMs, specifically designed for text generation in the clinical domain. We also propose a novel clinical evaluation rubric focused on the quality and safety of generated texts. The evaluation results show the effectiveness of the proposed framework.

Speaker(s):
Xinyuan Zhang, PhD
Abstractive Health

Vince Hartman, MS, Information Systems
Abstractive Health

Author(s):
Vince Hartman, MS, Information Systems - Abstractive Health; Thomas Campion, PhD - Weill Cornell Medicine; Xinyuan Zhang, Ph.D. - Abstractive Health; Ritika Poddar, MS, Information Systems - Abstractive Health; Evan Sholle, MS - Weill Cornell Medical College; Peter Steel, MA, MBBA - NewYork-Presbyterian Weill Cornell Medicine; Alexander Fortenko, MD, MPH - NewYork-Presbyterian Weill Cornell Medicine; Matthew McCarty, MD - NewYork-Presbyterian Weill Cornell Medicine;