New Paper: Scalable incident detection via natural language processing and probabilistic language models

We're excited to share a new paper out of the lab, in collaboration with and funded by the FDA along with many wonderful colleagues at VUMC, Washington Health Research Institute, University of Pennsylvania, Brigham and Women’s Hospital, and Harvard Pilgrim Health Care Institute. Post marketing safety surveillance depends in part on the ability to detect…

New Paper: Enhancing Suicide Risk Prediction Models with Temporal Clinical Note Features

Kevin Krause, PhD student in the lab, led a paper to investigate the impact of enhancing a structured-data-based suicide attempt risk prediction model with temporal Concept Unique Identifiers (CUIs) derived from clinical notes. Co-authors are Sharon Davis, Zhijun Yin, Katherine Schafer, Trent Rosenbloom, and Colin Walsh. Read the full paper here!

New Paper: Completeness and readability of GPT-4-generated multilingual discharge instructions in the pediatric emergency department

New paper out in JAMIA, co-authored with PhD student in the lab KJ Krause along with Vanderbilt medical students Alex Gimeno and Starina D'Souza. The aim of this study was to assess the completeness and readability of generative pre-trained transformer-4 (GPT-4)-generated discharge instructions at prespecified reading levels for common pediatric emergency room complaints. English-language GPT-generated…