event-icon
Description

While natural language processing (NLP) of unstructured clinical narratives holds the potential for patient care and clinical research, portability of NLP approaches across multiple sites remains a major challenge. This study investigated the portability of an NLP system developed initially at the Department of Veterans Affairs (VA) to extract 27 key cardiac concepts from free-text or semi-structured echocardiograms from three academic medical centers: Weill Cornell Medicine, Mayo Clinic and Northwestern Medicine. While the NLP system showed high precision and recall measurements for four target concepts (aortic valve regurgitation, left atrium size at end systole, mitral valve regurgitation, tricuspid valve regurgitation) across all sites, we found moderate or poor results for the remaining concepts and the NLP system performance varied between individual sites.

Learning Objective: Evaluate the performance of a Natural Language Processing (NLP) system

Authors:

Prakash Adekkanattu, Weill Cornell Medicine
Guoqian Jiang, Mayo Clinic
Yuan Luo, Northwestern University
Paul Kingsbury, Mayo Clinic
zhenxing xu, Weill Cornell Medicine
Luke Rasmussen, Northwestern University
Jennifer Pacheco, Northwestern University
Richard Kiefer, Mayo Clinic
Daniel Stone, Mayo Clinic
Pascal Brandt, Washington University
Liang Yao, Northwestern University
Yizhen Zhong, Northwestern University
Yu Deng, Northwestern University
Fei Wang, Weill Cornell Medicine
Jessica Ancker, Weill Cornell Medicine
Thomas Campion, Weill Cornell Medicine
Jyotishman Pathak (Presenter)
Weill Cornell Medicine

Presentation Materials:

Tags