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.
@article{arxiv.1905.01961,
title = {Evaluating the Portability of an NLP System for Processing Echocardiograms: A Retrospective, Multi-site Observational Study},
author = {Prakash Adekkanattu and Guoqian Jiang and Yuan Luo and Paul R. Kingsbury and Zhenxing Xu and Luke V. Rasmussen and Jennifer A. Pacheco and Richard C. Kiefer and Daniel J. Stone and Pascal S. Brandt and Liang Yao and Yizhen Zhong and Yu Deng and Fei Wang and Jessica S. Ancker and Thomas R. Campion and Jyotishman Pathak},
journal= {arXiv preprint arXiv:1905.01961},
year = {2019}
}