Clinical Information Extraction From Notes of Veterans With Lymphoid Malignancies: Natural Language Processing Study
The system exhibits satisfying and comparable performance for most clinical entities of interest except for (1) the primary diagnosis and (2) substance use. Future work will address the challenges encountered in developing and deploying the cNLP pipeline on the Department of Veterans Affairs data for rare cancers and enhance the performance of cNLP systems to avoid biases.
Authors
- Helen Ma (ORCID: https://orcid.org/0000-0002-0416-5115)
- Kai Zheng (ORCID: https://orcid.org/0000-0003-4121-4948)
- Lu He (ORCID: https://orcid.org/0000-0003-0181-018X)
- Matthew R. Moldenhauer (ORCID: https://orcid.org/0000-0002-6596-6231)
Institutions
- University of California, Irvine (US)
- University of California San Diego (US)
- VA Long Beach Healthcare System (US)
- University of Wisconsin–Milwaukee (US)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-09-15
- DOI
- https://doi.org/10.2196/63908
- Primary Topic
- Natural Language Processing Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00