Natural Language Processing Accurately Differentiates Cancer Symptom Information in Electronic Health Record Narratives
We illustrated the feasibility of detecting 14 symptom groups in EHR narratives and showed that an embeddings-augmented NLP system outperforms conventional machine learning algorithms in detecting symptom information and differentiating observed symptoms from negated symptoms and medication-related side effects.
Authors
- Alaa Albashayreh (ORCID: https://orcid.org/0000-0002-2471-9082)
- Nahid Zeinali (ORCID: https://orcid.org/0009-0009-1546-9972)
- Stephanie Gilbertson‐White (ORCID: https://orcid.org/0000-0002-9718-3717)
- Weiguo Fan (ORCID: https://orcid.org/0000-0003-1272-5538)
- Anindita Bandyopadhyay (ORCID: https://orcid.org/0000-0003-4881-1139)
- Min Zhang (ORCID: https://orcid.org/0000-0003-3890-2942)
Institutions
- University of Iowa (US)
- Communication University of China (CN)
Publication Details
- Journal
- JCO Clinical Cancer Informatics
- Published
- 2024-08-01
- DOI
- https://doi.org/10.1200/cci.23.00235
- Citations
- 11
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 3.82
Funders
- Georgia Clinical and Translational Science Alliance
- National Institute of Nursing Research