Identification and validation of respiratory virus immunization using natural language processing
We demonstrated the effectiveness of NLP methods in identifying immunizations from EHR. High precision and recall for COVID-19 and influenza immunizations suggest that the algorithm can effectively identify immunization references when they are present in the text; however, low recall when compared to the structured data suggests that there are many more immunizations in the structured data not present in the text. Thus, the algorithm has specialized utility for augmenting immunization records using text data from individual notes; however, the algorithm's extensibility and generalizability can serve as a framework for future EHR-based research.
Authors
- Mengshi Zhou (ORCID: https://orcid.org/0000-0002-0081-2485)
- John Riddles
- Lawrence Reichle
- Kevin A. Wilson
- Jennifer DeCuir (ORCID: https://orcid.org/0000-0001-5071-3875)
- Anil Battalahalli
- Rahul Shrivastava (ORCID: https://orcid.org/0000-0002-6764-9459)
- Michelle Barron (ORCID: https://orcid.org/0000-0001-8131-3030)
- Andrew C. Hill
- Catia Chavez
- Amanda B Payne
- Toan Ong
- Elizabeth Rowley
- Elizabeth A. Bassett
- Zachary A. Weber
- Ethan Moran
- Sarah W. Ball
- Ruth Link-Gelles
- Daniel Chacreton
Institutions
- Westat (United States) (US)
- Colorado School of Public Health (US)
- National Center for Immunization and Respiratory Diseases (US)
- United States Public Health Service Commissioned Officers Association (US)
- University of Colorado Anschutz Medical Campus (US)
Publication Details
- Journal
- Frontiers in Digital Health
- Published
- 2026-02-02
- DOI
- https://doi.org/10.3389/fdgth.2026.1733630
- Primary Topic
- Data-Driven Disease Surveillance
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Centers for Disease Control and Prevention