EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Identifying Early Signals From Emerging Public Health Events Using Natural Language Processing

Kelly S Peterson iD, Christian Dalton, Andrea Kalvesmaki iD, JoAnn Vuong, Colton Gordon, Senthil Nachimuthu, Mary Jo Pugh, Makoto M Jones

Interdisciplinary Perspectives on Infectious Diseases · 2026-01 · 2026 (1)

DOI: 10.1155/ipid/6176855 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Interdisciplinary Perspectives on Infectious Diseases, online erschienen am 06.03.2026. Verfasst von Kelly S Peterson und 7 weiteren Autor:innen. Beteiligte Einrichtung: Veterans Health Administration, Office of Analytics and Performance Integration, Washington, District of Columbia, USA. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: U.S. Department of Defense.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Timely detection of emerging public health threats is challenging because the surveillance infrastructure is not yet tuned to the emerging threat. We attempt to identify three nonspecific early signals that might be common across emerging events: public health authority communication, zoonotic exposure mentions, and other pathogen exposure mentions.

Methods

Data from U.S. Department of Veterans Affairs emergency department visits between 2004 and 2024 were used to construct training and validation sets from reportable or emerging infectious diseases identified by historical diagnoses and laboratories. Not all early signal types were extracted using the same method. Rule‐based and transformer models were used in a way to minimize developer and chart reviewer time. We then extracted cases from historic documents among selected diseases.

Results

Positive predictive values for public health authority communication, zoonotic exposure, and other pathogen exposure ranged from 0.615 to 1.0. Target concepts were extracted from over 33 million emergency department visits. Distributions of extracted exposures generally matched expectations for the identified pathogen.

Conclusion

Automated natural language processing methods allow surveillance scaling to large amounts of clinical documents to identify relevant cases. Initial validation compared to manual text review shows that accuracy is acceptable for initial feasibility exploration in biosurveillance efforts.

Autor:innen und Institutionen

  • Veterans Health Administration, Office of Analytics and Performance Integration, Washington, District of Columbia, USA.
  • Informatics Decision-Enhancement, and Analytic Sciences (IDEAS) Center of Innovation, VA Salt Lake City Health Care System, Salt Lake City, Utah, USA.
  • Department of Internal Medicine, Division of Epidemiology, Spencer Fox Eccles School of Medicine University of Utah, Salt Lake City, Utah, USA.

ORCID-Profile: Kelly S Peterson, Andrea Kalvesmaki

Förderung

  • U.S. Department of Defense

Zitieren

APA

Peterson, K. S., Dalton, C., Kalvesmaki, A., Vuong, J., Gordon, C., Nachimuthu, S., Pugh, M. J., & Jones, M. M. (2026). Identifying Early Signals From Emerging Public Health Events Using Natural Language Processing. Interdisciplinary Perspectives on Infectious Diseases, 2026(1). https://doi.org/10.1155/ipid/6176855

Vancouver

Peterson KS, Dalton C, Kalvesmaki A, Vuong J, Gordon C, Nachimuthu S, et al. Identifying Early Signals From Emerging Public Health Events Using Natural Language Processing. Interdisciplinary Perspectives on Infectious Diseases. 2026;2026(1). doi:10.1155/ipid/6176855

BibTeX
@article{Peterson2026,
  author = {Peterson, Kelly S and Dalton, Christian and Kalvesmaki, Andrea and Vuong, JoAnn and Gordon, Colton and Nachimuthu, Senthil and Pugh, Mary Jo and Jones, Makoto M},
  title = {Identifying Early Signals From Emerging Public Health Events Using Natural Language Processing},
  journal = {Interdisciplinary Perspectives on Infectious Diseases},
  year = {2026},
  volume = {2026},
  number = {1},
  doi = {10.1155/ipid/6176855}
}
Kostenlos starten →