EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Enhancing Vaccine Safety Surveillance: Extracting Vaccine Mentions from Emergency Department Triage Notes Using Fine-Tuned Large Language Models

Sedigh Khademi, Jim Black, Christopher Palmer, Muhammad Javed, Hazel Clothier, Jim Buttery, Gerardo Luis Dimaguila

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti251023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Sedigh Khademi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Murdoch Children's Research Institute, Parkville, Australia. Hauptthemen laut MEDLINE: Emergency Service, Hospital, Natural Language Processing, Vaccines, Triage. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study evaluates fine-tuned Llama 3.2 models for extracting vaccine-related information from emergency department triage notes to support near real-time vaccine safety surveillance. Prompt engineering was used to initially create a labeled dataset, which was then confirmed by human annotators. The performance of prompt-engineered models, fine-tuned models, and a rule-based approach was compared. The fine-tuned Llama 3 billion parameter model outperformed other models in its accuracy of extracting vaccine names. Model quantization enabled efficient deployment in resource-constrained environments. Findings demonstrate the potential of large language models in automating data extraction from emergency department notes, supporting efficient vaccine safety surveillance and early detection of emerging adverse events following immunization issues.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Emergency Service, HospitalNatural Language ProcessingVaccinesTriageElectronic Health RecordsData MiningProduct Surveillance, PostmarketingAdverse Drug Reaction Reporting SystemsHumansLarge Language Models

Stichwörter der Autor:innen

Emergency departmentNatural language processingvaccine safety

Substanzen

Vaccines

Autor:innen und Institutionen

  • Murdoch Children's Research Institute, Parkville, Australia.
  • Department of Health, State Government of Victoria, Melbourne, Australia.
  • Department of Paediatrics, The University of Melbourne, Parkville, Australia.

Zitieren

APA

Khademi, S., Black, J., Palmer, C., Javed, M., Clothier, H., Buttery, J., & Dimaguila, G. L. (2025). Enhancing Vaccine Safety Surveillance: Extracting Vaccine Mentions from Emergency Department Triage Notes Using Fine-Tuned Large Language Models. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti251023

Vancouver

Khademi S, Black J, Palmer C, Javed M, Clothier H, Buttery J, et al. Enhancing Vaccine Safety Surveillance: Extracting Vaccine Mentions from Emergency Department Triage Notes Using Fine-Tuned Large Language Models. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti251023

BibTeX
@article{Khademi2025,
  author = {Khademi, Sedigh and Black, Jim and Palmer, Christopher and Javed, Muhammad and Clothier, Hazel and Buttery, Jim and Dimaguila, Gerardo Luis},
  title = {Enhancing Vaccine Safety Surveillance: Extracting Vaccine Mentions from Emergency Department Triage Notes Using Fine-Tuned Large Language Models},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti251023}
}
Kostenlos starten →