EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bitesize Biosecurity: A tool and framework for curating and summarising expert biosecurity advice for farmers using artificial intelligence

Alexander F B Carmichael iD, Lorna A Pate iD, Andrew J Duncan iD, Lynsey Melville iD, Kate Lamont

Veterinary Record Open · 2026-06 · 13 (1)

DOI: 10.1002/vro2.70035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Veterinary Record Open, online erschienen am 22.05.2026. Verfasst von Alexander F B Carmichael und 4 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Epidemiology and Planetary Health Scotland's Rural College Inverness UK. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Rural and Environment Science and Analytical Services Division.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Biosecurity practices mitigate disease risk on farms; however, adoption and consistent implementation remain variable across farmers. Improved communication of biosecurity information could increase uptake, reduce disease incidence and improve productivity, profitability and animal welfare.

Methods

This project developed a framework leveraging large language models (LLMs) to transform complex biosecurity guidance into accessible information for livestock farmers. The system condenses expert advice from publicly available UK government and veterinary advisory sources to generate more accessible summaries on a purpose‐built platform. Initial implementation targets three UK livestock health challenges for cattle and sheep farmers with the purpose of demonstrating a proof of concept: sheep scab, liver fluke and Johne's disease.

Results

Bitesize Biosecurity provides a centralised repository where farmers can access evidence‐based recommendations without navigating complex literature or multiple websites. The system maintains scientific integrity while presenting guidance in practical, actionable formats.

Limitations

The effectiveness of the framework depends on the quality and availability of source materials. In this study, implementation was limited to three diseases and the UK context, with system performance reliant on LLM accuracy in content transformation process and summary generation.

Conclusion

This tool addresses critical gaps in agricultural communication by streamlining knowledge transfer between research institutions and practitioners. The scalable architecture enables expansion to additional diseases, farm types and regions, with the potential to transform biosecurity information communication across the agricultural sector.

Autor:innen und Institutionen

  • Centre for Epidemiology and Planetary Health Scotland's Rural College Inverness UK.
  • Rural Policy Centre Scotland's Rural College Edinburgh UK.
  • UHI Inverness University of the Highlands and Islands Inverness UK.
  • Moredun Research Institute Pentlands Science Park Edinburgh UK.

ORCID-Profile: Alexander F B Carmichael, Lorna A Pate, Andrew J Duncan, Lynsey Melville

Förderung

  • Rural and Environment Science and Analytical Services Division

Zitieren

APA

Carmichael, A. F. B., Pate, L. A., Duncan, A. J., Melville, L., & Lamont, K. (2026). Bitesize Biosecurity: A tool and framework for curating and summarising expert biosecurity advice for farmers using artificial intelligence. Veterinary Record Open, 13(1). https://doi.org/10.1002/vro2.70035

Vancouver

Carmichael AFB, Pate LA, Duncan AJ, Melville L, Lamont K. Bitesize Biosecurity: A tool and framework for curating and summarising expert biosecurity advice for farmers using artificial intelligence. Veterinary Record Open. 2026;13(1). doi:10.1002/vro2.70035

BibTeX
@article{Carmichael2026,
  author = {Carmichael, Alexander F B and Pate, Lorna A and Duncan, Andrew J and Melville, Lynsey and Lamont, Kate},
  title = {Bitesize Biosecurity: A tool and framework for curating and summarising expert biosecurity advice for farmers using artificial intelligence},
  journal = {Veterinary Record Open},
  year = {2026},
  volume = {13},
  number = {1},
  doi = {10.1002/vro2.70035}
}
Kostenlos starten →