Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Diagnosing scrapie in sheep: a classification experiment.

Ludmila I Kuncheva1, Victor J del Rio Vilas, Juan J Rodríguez

  • 1School of Informatics, University of Wales, Bangor, UK. l.i.kuncheva@bangor.ac.uk

Computers in Biology and Medicine
|January 16, 2007
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Enhancing laboratory testing capacity: strategies for pandemic preparedness.

Health care management science·2026
Same author

Animal re-identification in video through track clustering.

Pattern analysis and applications : PAA·2025
Same author

Within-laboratory SARS-CoV-2 real time PCR testing operations in Nepal: a simulation-based analysis.

The Lancet regional health. Southeast Asia·2025
Same author

Cardiovascular Complications in Coronavirus Disease 2019-Pathogenesis and Management.

Seminars in respiratory and critical care medicine·2023
Same author

Public health research priorities for WHO on COVID-19 in the South-East Asia Region: results of a prioritization survey.

Health research policy and systems·2022
Same author

The Relative Importance of Vulnerability and Efficiency in COVID-19 Contact Tracing Programmes: A Discrete Choice Experiment.

International journal of public health·2022

Veterinary officials

Area of Science:

  • Veterinary medicine
  • Animal pathology
  • Machine learning applications in animal health

Background:

  • Scrapie is a fatal neurodegenerative disease affecting small ruminants.
  • Accurate diagnosis is crucial for disease control and management.
  • Clinical signs are often the first indicators of scrapie in affected animals.

Purpose of the Study:

  • To evaluate the efficacy of clinical signs in differentiating healthy sheep from those suspected of scrapie.
  • To assess the performance of various machine learning classification methods for scrapie diagnosis based on clinical data.
  • To determine if clinical classification by veterinary officials is sufficient for initial scrapie suspect identification.

Main Methods:

  • Analysis of 3113 sheep records from the Great Britain Scrapie Notifications Database.

Related Experiment Videos

  • Recording of clinical signs (present/absent) by veterinary officials (VO).
  • Application of 18 diverse classification algorithms, including linear classifiers, Bagging, AdaBoost, and Random Forests.

    • Main Results:

    • The study applied 18 classification methods to identify healthy animals among scrapie suspects using clinical signs.
    • No machine learning model could reliably differentiate healthy from scrapie-suspect animals based solely on clinical data.
    • The clinical classification performed by veterinary officials was deemed adequate for initial suspect identification.

    Conclusions:

    • Clinical signs recorded by veterinary officials are sufficient for the initial classification of scrapie suspects in sheep.
    • Advanced machine learning techniques did not improve the differentiation of healthy animals from scrapie suspects using only clinical data.
    • Further diagnostic steps beyond clinical assessment are necessary for definitive scrapie diagnosis.