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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

What can be done virtually? A modified Delphi study offering guidance on virtual companion animal physical examinations.

The Veterinary record·2026
Same author

Veterinary clients view the Value Matrix as a valuable communication tool to aid veterinarian-client decision-making.

Journal of the American Veterinary Medical Association·2026
Same author

Exploring veterinarians' perceptions of decision-making with clients in the context of providing access to veterinary care.

PloS one·2026
Same author

Johne's Disease Control in Beef Cattle: Balancing Test-and-Cull Strategies with Economic and Epidemiological Trade-Offs.

Veterinary sciences·2025
Same author

Associations between endometrial swab bacteriology and cytology findings and live foal rates in Thoroughbred broodmares in the United Kingdom.

Equine veterinary journal·2025
Same author

Born to run? Associations between gestational and early-life exposures and later-life performance outcomes in Thoroughbreds.

Equine veterinary journal·2025

Related Experiment Video

Updated: Jun 28, 2025

Application of Long-term cultured Interferon-γ Enzyme-linked Immunospot Assay for Assessing Effector and Memory T Cell Responses in Cattle
15:57

Application of Long-term cultured Interferon-γ Enzyme-linked Immunospot Assay for Assessing Effector and Memory T Cell Responses in Cattle

Published on: July 11, 2015

12.2K

Comparison of Machine Learning Tree-Based Algorithms to Predict Future Paratuberculosis ELISA Results Using Repeat

Jamie Imada1, Juan Carlos Arango-Sabogal2, Cathy Bauman1

  • 1Department of Population Medicine, University of Guelph, Guelph, ON N1G 2W1, Canada.

Animals : an Open Access Journal From MDPI
|April 13, 2024
PubMed
Summary
This summary is machine-generated.

Machine learning, specifically random forest models, can predict future Johne's disease (a bovine illness) test results using milk data. This offers a promising approach for targeted Johne's testing in dairy herds.

Keywords:
Johne’s diseasecattledairy farmingdecision treediagnosticsdisease controlmachine learningparatuberculosisrandom forest

More Related Videos

Milk Collection Methods for Mice and Reeves' Muntjac Deer
07:34

Milk Collection Methods for Mice and Reeves' Muntjac Deer

Published on: July 19, 2014

19.9K
An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice
04:56

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice

Published on: March 28, 2025

592

Related Experiment Videos

Last Updated: Jun 28, 2025

Application of Long-term cultured Interferon-γ Enzyme-linked Immunospot Assay for Assessing Effector and Memory T Cell Responses in Cattle
15:57

Application of Long-term cultured Interferon-γ Enzyme-linked Immunospot Assay for Assessing Effector and Memory T Cell Responses in Cattle

Published on: July 11, 2015

12.2K
Milk Collection Methods for Mice and Reeves' Muntjac Deer
07:34

Milk Collection Methods for Mice and Reeves' Muntjac Deer

Published on: July 19, 2014

19.9K
An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice
04:56

An Efficient Single—Person Technique for Milk Sampling from Laboratory Mice

Published on: March 28, 2025

592

Area of Science:

  • Veterinary Medicine
  • Animal Husbandry
  • Data Science
  • Machine Learning Applications

Background:

  • Machine learning (ML) applications in animal husbandry and veterinary medicine are emerging.
  • The use of ML for Johne's disease (paratuberculosis) diagnosis and control remains limited.
  • Johne's disease poses significant economic challenges to the dairy industry.

Purpose of the Study:

  • To explore the efficacy of tree-based ML algorithms (decision trees, random forest) in predicting Johne's disease.
  • To analyze repeat milk testing data for predictive modeling of future Johne's test outcomes.
  • To assess the performance of ML models in diagnosing Johne's disease in dairy cows.

Main Methods:

  • Applied decision tree and random forest algorithms to milk testing data from 1197 Canadian dairy cows.
  • Utilized milk component testing results and historical Johne's test data as input features.
  • Evaluated model performance using metrics such as kappa, ROC AUC, sensitivity, specificity, and predictive values.

Main Results:

  • Random forest models incorporating milk components and past Johne's results showed strong predictive performance for dichotomous Johne's ELISA outcomes.
  • The optimal random forest model achieved a kappa of 0.626, ROC AUC of 0.915, 72% sensitivity, and 98% specificity.
  • Decision tree models offered interpretability with a marginal reduction in sensitivity compared to random forest.

Conclusions:

  • Tree-based machine learning algorithms, particularly random forest, demonstrate significant potential for predicting Johne's disease status in dairy cattle.
  • These models can enhance the development of targeted Johne's testing strategies, improving disease management efficiency.
  • Further validation in real-world settings and integration into control programs are recommended.