Jove
Visualize
Contact Us

Related Concept Videos

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
  1. Home
  3. Application Of Machine Learning Models For The Early Detection Of Metritis In Dairy Cows Based On Physiological, Behavioural And Milk Quality Indicators.
  1. Home
  3. Application Of Machine Learning Models For The Early Detection Of Metritis In Dairy Cows Based On Physiological, Behavioural And Milk Quality Indicators.

Related Experiment Video

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

Application of Machine Learning Models for the Early Detection of Metritis in Dairy Cows Based on Physiological,

Karina Džermeikaitė1, Justina Krištolaitytė1, Ramūnas Antanaitis1

  • 1Animal Clinic, Veterinary Academy, Lithuania University of Health Sciences, Tilžės Str. 18, LT-47181 Kaunas, Lithuania.

Animals : an Open Access Journal From MDPI
|June 13, 2025

View abstract on PubMed

Summary
This summary is machine-generated.
Keywords:
dairy cowearly diagnosismachine learningmetritisprecision livestock farming

More Related Videos

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

552
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

Related Experiment Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
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

552
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

Machine learning models accurately detect early bovine metritis using non-invasive farm data. Neural networks show highest performance, enabling improved dairy cow health and welfare through automated monitoring.

Area of Science:

  • Veterinary Medicine
  • Animal Health Monitoring
  • Machine Learning in Agriculture

Background:

  • Metritis is a common postpartum disease in dairy cows, leading to reduced reproductive performance and economic losses.
  • Early detection of metritis is crucial for timely intervention and improved animal welfare.

Purpose of the Study:

  • To investigate the efficacy of machine learning (ML) techniques for early detection of metritis in dairy cows.
  • To evaluate ML models using physiological, behavioral, and milk quality parameters from routinely collected on-farm data.

Main Methods:

  • Collected 2707 daily observations from 94 cows, including body weight, rumination, milk yield/composition, SCC, and feed intake.
  • Developed and compared five ML models: PLS-DA, RF, SVM, NN, and Ensemble, using stratified 80/20 splits and class weights for imbalance.
  • Evaluated models using accuracy, AUC, MCC, sensitivity, specificity, PPV, and NPV.

    • Main Results:

    • The Neural Network (NN) model achieved the highest overall performance (accuracy = 96.1%, AUC = 96.3%, MCC = 0.79).
    • SVM showed the highest sensitivity (90.9%), while RF and Ensemble models exhibited high specificity (>98%) and PPV.
    • ML models effectively distinguished between healthy and metritic cows using non-invasive, automated data.

    Conclusions:

    • Machine learning, particularly NN and Ensemble models, can effectively detect early-stage metritis in dairy cows.
    • Integration of these ML models into automated health monitoring systems can enhance early disease detection and animal welfare.
    • The study demonstrates the potential of using routinely collected, non-invasive on-farm data for disease prediction in dairy herds.