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

Multiple Regression01:25

Multiple Regression

3.7K
Multiple regression assesses a linear relationship between one response or dependent variable and two or more independent variables. It has many practical applications.
Farmers can use multiple regression to determine the crop yield based on more than one factor, such as water availability, fertilizer, soil properties, etc. Here, the crop yield is the response or dependent variable as it depends on the other independent variables. The analysis requires the construction of a scatter plot...
3.7K
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

284
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
284

You might also read

Related Articles

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

Sort by
Same author

Can trained behavior serve as tool for welfare assessment? A pilot study in a cancer model with Wistar rats.

Laboratory animals·2026
Same author

Evaluating Reticulorumen Temperature, Rumination, Activity and pH Measured by Rumen Sensors as Indicators of Heat Load in Fattening Bulls.

Sensors (Basel, Switzerland)·2025
Same author

Occurrence, treatment and pathogens involved in mastitis on a commercial German dairy farm: A retrospective study from 2012 to 2021.

Journal of advanced veterinary and animal research·2025
Same author

Evaluation of the Effects of an Undenatured Collagen Type-2-Based Nutraceutical (ARTHROSHINE<sup>®</sup> HA²) on Recovery Time after TPLO in Dogs: A Prospective, Randomized Study with Objective Gait Analysis as the Primary Outcome Measure.

Animals : an open access journal from MDPI·2024
Same author

Opportunities to Improve Animal Welfare during Transport and Slaughter of Cattle and Pigs through Staff Training-Results of a Delphi Survey.

Animals : an open access journal from MDPI·2023
Same author

Innovative e-Learning Training Modules to Improve Animal Welfare during Transport and Slaughter of Pigs: A Pretest-Posttest Study to Pre-Evaluate the General Didactical Concept.

Animals : an open access journal from MDPI·2023

Related Experiment Video

Updated: Jan 15, 2026

Bovine Mammary Gland Biopsy Techniques
14:53

Bovine Mammary Gland Biopsy Techniques

Published on: December 23, 2018

15.0K

Farm-Specific Effects in Predicting Mastitis by Applying Machine Learning Models to Automated Milking System and

Muhammad N Dharejo1, Olivier Kashongwe2, Thomas Amon2,3

  • 1Institute for Veterinary Epidemiology & Biostatistics, School of Veterinary Medicine, Free University of Berlin, House 21, Königsweg 57, 14163 Berlin, Germany.

Animals : an Open Access Journal From MDPI
|October 16, 2025
PubMed
Summary

Machine learning models show promise for predicting mastitis in dairy cows using automated milking system data. However, farm-specific factors significantly impact model accuracy, necessitating tailored approaches for effective herd management.

Keywords:
automatic milking systemfarm-specific effectsmachine learning modelsmastitis predictiontime series data

More Related 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

7.4K
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

20.5K

Related Experiment Videos

Last Updated: Jan 15, 2026

Bovine Mammary Gland Biopsy Techniques
14:53

Bovine Mammary Gland Biopsy Techniques

Published on: December 23, 2018

15.0K
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

7.4K
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

20.5K

Area of Science:

  • Veterinary Medicine
  • Animal Science
  • Data Science

Background:

  • Mastitis poses significant economic challenges in dairy farming.
  • Early and accurate mastitis detection is vital for herd health and profitability.
  • Automated milking systems (AMS) generate extensive data for potential predictive modeling.

Purpose of the Study:

  • To evaluate the accuracy of machine learning (ML) models in predicting mastitis.
  • To investigate the influence of farm-specific factors on ML model performance for mastitis prediction.
  • To assess the generalizability of ML models across different dairy farms.

Main Methods:

  • Analysis of 5.88 million observations from four German dairy farms (2019-2024).
  • Application of six ML algorithms using AMS and farm management data.
  • Evaluation of model performance using accuracy, sensitivity, specificity, and AUC, with farm-specific and leave-one-out analyses.

Main Results:

  • Combined farm data yielded high prediction performance (AUC 91-96%).
  • Individual farm analysis showed excellent internal model adaptation (AUC up to 98%).
  • Significant performance drops were observed in leave-one-out cross-validation, indicating poor generalization.

Conclusions:

  • Farm-specific data patterns influence ML model accuracy for mastitis prediction.
  • A one-size-fits-all approach is insufficient; tailored ML models are needed for each farm.
  • Integrating farm-specific characteristics into ML models can enhance mastitis prediction accuracy.