Related Experiment Video
Updated: May 16, 2025
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
12.1K
Using Supervised Machine Learning Algorithms to Predict Bovine Leukemia Virus Seropositivity in Florida Beef Cattle:
Ameer A Megahed1,2, Y Reddy Bommineni1,3, Michael Short3
1Department of Large Animal Clinical Sciences, College of Veterinary Medicine, University of Florida, Gainesville, Florida, USA.
Journal of Veterinary Internal Medicine
|April 2, 2025
Summary
Bovine leukemia virus (BLV) infection in beef cattle can be predicted using machine learning models. The random forest model identified dry season testing and southern Florida location as key risk factors for BLV seropositivity.
Area of Science:
- Veterinary Medicine
- Animal Science
- Machine Learning in Agriculture
Background:
- Bovine leukemia virus (BLV) infection impacts the beef industry, yet receives less attention than in dairy herds.
- Understanding BLV risk factors in beef cattle is crucial for industry health.
Purpose of the Study:
- To compare six supervised machine-learning (SML) algorithms for predicting BLV seropositivity in Florida beef cattle.
- To identify the most significant risk factors associated with BLV infection in this population.
Main Methods:
- A retrospective study analyzed 1511 BLV antibody test records from Florida (2012-2022).
- Six SML algorithms were evaluated: logistic regression, decision tree, gradient boosting, random forest, neural network, and support vector machine.
Main Results:
- 11.6% of tested beef cattle samples were BLV positive.
- The random forest (RF) model demonstrated the highest predictive accuracy (AUROC=0.98), outperforming other algorithms.
- Key predictors identified by the RF model included testing during the dry season (coinciding with pre-calving/calving) and southern Florida location.
Conclusions:
- The random forest model is a promising tool for predicting BLV seropositivity in beef cattle.
- Identifying high-risk periods (dry, pre-calving, calving seasons) and locations can guide targeted BLV screening and intervention strategies.
- This predictive approach can enhance BLV management in the beef industry.
