We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Machine Learning to Predict Pregnancy in Dairy Cows: An Approach Integrating Automated Activity Monitoring and On-Farm Data.
- Authors
Marques, Thaisa Campos; Marques, Letícia Ribeiro; Fernandes, Patrick Bezerra; de Lima, Fabio Soares; do Prado Paim, Tiago; Leão, Karen Martins
- Abstract
Simple Summary: Scientists have developed a way to more accurately predict when dairy cows are most likely to become pregnant using automated activity monitoring (AAM) systems to track their activity. These systems track the cow's movement and behavior in real time, which is crucial for determining the best time for artificial insemination (AI). This study used data from over a thousand Holstein cows to create a mathematical model that predicts pregnancy chances at the time of AI, considering not just the cow's activity data but also individual health, the environment, and even the specific bull used for insemination. This study found that combining on-farm data (like health and environmental conditions) with the AAM data gives a clearer picture of a cow's pregnancy chances compared to using AAM data alone. The random forest model, one of the mathematical methods used, was particularly good at reducing errors in prediction. This research suggests that merging detailed farm data with automated monitoring can greatly improve the predictions of pregnancy at the time of AI, which is beneficial for managing dairy cow reproduction efficiently. Automated activity monitoring (AAM) systems are critical in the dairy industry for detecting estrus and optimizing the timing of artificial insemination (AI), thus enhancing pregnancy success rates in cows. This study developed a predictive model to improve pregnancy success by integrating AAM data with cow-specific and environmental factors. Utilizing data from 1,054 cows, this study compared the pregnancy outcomes between two AI timings—8 or 10 h post-AAM alarm. Variables such as age, parity, body condition, locomotion, and vaginal discharge scores, peripartum diseases, the breeding program, the bull used for AI, milk production at the time of AI, and environmental conditions (season, relative humidity, and temperature–humidity index) were considered alongside the AAM data on rumination, activity, and estrus intensity. Six predictive models were assessed to determine their efficacy in predicting pregnancy success: logistic regression, Bagged AdaBoost algorithm, linear discriminant, random forest, support vector machine, and Bagged Classification Tree. Integrating the on-farm data with AAM significantly enhanced the pregnancy prediction accuracy at AI compared to using AAM data alone. The random forest models showed a superior performance, with the highest Kappa statistic and lowest false positive rates. The linear discriminant and logistic regression models demonstrated the best accuracy, minimal false negatives, and the highest area under the curve. These findings suggest that combining on-farm and AAM data can significantly improve reproductive management in the dairy industry.
- Subjects
DAIRY cattle; MACHINE learning; CATTLE fertility; ESTRUS; PREGNANCY outcomes; PREGNANCY; SUPPORT vector machines
- Publication
Animals (2076-2615), 2024, Vol 14, Issue 11, p1567
- ISSN
2076-2615
- Publication type
Article
- DOI
10.3390/ani14111567