A cow-specific probability of having clinical mastitis for use in automatic milking systems

W. Steeneveld; L.C. van der Gaag; H.W. Barkema; H. Hogeveen

A cow-specific probability of having clinical mastitis for use in automatic milking systems

In: Precision livestock farming '09

Authors:

W. Steeneveld

W. Steeneveld ¹Dept. of Farm Animal Health, Faculty of Veterinary Medicine, Utrecht University, Utrecht, the Netherlands; w.steeneveld@uu.nl

Search for other papers by W. Steeneveld in
Current site
Google Scholar
PubMed

L.C. van der Gaag

L.C. van der Gaag ²Dept. of Information and Computing Sciences, Utrecht University, Utrecht, the Netherlands

Search for other papers by L.C. van der Gaag in
Current site
Google Scholar
PubMed

H.W. Barkema

H.W. Barkema ³Dept. of Production Animal Health, Faculty of Veterinary Medicine, University of Calgary, Calgary, Canada

Search for other papers by H.W. Barkema in
Current site
Google Scholar
PubMed

, and

H. Hogeveen

H. Hogeveen ¹Dept. of Farm Animal Health, Faculty of Veterinary Medicine, Utrecht University, Utrecht, the Netherlands; w.steeneveld@uu.nl
⁴Chair group Business Economics, Wageningen University, Wageningen, the Netherlands

Search for other papers by H. Hogeveen in
Current site
Google Scholar
PubMed

Type:: Chapter

Pages:: 323–330

DOI:: https://doi.org/10.3920/9789086866632_040

Purchase instant access (PDF download and unlimited online access):

€42.00€35.00 excl. VAT

Add to Cart

Redeem Access Token

An automatic milking system (AMS) generates clinical mastitis (CM) alert lists. Because of the general assumption of equal probabilities of CM for all cows, the success rate for an alert is the same for all alerts on the list. This study is based on the observation that the performance of a CM detection system is based not just on the test characteristics of the system, but also on the prior probability of a cow having CM. It is expected that using a cow-specific prior probability, based on non-AMS information, to determine the success rate of a CM alert instead of assuming equal probabilities for all cows, is likely to improve the interpretation of CM alert lists. By taking cowspecific prior probabilities into consideration it will be possible to rank-order the alerts on a CM alert list according to their success rate. In this study, a tree-augmented naive Bayesian network was developed to determine cow-specific prior probabilities of CM. The probability tables for the variables in the network were based on data from 274 Dutch dairy herds that recorded and sampled CM over an 18-month period. The final dataset contained information on 28,137 lactations of 22,860 cows, with a total of 5,363 CM cases. The available prior knowledge of a cow (parity, days in milk, season of the year, somatic cell count history and CM history) were included as variables in the network. By combining the cow-specific prior probabilities of CM with the test characteristics of the AMS, the resulting success rate can be used to discriminate between CM alerts. Our illustrations indicate that the success rate ranges from 2 to 97%. Using the success rate, the CM alerts on an alert list can be ranked-ordered, thereby providing the dairy farmer information about which cows have the highest priority for visual inspection for CM.

Citation Info

Save
Cite
Email this content

Share link with colleague or librarian

You can email a link to this page to a colleague or librarian:
Email this content
or copy the link directly:

https://brill.edhh.ma/abstract/book/9789086866632/BP000040.xml
The link was not copied. Your current browser may not support copying via this button.

Link copied successfully

Collapse
Expand

Precision livestock farming '09

E-Book ISBN:: 9789086866632

Publisher:: Wageningen Academic

Print Publication Date:: 30 Oct 2009

Subjects
- Life Sciences
  - General
  - Animal & Veterinary

Metrics

	All Time	Past 365 days
Abstract Views	58	22
Full Text Views	3	0
PDF Views & Downloads	2	0

African Studies	Education	Media Studies
American Studies	History	Middle East and Islamic Studies
Ancient Near East and Egypt	Human Rights and Humanitarian Law	Musicology
Art History	International Law	Philosophy
Asian Studies	International Relations	Religious Studies
Biblical Studies	Jewish Studies	Slavic and Eurasian Studies
Biology	Languages and Linguistics	Social Sciences
Book History and Cartography	Life Sciences	Theology and World Christianity
Classical Studies	Literature and Cultural Studies

Subjects

Authors

Open Access

Product Information

Company

Contact

A cow-specific probability of having clinical mastitis for use in automatic milking systems

Citation Info

Share link with colleague or librarian

Precision livestock farming '09

Table of Contents

Metrics

Metrics