Use of Danish National Somatic Cell Count Data to Assess the Need for Dry-Off Treatment in Holstein Dairy Cattle

Abstract

In Denmark, PCR testing of dairy cattle is commonly used to select animals for the antibacterial treatment of intramammary infection (IMI) during the dry-off period. IMI is associated with a high somatic cell count (SCC), routinely recorded for milk quality control for most commercial dairy herds. This study aimed to compare SCC curves over the lactation among dairy cows with positive vs. negative PCR test results for four major IMI pathogens. Data from 133,877 PCR-tested Holstein cows from 1364 Danish conventional dairy herds were used to fit a nonlinear mixed-effects model using a modified four-parameter Wilmink function. We stratified the data into first, second, third or fourth and later parity and fitted Wilmink curves to all SCC observations between 6 and 305 days in milk. The PCR tests were taken before dry-off at the end of the lactation to investigate which animals qualified for selective dry cow therapy. A PCR Ct-value of 37 and below was used to determine if an animal was PCR positive for any of the following IMI pathogens: Staphylococcus aureus, Streptococcus agalactiae, Str. dysgalactiae and Str. uberis. Our findings showed that mean SCC curve fits were higher for PCR-positive animals in all four parity groups and across lactations. The use of SCC data fitted to the entire lactation for multiple lactations enabled quantification of overall differences in SCC curves between cattle with and without detected IMI, adjusted for parity group and stage of lactation. These findings are relevant to the use of SCC to support treatment decisions.

Keywords: PCR testing; mastitis; wilmink function.

Figure 1

Flowchart showing the process for data cleaning and filtering of data for eligibility with an overview of the total number of herds and animals included in the modelling.

Figure 2

Q-Q plots of the residuals for the eight different models: to the left, with blue, PCR negative for Parities 1, 2, 3, and >3 and to the right, with orange, PCR positive for Parities 1, 2, 3, and >3.

Figure 3

ECDF plots of the between-herd variation in parameter estimates (based on the conditional modes of random effects) for the four NLME estimated Wilmink-parameters, a, b, c, and d, for both PCR positive and negative strata of Parity 2 animals.

Figure 4

logSCC curves created with means of the four estimated NLME Wilmink parameters plotted for each parity group, separated in PCR positive and PCR negative. The dashed line represents a threshold of 200,000 cells per ml, corresponding to 5.3 on the log scale. The numbers in the grey box refer to the Parity group.