Discriminating between true-positive and false-positive clinical mastitis alerts from automatic milking systems

Steeneveld, W.; Gaag, Linda C. van der; Ouweltjes, W.; Mollenhorst, H.; Hogeveen, H.

doi:10.3168/jds.2009-3020

Cited by 48 publications

(49 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mansell and Seguya (2003) estimated the Se and Sp of a different hand-held conductivity meter to be 51% and 71%, respectively for the detection of subclincal mastitis. A study conducted using an in-line conductivity system estimated the Se and Sp of electrical conductivity to be 70% and 98%, respectively for the detection of clinical mastitis (Steeneveld et al, 2010). The present study included a population of cows with subclinical and clinical mastitis and the results of our Bayesian model are different but closer to the estimates derived from the latter study.…”

Section: Discussionsupporting

confidence: 64%

Sensitivity and specificity of a hand-held milk electrical conductivity meter compared to the California mastitis test for mastitis in dairy cattle

Fosgate

Petzer

Karzis

2013

The Veterinary Journal

View full text Add to dashboard Cite

Screening tests for mastitis can play an important role in proactive mastitis control programs to reduce the economic impact of this disease. The primary objective of this study was to compare the accuracy of milk electrical resistance (MER) to the California milk cell test (CMCT) in commercial dairy cattle of South Africa using Bayesian methods without a perfect reference test. A total of 1,848 quarter milk specimens were collected from 173 cows sampled during 6 sequential farm visits and 25.8% yielded pathogenic bacterial isolates.Most frequently isolated bacterial species were coagulase negative Staphylococci (n = 346), Streptococcus agalactiae (n = 54), and Staphylococcus aureus (n = 42). The overall cowlevel prevalence of mastitis was 54% based on the Bayesian latent class analysis and the prevalence varied by quarter. The CMCT was more accurate than MER for classification of cows as having somatic cell counts >200,000/ml and isolation of a bacterial pathogen.Bayesian latent class analysis also suggested an overall benefit of CMCT over MER but the difference was not highly statistically probable. The Bayesian model estimated the sensitivity and specificity of MER at a cut-point of >25 mΩ/cm to be 89.9% and 86.8% respectively.The CMCT had a sensitivity and specificity of 94.5% and 77.7% respectively when evaluated at the slight positive cut-point. Milk electrical resistance was useful for identifying milk specimens harboring pathogens but was not able to differentiate among evaluated bacterial isolates. Screening tests can be used to improve udder health as part of a proactive management plan.

show abstract

Section: Discussionsupporting

confidence: 64%

Sensitivity and specificity of a hand-held milk electrical conductivity meter compared to the California mastitis test for mastitis in dairy cattle

Fosgate

Petzer

Karzis

2013

The Veterinary Journal

View full text Add to dashboard Cite

show abstract

“…The prevalence of quarters with mastitis on the present work with AMS was 9%, lower than that in Dimitar & Metodija (2012) study, where prevalence was also analysed at milk quarter level (15%). Although in terms of mastitis detection, the minimum recommendations are a sensitivity of 80% and a specificity of 99% , our AMS mastitis detection system did not reach these figures and our results do not agree with other researchers who reported higher values for specificity and sensitivity in both conventional milking systems (using single quarter samples) (Lam et al, 2009) and in AMS (Steeneveld et al, 2010a). However, these minimum levels for specificity and sensitivity are still under discussion .…”

Section: Mastitis Control With Amscontrasting

confidence: 57%

Mastitis diagnosis in ten Galician dairy herds (NW Spain) with automatic milking systems

Castro

Pereira

Amiama

et al. 2015

Span. j. agric. res.

View full text Add to dashboard Cite

Over the last few years, the adoption of automatic milking systems (AMS) has experienced significant increase. However, hardly any studies have been conducted to investigate the distribution of mastitis pathogens in dairy herds with AMS. Because quick mastitis detection in AMS is very important, the primary objective of this study was to determine operational reliability and sensibility of mastitis detection systems from AMS. Additionally, the frequency of pathogen-specific was determined. For this purpose, 228 cows from ten farms in Galicia (NW Spain) using this system were investigated. The California Mastitis Test (CMT) was considered the gold-standard test for mastitis diagnosis and milk samples were analysed from CMT-positive cows for the bacterial examination. Mean farm prevalence of clinical mastitis was 9% and of 912 milk quarters examined, 23% were positive to the AMS mastitis detection system and 35% were positive to the CMT. The majority of CMT-positive samples had a score of 1 or 2 on a 1 (lowest mastitis severity) to 4 (highest mastitis severity) scale. The average sensitivity and specificity of the AMS mastitis detection system were 58.2% and 94.0% respectively being similar to other previous studies, what could suggest limitations for getting higher values of reliability and sensibility in the current AMSs. The most frequently isolated pathogens were Streptococcus dysgalactiae (8.8%), followed by Streptococcus uberis (8.3%) and Staphylococcus aureus (3.3%). The relatively high prevalence of these pathogens indicates suboptimal cleaning and disinfection of teat dipping cups, brushes and milk liners in dairy farms with AMS in the present study.Additional key words: automatic milking system; mastitis detection; pathogen.

show abstract

“…Nevertheless, the NBC method can yield excellent performances, even if the assumption of independence is violated (Pazzani, 1997). Furthermore, Steeneveld et al (2010) attempted to improve their classification of TP mastitis cases by expanding their naïve Bayesian network to include dependencies between their included variables, but the resulting classification performance was not improved. We therefore consider the multivariate DLM/NBC method to be a reasonable compromise between accounting for codependencies between continuous variables while still allowing for easy incorporation of all available data, including the categorical nonsensor variables.…”

Section: Dlm/nbc Methodologymentioning

confidence: 97%

Bayesian integration of sensor information and a multivariate dynamic linear model for prediction of dairy cow mastitis

Jensen

Hogeveen

Vries

2016

Journal of Dairy Science

View full text Add to dashboard Cite

Rapid detection of dairy cow mastitis is important so corrective action can be taken as soon as possible. Automatically collected sensor data used to monitor the performance and the health state of the cow could be useful for rapid detection of mastitis while reducing the labor needs for monitoring. The state of the art in combining sensor data to predict clinical mastitis still does not perform well enough to be applied in practice. Our objective was to combine a multivariate dynamic linear model (DLM) with a naïve Bayesian classifier (NBC) in a novel method using sensor and nonsensor data to detect clinical cases of mastitis. We also evaluated reductions in the number of sensors for detecting mastitis. With the DLM, we co-modeled 7 sources of sensor data (milk yield, fat, protein, lactose, conductivity, blood, body weight) collected at each milking for individual cows to produce one-step-ahead forecasts for each sensor. The observations were subsequently categorized according to the errors of the forecasted values and the estimated forecast variance. The categorized sensor data were combined with other data pertaining to the cow (week in milk, parity, mastitis history, somatic cell count category, and season) using Bayes' theorem, which produced a combined probability of the cow having clinical mastitis. If this probability was above a set threshold, the cow was classified as mastitis positive. To illustrate the performance of our method, we used sensor data from 1,003,207 milkings from the University of Florida Dairy Unit collected from 2008 to 2014. Of these, 2,907 milkings were associated with recorded cases of clinical mastitis. Using the DLM/NBC method, we reached an area under the receiver operating characteristic curve of 0.89, with a specificity of 0.81 when the sensitivity was set at 0.80. Specificities with omissions of sensor data ranged from 0.58 to 0.81. These results are comparable to other studies, but differences in data quality, definitions of clinical mastitis, and time windows make comparisons across studies difficult. We found the DLM/NBC method to be a flexible method for combining multiple sensor and nonsensor data sources to predict clinical mastitis and accommodate missing observations. Further research is needed before practical implementation is possible. In particular, the performance of our method needs to be improved in the first 2 wk of lactation. The DLM method produces forecasts that are based on continuously estimated multivariate normal distributions, which makes forecasts and forecast errors easy to interpret, and new sensors can easily be added.

show abstract

Discriminating between true-positive and false-positive clinical mastitis alerts from automatic milking systems

Cited by 48 publications

References 21 publications

Sensitivity and specificity of a hand-held milk electrical conductivity meter compared to the California mastitis test for mastitis in dairy cattle

Sensitivity and specificity of a hand-held milk electrical conductivity meter compared to the California mastitis test for mastitis in dairy cattle

Mastitis diagnosis in ten Galician dairy herds (NW Spain) with automatic milking systems

Bayesian integration of sensor information and a multivariate dynamic linear model for prediction of dairy cow mastitis

Contact Info

Product

Resources

About