Sensor measurements revealed: Predicting the Gram-status of clinical mastitis causal pathogens

Abstract

a b s t r a c tAutomatic milking systems produce mastitis alert lists that report cows likely to have clinical mastitis (CM). A farmer has to check these listed cows to confirm a CM case and to start an antimicrobial treatment if necessary. In order to make a more informed decision, it would be beneficial to have information about the CM causal pathogen at the same time a cow is listed on the mastitis alert list. Therefore, this study explored whether decision-tree induction was able to predict the Gram-status of CM causal pathogens using in-line sensor measurements from automatic milking systems. Data were collected at nine Dutch dairy farms milking with automatic milking systems and included 140 bacteriological cultured CM cases with sensor measurements of electrical conductivity, colors red, green, and blue and milk yield for analyses. In total, 110 CM cases were classified as Gram-positive CM cases and 30 as Gram-negative. Stratified randomization was used to divide the data in a training set (n = 96) for model development, and a test set (n = 44) for validation. The decision tree used three variables to predict the Gram-status of the CM causal pathogen; two variables were based on electrical conductivity measurements, and one on measurements of the color blue. This decision tree had an accuracy of 90.6% and a kappa value of 0.76 based on data in the training set. When only those CM cases were considered with extreme high probability estimates for their Gram-status (either positive or negative), 74% of all records in the training set could be classified with a stratified accuracy of 97.1%. When validated, the decision tree performed poorly; accuracy dropped to 54.5% and the kappa value to À0.20. The stratified accuracy calculated for 75% of all records in the test set was 66.7%. Predicting the CM causal pathogen showed a similar poor result; the decision tree had an accuracy of 27.9% and a kappa of 0.12, based on data in the test set. Based on these results, it is concluded that decision-tree induction in conjunction with sensor information from the electrical conductivity, color, and milk yield provide insufficient discriminative power to predict the Gram-status or the CM causal pathogen itself.

Identifying gram-negative and gram-positive clinical mastitis using daily milk component and behavioral sensor data

“…When classifying a known CM case by gram status, Steeneveld et al (2009) reported 73% accuracy, which increased to 95% when a probability threshold of >0.9 was implemented. Similarly, Kamphuis et al (2011) reported 91% accuracy when classifying known CM cases as GP or GN based on the training data set, but accuracy declined to 55% when an independent test data set was used. Across 37 sensor systems developed for automated mastitis detection, the reported Se ranged from 55 to 89% and Sp ranged from 56 to 99% (Rutten et al, 2013).…”

“…These differences are likely to be reflected in milking performance, milk components, and behavioral parameters in the lead up to clinical presentation of mastitis, providing an opportunity for mastitis detection using sensors in conventional milking systems as well as automatic milking systems. Few researchers have used sensor data to categorize CM cases by gram status, where electrical conductivity and milk color (Kamphuis et al, 2011) or parity, DIM, and CM or SCC history (Steeneveld et al, 2009) have been used as inputs for predictive models. With access to more sensor inputs, such as milk components, the detection performance was improved for CM regardless of pathogen type (Jensen et al, 2016).…”

Treatment of Clinical Mastitis

“…The researchers concluded that this method provided insufficient discriminative power to predict the Gram-status or the clinical mastitis pathogen itself. 14 The logistics of using culture-based therapy has been challenging. Many dairies did not have a mechanism to get milk culture results back in a timely manner.…”

Invited review: Sensors to support health management on dairy farms

“…However, the current trend in western Europe is the use of AMS, which have changed the operational management on dairy farms dramatically. A few studies have focused on pathogen-specific treatment of mastitis, although the economic merit and practical feasibility of pathogenspecific treatment seems to be absent (Kamphuis et al, 2011;Steeneveld et al, 2011). Decision support systems are available for fertility management (Groenendaal et al, 2004;Olynk and Wolf, 2009;Inchaisri et al, 2010Inchaisri et al, , 2011 and could be used to develop sensor systems with integrated decision support.…”