A novel method of analyzing daily milk production and electrical conductivity to predict disease onset

Effects of targeted clinical examination based on alerts from automated health monitoring systems on herd health and performance of lactating dairy cows

Our objectives were to compare the proportion of lactating dairy cows diagnosed with health disorders (HD) and herd performance when using a health monitoring program designed to rely primarily but not exclusively on alerts from automated health monitoring (AHM) systems or a health monitoring program based primarily on systematic clinical examinations, milk yield monitoring, and visual observation of cows. In a clinical trial, at ∼30 d before expected parturition, nulliparous and parous Holstein cows, stratified by parity and days in gestation, were randomly assigned to the high-intensity clinical monitoring (HIC-M; n = 625) or automated monitoring (AUT-M; n = 624) treatment. Cows were fitted with a neck-attached rumination and physical activity monitoring tag, and individual daily milk yield data were collected from parlor milk meters. For cows in HIC-M, clinical examination was conducted daily until 10 d in milk (DIM) and then in response to milk yield reduction alerts or visual observation of clinical signs of HD over the course of 21 DIM. For cows in AUT-M, clinical examination until 21 DIM was because of health index (HI) score alerts and reduced milk yield alerts. The HI score alerts used were generated based on the manufacturer's settings for the system for the last 2-h period before cows were selected for examination. Visual observation of clinical signs of HD was used for identifying cows potentially missed by automated alerts. Binomial and quantitative data were analyzed by logistic regression and ANOVA with repeated measures, respectively. The percentage of cows diagnosed with at least 1 HD during the experimental treatments risk period tended to be greater and the incidence rate ratio of HD diagnosed was greater in the HIC-M than in the AUT-M treatment. We found no difference between treatments for cows that exited the herd up to 60 or 150 DIM, but more cows tended to exit the herd from 61 to 150 DIM in the HIC-M than in the AUT-M treatment. No differences were detectable between treatments in daily or total milk yield to 21 DIM or in weekly mean milk yield and total milk yield to 150 DIM. More cows were inseminated in estrus for first service if in the HIC-M treatment and had no HD diagnosed than if in the HIC-M treatment but with HD diagnosed, or in the AUT-M treatment and had no HD diagnosed. Cows in the AUT-M treatment with HD diagnosed did not differ from other groups. No differences between treatments were observed in pregnancies per artificial insemination or pregnancy loss for first service. Despite a reduction in the risk of diagnosis of HD, no evidence indicated that a health monitoring program that relied on AHM system alerts to select cows for clinical examination reduced herd performance compared with a more intensive program that included systematic clinical examinations of all cows for the first 10 DIM, reduced milk yield alerts, and visual observation. However, to obtain the same herd performance as with the HIC-M treatment, the AUT-M treatment required use of visual observation. In conclusion, a health monitoring program designed to rely primarily on targeted clinical examination based on alerts from automated health monitoring systems might be a feasible alternative to programs that rely more on clinical examination, provided that visual observation is used to identify cows not detected by automated alerts.

Seasonal autoregressive integrated moving average (SARIMA) time-series model for milk production forecasting in pasture-based dairy cows in the Andean highlands

Milk production in the Andean highlands is variable over space and time. This variability is related to fluctuating environmental factors such as rainfall season which directly influence the availability of livestock feeding resources. The main aim of this study was to develop a time-series model to forecast milk production in a mountainous geographical area by analysing the dynamics of milk records thorough the year. The study was carried out in the Andean highlands, using time-series models of monthly milk records collected routinely from dairy cows maintained in a controlled experimental farm over a 9-year period (2008-2016). Several statistical forecasting models were compared. The Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percent Error (MAPE) were used as selection criteria to compare models. A relation between monthly milk records and the season of the year was modelled using seasonal autoregressive integrated moving average (SARIMA) methods to explore temporal redundancy (trends and periodicity). According to white noise residual test (Q = 13.951 and p = 0.052), Akaike Information Criterion and MAE, MAPE, and RMSE values, the SARIMA (1, 0, 0) x (2, 0, 0)12 time-series model resulted slightly better forecasting model compared to others. In conclusion, time-series models were promising, simple and useful tools for producing reasonably reliable forecasts of milk production thorough the year in the Andean highlands. The forecasting potential of the different models were similar and they could be used indistinctly to forecast the milk production seasonal fluctuations. However, the SARIMA model performed the best good predictive capacity minimizing the prediction interval error. Thus, a useful effective strategy has been developed by using time-series models to monitor milk production and alleviate production drops due to seasonal factors in the Andean highlands.

Mastitis in Dairy Cattle: On-Farm Diagnostics and Future Perspectives

Mastitis is one of the most important diseases in dairy cattle farms, and it can affect the health status of the udder and the quantity and quality of milk yielded. The correct management of mastitis is based both on preventive and treatment action. With the increasing concern for antimicrobial resistance, it is strongly recommended to treat only the mammary quarters presenting intramammary infection. For this reason, a timely and accurate diagnosis is fundamental. The possibility to detect and characterize mastitis directly on farm would be very useful to choose the correct management protocol. Some on-field diagnostic tools are already routinely applied to detect mastitis, such as the California Mastitis Test and on-farm culture. Other instruments are emerging to perform a timely diagnosis and to characterize mastitis, such as Infra-Red Thermography, mammary ultrasound evaluation and blood gas analysis, even if their application still needs to be improved. The main purpose of this article is to present an overview of the methods currently used to control, detect, and characterize mastitis in dairy cows, in order to perform a timely diagnosis and to choose the most appropriate management protocol, with a specific focus on on-farm diagnostic tools.

Scoping review on clinical definition of bovine respiratory disease complex and related clinical signs in dairy cows

Bovine respiratory disease complex (BRD) is a worldwide multifactorial infectious disease. Antimicrobials are commonly used for treating BRD because bacteria are often involved. The clinical diagnosis of BRD is a challenge, especially in adult dairy cows, where information on this syndrome is scant. Having a definition based on consistent and reliable clinical signs would improve the accuracy of BRD diagnosis and could help to develop an optimal treatment approach by an early detection. The aim of this scoping review was to review clinical signs that could be recognized by producers in dairy cattle suffering from naturally occurring infectious respiratory disease, as reported in the literature. A review of the literature was performed for articles published between January 1, 1990 and January 1, 2020. The search of literature in English, French, and Italian languages included 2 different databases (Pubmed, https://pubmed.ncbi.nlm.nih.gov/; CAB abstract, https://www.cabi.org/publishing-products/cab-abstracts/). Clinical signs were categorized as follows: (1) "general manifestations of disease," which included behavioral changes or fever; (2) "alterations in respiratory function," which included clinical signs specifically associated with the respiratory tract examination; and (3) "clinical signs of other body systems," which included clinical signs related to other systems such as diarrhea or subcutaneous emphysema. The focus of the review was on clinical signs that could be monitored by animal handlers and producers. A total of 1,067 titles were screened, and 23 studies were finally included. The most common general clinical signs were increased body temperature (reported in 83% of studies, n = 19), change in feed intake (26%, n = 6), altered mentation (22%, n = 5), and decreased milk production (17%, n = 4). The alterations in respiratory function noted were nasal discharge (74%, n = 17), cough (65%, n = 15), altered respiratory dynamic or dyspnea (61%, n = 14), increased respiratory rate (43%, n = 10), and ocular discharge or lacrimation (30%, n = 7). The clinical signs associated with infectious respiratory disease reported in the 23 studies generally lacked a clear description of what constitutes a deviation from normality (0-50% of studies clearly reported what was considered normal versus abnormal depending on the clinical signs). This limitation prevented any comparison between studies that apparently reported the same "clinical sign," but possibly referred to a different assessment and definition of what was considered normal versus abnormal. Therefore, the definition of clinical signs in a repeatable way with validated interobserver agreement to determine the optimal combination for the diagnosis of BRD in dairy cows is needed. This could lead to a more judicious use of antimicrobials for respiratory disease in adult dairy cows.

Monitoring and Improving the Metabolic Health of Dairy Cows during the Transition Period

Simple Summary

The transition from late gestation to early lactation is a challenging period for dairy cows. A successful transition period depends on metabolic adaptation to the new physiological state in early lactation and proper management in order to support the cow’s requirements. This review paper will discuss various aspects of routine and consistent approaches to collect and analyze herd records, to detect unintended disruptions in performance. In addition, we discuss how to incorporate methods to assess health, production, nutrition, and welfare information to monitor cows during the transition period. Lastly, we discuss management strategies that can be implemented to improve the metabolic health and performance of transition dairy cows.

Abstract

The peripartum period of a dairy cow is characterized by several physiological and behavioral changes in response to a rapid increase in nutrient demands, to support the final stages of fetal growth and the production of colostrum and milk. Traditionally, the transition period is defined as the period 3 weeks before and 3 weeks after parturition. However, several researchers have argued that the transition period begins at the time of dry-off (~60–50 days prior to calving) and extends beyond the first month post-calving in high producing dairy cows. Independent of the definition used, adequate adaptation to the physiological demands of this period is paramount for a successful lactation. Nonetheless, not all cows are successful in transitioning from late gestation to early lactation, leading to approximately one third of dairy cows having at least one clinical disease (metabolic and/or infectious) and more than half of the cows having at least one subclinical case of disease within the first 90 days of lactation. Thus, monitoring dairy cows during this period is essential to detect early disease signs, diagnose clinical and subclinical diseases, and initiate targeted health management to avoid health and production impairment. In this review, we discuss different strategies to monitor dairy cows to detected unintended disruptions in performance and management strategies that can be implemented to improve the metabolic health and performance of dairy cows during the transition period.

Precision dairy farming: Opportunities and challenges for India

Effective management of a dairy farm has to focus on individual animal apart from group or herd management since 'smallest production unit in the dairy is the individual animal’. In this context, precision dairy farming (PDF) aims to manage the basic production unit in order to exploit its maximal production capacity. PDF is the use of information and technology based farm management system to measure physiological, behavioural and production indicators of individual animals to improve management strategies, profitability and farm performance. PDF applications are finding their way on dairy farms, although there seem to be differences in the uptake of PDF applications between dairy systems. The authors have attempted to identify different PDF tools utilized across the globe and have highlighted the status of adoption in Indian scenario by highlighting about few farms/organizations involved in its utilization and uptake over the years. In this direction, the authors have also focused on several benefits and challenges faced by developing countries including India since the benefits are often not immediately apparent and they require more management expertise along with an investment of time and money to realize. In addition, the adoption rate depends on various factors like farmer education, farm size, perceptions of risk, ownership of a non-farm business etc. Addressing these issues is very essential for the uptake of technologies and hence, an effort has been made to propose strategies for adoption and operationalization of PDF in India and other developing countries where the similar scenario exists. The study also highlights that PDF in many developing countries including India is in its infancy, but there are tremendous opportunities for improvements in individual animal and herd management in dairy farms. The progressive farmers or the farmers’ groups, with guidance from the public and private sectors, and professional associations, can adopt it on a limited scale as the technology shows potential for raising yields and economic returns on fields with significant variability, and for minimizing environmental degradation. Additional research needs to be undertaken to examine the adoption process for not only successful adoption of technology, but also to solve the issues associated with the technology adoption. Further, right extension approaches and advisory services for the farmers interested in PDF needs to be undertaken for its effective application under different socio-economic and ecological conditions.

Using Sensor Data to Detect Lameness and Mastitis Treatment Events in Dairy Cows: A Comparison of Classification Models

The aim of this study was to develop classification models for mastitis and lameness treatments in Holstein dairy cows as the target variables based on continuous data from herd management software with modern machine learning methods. Data was collected over a period of 40 months from a total of 167 different cows with daily individual sensor information containing milking parameters, pedometer activity, feed and water intake, and body weight (in the form of differently aggregated data) as well as the entered treatment data. To identify the most important predictors for mastitis and lameness treatments, respectively, Random Forest feature importance, Pearson’s correlation and sequential forward feature selection were applied. With the selected predictors, various machine learning models such as Logistic Regression (LR), Support Vector Machine (SVM), K-nearest neighbors (KNN), Gaussian Naïve Bayes (GNB), Extra Trees Classifier (ET) and different ensemble methods such as Random Forest (RF) were trained. Their performance was compared using the receiver operator characteristic (ROC) area-under-curve (AUC), as well as sensitivity, block sensitivity and specificity. In addition, sampling methods were compared: Over- and undersampling as compensation for the expected unbalanced training data had a high impact on the ratio of sensitivity and specificity in the classification of the test data, but with regard to AUC, random oversampling and SMOTE (Synthetic Minority Over-sampling) even showed significantly lower values than with non-sampled data. The best model, ET, obtained a mean AUC of 0.79 for mastitis and 0.71 for lameness, respectively, based on testing data from practical conditions and is recommended by us for this type of data, but GNB, LR and RF were only marginally worse, and random oversampling and SMOTE even showed significantly lower values than without sampling. We recommend the use of these models as a benchmark for similar self-learning classification tasks. The classification models presented here retain their interpretability with the ability to present feature importances to the farmer in contrast to the “black box” models of Deep Learning methods.

The relationships between udder-quarter somatic-cell counts and milk and milking parameters in cows managed with an automatic milking system

Context Some milking parameters such as milk yield, milk flow, milking duration, milk conductivity and somatic-cell count can all be listed as economically important traits in dairy practice. Aims The aim of the study was to investigate the relationships among lactation stage, lactation number, milking season and milk-performance traits at an udder-quarter level, including somatic-cell count (SCC), milk yield (MY), milking duration (MD), time in box (TB), milk flow (MF) and milk conductivity (MC). An additional aim was to analyse milking-parameter levels in milkings with a SCC lower and higher than 400000 cells/mL. Methods The study included an analysis of 1621582 successful milkings obtained from six herds of dairy cattle equipped with milking robots (AMS). Key results The study confirmed that MD and MY differed greatly between front and rear quarters. Rear quarters took longer to be milked but produced more milk. During the first 100 days of lactation, the primiparous cows spent more time in the robot than did multiparous cows; however, in the second and third lactations, older cows were spending more time in the AMS. For primiparous cows, MF increased with time, being the highest at the end of lactation (>200 days in milk). A different trend has been found in the group of multiparous cows, where a steady decrease in MF was observed with subsequent lactation stages. A lower MC was recorded for cows in their first lactation than for multiparous cows. Data obtained from primiparous cows showed the highest MC to occur between 100 and 200 days of lactation. In the group of multiparous cows, MC increased with the lactation stage. It was also shown that the mean values obtained for MY, MD and TB were higher for cows with a lower SCC (<400000). Correlations between lnSCC (the natural logarithm of SCC) and MY and between lnSCC and MD were negative and low, while those between lnSCC and MC and lnSCC and MF were positive. Moderate correlations were found between lnSCC and total MC. Conclusions The study confirmed the differences in the performance of different udder quarters in relation to MY, MD, TB, MF, MS and SCC. Implications AMS provides farmers with vast data on milk and milking parameters. By monitoring changes in these parameters, farmer may be able to predict the level of production of their herd and the health of cows.

Evaluation of applying statistical process control techniques to daily average feeding behaviors to detect disease in automatically fed group-housed preweaned dairy calves

Group housing and computerized feeding of preweaned dairy calves are gaining in popularity among dairy producers, yet disease detection remains a challenge for this management system. The aim of this study was to investigate the application of statistical process control charting techniques to daily average feeding behavior to predict and detect illness and to describe the diagnostic test characteristics of using this technique to find a sick calf compared with detection by calf personnel. This prospective cross-sectional study was conducted on 10 farms in Minnesota (n = 4) and Virginia (n = 6) utilizing group housing and computerized feeding from February until October 2014. Calves were enrolled upon entrance to the group pen. Calf personnel recorded morbidity and mortality events. Farms were visited either every week (MN) or every other week (VA) to collect calf enrollment data, computer-derived feeding behavior data, and calf personnel-recorded calf morbidity and mortality. Standardized self-starting cumulative sum (CUSUM) charts were generated for each calf for each daily average feeding behavior, including drinking speed (mL/min), milk consumption (L/d), and visits to the feeder without a milk meal (no.). A testing subset of 352 calves (176 treated, 176 healthy) was first used to find CUSUM chart parameters that provided the highest diagnostic test sensitivity and best signal timing, which were then applied to all calves (n = 1,052). Generalized estimating equations were used to estimate the diagnostic test characteristics of a single negative mean CUSUM chart signal to detect a sick calf for a single feeding behavior. Combinations of feeding behavior signals were also explored. Single signals and combinations of signals that included drinking speed provided the most sensitive and timely signal, finding a sick calf up to an average (±SE) of 3.1 ± 8.8 d before calf personnel. However, there was no clear advantage to using CUSUM charting over calf observation for any one feeding behavior or combination of feeding behaviors when predictive values were considered. The results of this study suggest that, for the feeding behaviors monitored, the use of CUSUM control charts does not provide sufficient sensitivity or predictive values to detect a sick calf in a timely manner compared with calf personnel. This approach to examining daily average feeding behaviors cannot take the place of careful daily observation.

Early detection of clinical mastitis from electrical conductivity data in an automatic milking system

Mastitis adversely affects profit and animal welfare in the Australian dairy industry. Electrical conductivity (EC) is increasingly used to detect mastitis, but with variable results. The aim of the present study was to develop and evaluate a range of indexes and algorithms created from quarter-level EC data for the early detection of clinical mastitis at four different time windows (7 days, 14 days, 21 days, 27 days). Historical longitudinal data collected (4-week period) for 33 infected and 139 healthy quarters was used to compare the sensitivity (Se; target >80%), specificity (Sp; target >99%), accuracy (target >90%) and timing of ‘alert’ by three different approaches. These approaches involved the use of EC thresholds (range 7.5– 10 mS/cm), testing of over 250 indexes (created ad hoc), and a statistical process-control method. The indexes were developed by combining factors (and levels within each factor), such as conditional rolling average increase, percentage of variation, mean absolute deviation, mean error %; infected to non-infected ratio, all relative to the rolling average (3–9 data points) of either the affected quarter or the average of the four quarters. Using EC thresholds resulted in Se, Sp and accuracy ranging between 47% and 92%, 39% and 92% and 51% and 82% respectively (threshold 7.5 mS/cm performed best). The six highest performing indexes achieved Se, Sp and accuracy ranging between 68% and 84%, 60% and 85% and 56% and 81% respectively. The statistical process-control approach did not generate accurate predictions for early detection of clinical mastitis on the basis of EC data. Improved Sp was achieved when the time window before treatment was reduced regardless of the test approach. We concluded that EC alone cannot provide the accuracy required to detect infected quarters. Incorporating other information (e.g. milk yield, milk flow, number of incomplete milking) may increase accuracy of detection and ability to determine early onset of mastitis.

Episodes of clinical mastitis and its relationship with duration of treatment and seasonality in crossbred cows maintained in organized dairy farm

Aim:

Present study aimed to evaluate the different episodes of clinical mastitis (CM) and influence of duration of treatment and seasonality on the occurrence of different episodes of CM in crossbred cows.

Materials and Methods:

A total of 1194 lactation data of crossbred CM cows were collected from mastitis treatment record from 2002 to 2012. Data of CM cows were classified into types of episodes (pattern of repeated or multiple episodes occurrence) and number of episodes (magnitude of multiple cases). Types of episodes were divided as single (clinical cure by a single episode of treatment), relapse (retreatment of the same cow within 21 days), recurrence (new CM at least 21 days after treatment), and both (relapse and recurrence). The season was classified as winter (December to March), summer (April to June), rainy (July to September), and autumn (October to November). The difference between incidences of different types of CM episodes and the association between number or type of CM episodes with duration of treatment and seasons of CM occurrence were analyzed by Chi-square test.

Results:

Among 1194 animals suffered with CM, 53, 16, and 18% had the single episode, relapse, and recurrence, respectively; while 13% suffered by both relapse and recurrence. We estimated the duration of treatment and found 80% of the cows treated 1-8 days, in which 65% treated for 1-4 days, while 35% cows were treated for 5-8 days. Further, 12% cows treated for 9-15 days and 7.5% cows treated >15 days. The relationship between duration of treatment and different episodes of CM revealed that 1-8 days treated cows were mostly cured by the single episode with less relapse and recurrence. In contrast, the incidences of recurrence and relapse episodes were higher in cows treated for more than 9 days. The highest incidence of relapse was noticed in winter (36%) than other seasons (10-28%), while the recurrence was less during autumn (9%) compared to other seasons (20-40%).

Conclusion:

Cows those suffered by both relapse and recurrence were more susceptible to CM, and they need to be culled from farm to control the transmission of infections. Although the influence of seasonality was difficult to understand, the higher magnitude of relapse and recurrence during winter suggested the adverse effects of cold stress on treatment outcome.

Implementation of multivariate cumulative sum control charts in mastitis and lameness monitoring

This study analyzed the methodology and applicability of multivariate cumulative sum (MCUSUM) charts for early mastitis and lameness detection. Data used were recorded on the Karkendamm dairy research farm, Germany, between August 2008 and December 2010. Data of 328 and 315 cows in their first 200 d in milk were analyzed for mastitis and lameness detection, respectively. Mastitis as well as lameness was specified according to veterinary treatments. Both diseases were defined as disease blocks. Different disease definitions for mastitis and lameness (2 for mastitis and 3 for lameness) varied solely in the sequence length of the blocks. Only the days before the treatment were included in the disease blocks. Milk electrical conductivity, milk yield, and feeding patterns (feed intake, number of trough visits, and feeding time) were used for the recognition of mastitis. Pedometer activity and feeding patterns were used for lameness detection. To exclude biological trends and obtain independent observations, the values of each input variable were either preprocessed by wavelet filters or a multivariate vector autoregressive model. The residuals generated between the observed and filtered or observed and forecast values, respectively, were then transferred to a classic or self-starting MCUSUM chart. The combination of the 2 preprocessing methods with each of the 2 MCUSUM sum charts resulted in 4 combined monitoring systems. For mastitis as well as lameness detection requiring a block sensitivity of at least 70%, all 4 of the combined monitoring systems used revealed similar results within each of the disease definitions. Specificities of 73 to 80% and error rates of 99.6% were achieved for mastitis. The results for lameness showed that the definitions used obtained specificities of up to 81% and error rates of 99.1%. The results indicate that the monitoring systems with these study characteristics have appealing features for mastitis and lameness detection. However, they are not yet directly applicable for practical implementations.

Principal component analysis for the early detection of mastitis and lameness in dairy cows

This investigation analysed the applicability of principal component analysis (PCA), a latent variable method, for the early detection of mastitis and lameness. Data used were recorded on the Karkendamm dairy research farm between August 2008 and December 2010. For mastitis and lameness detection, data of 338 and 315 cows in their first 200 d in milk were analysed, respectively. Mastitis as well as lameness were specified according to veterinary treatments. Diseases were defined as disease blocks. The different definitions used (two for mastitis, three for lameness) varied solely in the sequence length of the blocks. Only the days before the treatment were included in the blocks. Milk electrical conductivity, milk yield and feeding patterns (feed intake, number of feeding visits and time at the trough) were used for recognition of mastitis. Pedometer activity and feeding patterns were utilised for lameness detection. To develop and verify the PCA model, the mastitis and the lameness datasets were divided into training and test datasets. PCA extracted uncorrelated principle components (PC) by linear transformations of the raw data so that the first few PCs captured most of the variations in the original dataset. For process monitoring and disease detection, these resulting PCs were applied to the Hotelling's T2 chart and to the residual control chart. The results show that block sensitivity of mastitis detection ranged from 77·4 to 83·3%, whilst specificity was around 76·7%. The error rates were around 98·9%. For lameness detection, the block sensitivity ranged from 73·8 to 87·8% while the obtained specificities were between 54·8 and 61·9%. The error rates varied from 87·8 to 89·2%. In conclusion, PCA seems to be not yet transferable into practical usage. Results could probably be improved if different traits and more informative sensor data are included in the analysis.

Invited review: sensors to support health management on dairy farms

Since the 1980s, efforts have been made to develop sensors that measure a parameter from an individual cow. The development started with individual cow recognition and was followed by sensors that measure the electrical conductivity of milk and pedometers that measure activity. The aim of this review is to provide a structured overview of the published sensor systems for dairy health management. The development of sensor systems can be described by the following 4 levels: (I) techniques that measure something about the cow (e.g., activity); (II) interpretations that summarize changes in the sensor data (e.g., increase in activity) to produce information about the cow's status (e.g., estrus); (III) integration of information where sensor information is supplemented with other information (e.g., economic information) to produce advice (e.g., whether to inseminate a cow or not); and (IV) the farmer makes a decision or the sensor system makes the decision autonomously (e.g., the inseminator is called). This review has structured a total of 126 publications describing 139 sensor systems and compared them based on the 4 levels. The publications were published in the Thomson Reuters (formerly ISI) Web of Science database from January 2002 until June 2012 or in the proceedings of 3 conferences on precision (dairy) farming in 2009, 2010, and 2011. Most studies concerned the detection of mastitis (25%), fertility (33%), and locomotion problems (30%), with fewer studies (16%) related to the detection of metabolic problems. Many studies presented sensor systems at levels I and II, but none did so at levels III and IV. Most of the work for mastitis (92%) and fertility (75%) is done at level II. For locomotion (53%) and metabolism (69%), more than half of the work is done at level I. The performance of sensor systems varies based on the choice of gold standards, algorithms, and test sizes (number of farms and cows). Studies on sensor systems for mastitis and estrus have shown that sensor systems are brought to a higher level; however, the need to improve detection performance still exists. Studies on sensor systems for locomotion problems have shown that the search continues for the most appropriate indicators, sensor techniques, and gold standards. Studies on metabolic problems show that it is still unclear which indicator reflects best the metabolic problems that should be detected. No systems with integrated decision support models have been found.

Test-day somatic cell score, fat-to-protein ratio and milk yield as indicator traits for sub-clinical mastitis in dairy cattle

Test-day (TD) records of milk, fat-to-protein ratio (F:P) and somatic cell score (SCS) of first-lactation Canadian Holstein cows were analysed by a three-trait finite mixture random regression model, with the purpose of revealing hidden structures in the data owing to putative, sub-clinical mastitis. Different distributions of the data were allowed in 30 intervals of days in milk (DIM), covering the lactation from 5 to 305 days. Bayesian analysis with Gibbs sampling was used for model inferences. Estimated proportion of TD records originated from cows infected with mastitis was 0.66 in DIM from 5 to 15 and averaged 0.2 in the remaining part of lactation. Data from healthy and mastitic cows exhibited markedly different distributions, with respect to both average value and the variance, across all parts of lactation. Heterogeneity of distributions for infected cows was also apparent in different DIM intervals. Cows with mastitis were characterized by smaller milk yield (down to -5 kg) and larger F:P (up to 0.13) and SCS (up to 1.3) compared with healthy contemporaries. Differences in averages between healthy and infected cows for F:P were the most profound at the beginning of lactation, when a dairy cow suffers the strongest energy deficit and is therefore more prone to mammary infection. Residual variances for data from infected cows were substantially larger than for the other mixture components. Fat-to-protein ratio had a significant genetic component, with estimates of heritability that were larger or comparable with milk yield, and was not strongly correlated with milk and SCS on both genetic and environmental scales. Daily milk, F:P and SCS are easily available from milk-recording data for most breeding schemes in dairy cattle. Fat-to-protein ratio can potentially be a valuable addition to SCS and milk yield as an indicator trait for selection against mastitis.

Application of statistical process control charts to monitor changes in animal production systems

Statistical process control (SPC) is a method of monitoring, controlling, and improving a process through statistical analysis. An important SPC tool is the control chart, which can be used to detect changes in production processes, including animal production systems, with a statistical level of confidence. This paper introduces the philosophy and types of control charts, design and performance issues, and provides a review of control chart applications in animal production systems found in the literature from 1977 to 2009. Primarily Shewhart and cumulative sum control charts have been described in animal production systems, with examples found in poultry, swine, dairy, and beef production systems. Examples include monitoring of growth, disease incidence, water intake, milk production, and reproductive performance. Most applications describe charting outcome variables, but more examples of control charts applied to input variables are needed, such as compliance to protocols, feeding practice, diet composition, and environmental factors. Common challenges for applications in animal production systems are the identification of the best statistical model for the common cause variability, grouping of data, selection of type of control chart, the cost of false alarms and lack of signals, and difficulty identifying the special causes when a change is signaled. Nevertheless, carefully constructed control charts are powerful methods to monitor animal production systems. Control charts might also supplement randomized controlled trials.