Lameness detection in dairy cattle: single predictor v. multivariate analysis of image-based posture processing and behaviour and performance sensing

Abstract

The objective of this study was to evaluate if a multi-sensor system (milk, activity, body posture) was a better classifier for lameness than the single-sensor-based detection models. Between September 2013 and August 2014, 3629 cow observations were collected on a commercial dairy farm in Belgium. Human locomotion scoring was used as reference for the model development and evaluation. Cow behaviour and performance was measured with existing sensors that were already present at the farm. A prototype of three-dimensional-based video recording system was used to quantify automatically the back posture of a cow. For the single predictor comparisons, a receiver operating characteristics curve was made. For the multivariate detection models, logistic regression and generalized linear mixed models (GLMM) were developed. The best lameness classification model was obtained by the multi-sensor analysis (area under the receiver operating characteristics curve (AUC) = 0.757 ± 0.029), containing a combination of milk and milking variables, activity and gait and posture variables from videos. Second, the multivariate videobased system (AUC = 0.732 ± 0.011) performed better than the multivariate milk sensors (AUC = 0.604 ± 0.026) and the multivariate behaviour sensors (AUC = 0.633 ± 0.018). The video-based system performed better than the combined behaviour and performance-based detection model (AUC = 0.669 ± 0.028), indicating that it is worthwhile to consider a video-based lameness detection system, regardless the presence of other existing sensors in the farm. The results suggest that Θ 2 , the feature variable for the back curvature around the hip joints, with an AUC of 0.719 is the best single predictor variable for lameness detection based on locomotion scoring. In general, this study showed that the video-based back posture monitoring system is outperforming the behaviour and performance sensing techniques for locomotion scoring-based lameness detection. A GLMM with seven specific variables (walking speed, back posture measurement, daytime activity, milk yield, lactation stage, milk peak flow rate and milk peak conductivity) is the best combination of variables for lameness classification. The accuracy on four-level lameness classification was 60.3%. The accuracy improved to 79.8% for binary lameness classification. The binary GLMM obtained a sensitivity of 68.5% and a specificity of 87.6%, which both exceed the sensitivity (52.1% ± 4.7%) and specificity (83.2% ± 2.3%) of the multi-sensor logistic regression model. This shows that the repeated measures analysis in the GLMM, taking into account the individual history of the animal, outperforms the classification when thresholds based on herd level (a statistical population) are used.

A Review of Welfare Indicators of Indoor-Housed Dairy Cow as a Basis for Integrated Automatic Welfare Assessment Systems

“…A further opportunity to improve the detection accuracy of an integrated automatic assessment system would be to integrate not only sensor data, but also non-sensor information, such as herd data [26,105]. For instance, information on days in milk, parity and previous incidence of a specific welfare issue could all be helpful to identify individuals that would be more at risk to suffer from certain welfare issues (e.g., [17,18]).…”

“…For instance, in the assessment of heat stress both environment-based indicators, such as ambient temperature, and animal-based indicators, such as respiratory rate, could be measured (e.g., [15,16]). While studies often focus on testing the performance of one automatic detection method, several studies have found that integrating data from different detection methods improves the detection performance (e.g., [17,18]; reviewed by [19]) and commercial systems that integrate several parameters, such as RumiWatch (Itin + Hoch GmbH, Liestal, Switzerland [20]) and Cow Manager SensOor (Agis Automatisering BV, Harmelen, the Netherlands [21]), have been suggested to outperform systems with less or one parameter [22,23]. However, there is still a need to integrate data from many systems to into one system that would be able to make an overall assessment of the welfare of an animal (e.g., [24,25]).…”

Individual dairy cow management: achievements, obstacles and prospects

“…One that is based on physical variables and gait movements detected lameness and even the limb that causes it (Rajkondawar et al ., 2006; Liu et al ., 2009). Another lameness detection sensor based on the posture and back curvature of walking cows (Van Hertem et al ., 2016, 2018) indicated lameness before its visual appearance. Both products were put on the market, but did not meet expectations and are not yet widely used.…”

A Feasibility Study on the Use of a Structured Light Depth-Camera for Three-Dimensional Body Measurements of Dairy Cows in Free-Stall Barns

“…Frequent monitoring of animals’ body condition in quantitative terms is helpful in order to allow for early recognition of health anomalies and consequently decrease the amount of complications related to infertility, lameness, or other animal diseases [ 1 , 2 , 3 , 4 ]. With reference to young calves, the first months of life are critical, since animals’ growth may be affected by the appearance of several diseases or other stress factors, such as dehorning [ 5 ].…”