Estimating risk probabilities for sickness from behavioural patterns to identify health challenges in dairy cows with multivariate cumulative sum control charts

Classically, the diagnosis of respiratory disease in cattle has been based on observation of clinical signs and the behavior of the animals, but this technique can be subjective, time-consuming and labor intensive. It also requires proper training of staff and lacks sensitivity (Se) and specificity (Sp). Furthermore, respiratory disease is diagnosed too late, when the animal already has severe lesions. A total of 104 papers were included in this review. The use of new advanced technologies that allow early diagnosis of diseases using real-time data analysis may be the future of cattle farms. These technologies allow continuous, remote, and objective assessment of animal behavior and diagnosis of bovine respiratory disease with improved Se and Sp. The most commonly used behavioral variables are eating behavior and physical activity. Diagnosis of bovine respiratory disease may experience a significant change with the help of big data combined with machine learning, and may even integrate metabolomics as disease markers. Advanced technologies should not be a substitute for practitioners, farmers or technicians, but could help achieve a much more accurate and earlier diagnosis of respiratory disease and, therefore, reduce the use of antibiotics, increase animal welfare and sustainability of livestock farms. This review aims to familiarize practitioners and farmers with the advantages and disadvantages of the advanced technological diagnostic tools for bovine respiratory disease and introduce recent clinical applications.

Section: Resultsmentioning

confidence: 99%

Technological Tools for the Early Detection of Bovine Respiratory Disease in Farms

Puig

Ruiz²,

Bassols³

et al. 2022

“…Making use of the IoT enables monitoring certain parameters or health symptoms such as udder health, estrus events, feet and leg health, temperature, humidity, heart rate, rumination rate, and metabolic health [33,34]. Some non-invasive approaches [35] and technologies, such as visible video (VisV) and infrared thermal imagery (IRTI) [18], together with ML methods are aimed at animal health monitoring [14], identifying individual sick animals by observing eating and drinking behavior [36,37], temperature analysis of cold and heat stress [38,39], and video-based individual cow identification [40,41].…”

Section: Discussionmentioning

confidence: 99%

Health Status Classification for Cows Using Machine Learning and Data Management on AWS Cloud

Dineva,

Atanasova

2023

The health and welfare of livestock are significant for ensuring the sustainability and profitability of the agricultural industry. Addressing efficient ways to monitor and report the health status of individual cows is critical to prevent outbreaks and maintain herd productivity. The purpose of the study is to develop a machine learning (ML) model to classify the health status of milk cows into three categories. In this research, data are collected from existing non-invasive IoT devices and tools in a dairy farm, monitoring the micro- and macroenvironment of the cow in combination with particular information on age, days in milk, lactation, and more. A workflow of various data-processing methods is systematized and presented to create a complete, efficient, and reusable roadmap for data processing, modeling, and real-world integration. Following the proposed workflow, the data were treated, and five different ML algorithms were trained and tested to select the most descriptive one to monitor the health status of individual cows. The highest result for health status assessment is obtained by random forest classifier (RFC) with an accuracy of 0.959, recall of 0.954, and precision of 0.97. To increase the security, speed, and reliability of the work process, a cloud architecture of services is presented to integrate the trained model as an additional functionality in the Amazon Web Services (AWS) environment. The classification results of the ML model are visualized in a newly created interface in the client application.

“…Although the day-to-day routines and life of dairy and beef cattle differ greatly, there are common behavioral measures that may be useful in the diagnosis of disease in both types of animals. Physical activity (distance traveled or steps taken/lying time), feeding and watering behaviors, and social behaviors have all been suggested as potential indicators of cattle health status in both dairy and beef cattle [8][9][10][11][12][13][14][15][16][17][18]. Furthermore, these behavioral variables have been directly linked to predicting BRD [8,9,11,[19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Determination of Behavioral Changes Associated with Bovine Respiratory Disease in Australian Feedlots

White,

Goehl,

McMeniman

et al. 2023

Accurately identifying bovine respiratory disease is challenging in feedlots, and previous studies suggest behavioral monitoring is important. The study objective was to describe individual differences in physical activity (distance traveled), feeding/watering patterns (proximity to feed and water), and social behavior (average cattle within 3 m) when associated with health status in commercially raised beef cattle during the first 28 days on feed. Data from a previous Australian feedlot study monitoring cattle behavior and associated health outcomes were analyzed. Health status categories were generated for all cattle, and each animal was categorized as known healthy (HLTH), known diseased (SICK), or intermediate/uncertain (INTR). The INTR animals were excluded from the final analysis. Key findings included: differentiation in activity between SICK (n = 138) and HLTH (n = 1508) cattle dependent on time of day, SICK cattle spending more time in water and feeding zones early in the feeding phase (<6 days on feed), SICK cattle spending more time in the water and feeding zone during the overnight hours, and SICK cattle spending more time in groups early in the feeding phase but more time in isolation after the first week on feed. Results illustrate behavioral data were associated with important health outcomes.