CSH researcher Caspar Matzhold will present an online talk within the seminar “Analysis of Complex Systems” on June 04, 2021, 3–4 pm (CET) via Zoom.
If you would like to attend, please email office@csh.ac.at
Abstract:
Digitisation in dairy cattle farming holds the promise of substantially improving early detection and prevention of animal disease, in particular through the collection, linkage, and analysis of routine data generated by milking, feeding, and performance recording systems.
However, the detection of disease risk factors on the basis of such data is complicated by the heterogeneity of the data itself and, above all, by the fact that diseases are often caused by a combination of several factors, rather than individual factors. Here, we present a systematic approach to integrate machine learning techniques with statistical analysis in order to analyse disease risks in relation to a comprehensive collection of cow-, farm-related and environmental parameters and interrelations thereof.
The data used in this analysis includes 166 farms with a total of 5,828 dairy cows. Each farm is characterised by features from five categories: husbandry, feeding, environmental conditions, housing, and milking systems. We combine dimension reduction with clustering techniques to identify groups of similar farm attributes, which we refer to as farm profiles. A statistical analysis of the farm profiles and their related disease risks is carried out to study the associations between disease risk, farm membership to a specific cluster as well as variables that characterise a given cluster by means of a multivariate regression model.
The disease risks of five different farm profiles arise as the result of complex interactions between environmental conditions and farm management practices. We confirm associations between diseases and feeding and husbandry, respectively, as reported by the literature. In addition, our analysis reveals new relationships between housing and milking systems and specific diseases, such as lameness and ketosis. Our approach contributes to paving a way towards a more holistic and data-driven understanding of bovine health and its risk factors.