The Combined Use of Automated Milking System and Sensor Data to Improve Detection of Mild Lameness in Dairy Cattle
Lena Lemmens,
Katharina Schodl,
Birgit Fuerst-Waltl,
Hermann Schwarzenbacher,
Christa Egger-Danner,
Kristina Linke,
Marlene Suntinger,
Mary Phelan,
Martin Mayerhofer,
Franz Steininger,
Franz Papst,
Lorenz Maurer,
Johann Kofler
Affiliations
Lena Lemmens
Department of Farm Animals and Veterinary Public Health, University Clinic for Ruminants, University of Veterinary Medicine Vienna, 1210 Vienna, Austria
Katharina Schodl
Department of Sustainable Agricultural Systems, Institute of Livestock Sciences, University of Natural Resources and Life Sciences Vienna, 1180 Vienna, Austria
Birgit Fuerst-Waltl
Department of Sustainable Agricultural Systems, Institute of Livestock Sciences, University of Natural Resources and Life Sciences Vienna, 1180 Vienna, Austria
Hermann Schwarzenbacher
ZuchtData EDV-Dienstleistungen GmbH, 1200 Vienna, Austria
Christa Egger-Danner
ZuchtData EDV-Dienstleistungen GmbH, 1200 Vienna, Austria
Kristina Linke
ZuchtData EDV-Dienstleistungen GmbH, 1200 Vienna, Austria
Marlene Suntinger
ZuchtData EDV-Dienstleistungen GmbH, 1200 Vienna, Austria
Mary Phelan
MSD Animal Health, D18X5K7 Dublin, Ireland
Martin Mayerhofer
ZuchtData EDV-Dienstleistungen GmbH, 1200 Vienna, Austria
Franz Steininger
ZuchtData EDV-Dienstleistungen GmbH, 1200 Vienna, Austria
Franz Papst
Institute of Technical Informatics, Graz University of Technology, 8010 Graz, Austria
Lorenz Maurer
Department of Sustainable Agricultural Systems, Institute of Livestock Sciences, University of Natural Resources and Life Sciences Vienna, 1180 Vienna, Austria
Johann Kofler
Department of Farm Animals and Veterinary Public Health, University Clinic for Ruminants, University of Veterinary Medicine Vienna, 1210 Vienna, Austria
This study aimed to develop a tool to detect mildly lame cows by combining already existing data from sensors, AMSs, and routinely recorded animal and farm data. For this purpose, ten dairy farms were visited every 30–42 days from January 2020 to May 2021. Locomotion scores (LCS, from one for nonlame to five for severely lame) and body condition scores (BCS) were assessed at each visit, resulting in a total of 594 recorded animals. A questionnaire about farm management and husbandry was completed for the inclusion of potential risk factors. A lameness incidence risk (LCS ≥ 2) was calculated and varied widely between farms with a range from 27.07 to 65.52%. Moreover, the impact of lameness on the derived sensor parameters was inspected and showed no significant impact of lameness on total rumination time. Behavioral patterns for eating, low activity, and medium activity differed significantly in lame cows compared to nonlame cows. Finally, random forest models for lameness detection were fit by including different combinations of influencing variables. The results of these models were compared according to accuracy, sensitivity, and specificity. The best performing model achieved an accuracy of 0.75 with a sensitivity of 0.72 and specificity of 0.78. These approaches with routinely available data and sensor data can deliver promising results for early lameness detection in dairy cattle. While experimental automated lameness detection systems have achieved improved predictive results, the benefit of this presented approach is that it uses results from existing, routinely recorded, and therefore widely available data.