Efficient lameness detection is crucial in maintaining health, welfare and productivity of dairy cattle. This study evaluated a fully automated 2-dimensional imaging system employing machine learning to provide real-time mobility score predictions. The system was tested on eleven commercial farms, showing a performance comparable to that of experienced human assessors in detecting lame cows and cows with foot lesions. When using daily mobility scores generated over 30 days before trimming, the system¡¯s accuracy was improved and outperformed the human assessor. This advanced technological application offers potential for early detection of lame cows and effective management of lameness in dairy herds.
