Mastitis remains one of the most costly and significant endemic diseases affecting dairy cattle, with impacts including reduced production, environmental sustainability, and animal welfare and increased antimicrobial use. The success of the AHDB national mastitis control programme (NMCP) has reduced the incidence of mastitis. One of the key drivers to success was the use of the Mastitis Pattern Analysis Tool (MPAT). Whilst the current version of the MPAT performed reasonably well in comparison to expert diagnosis, it is clear the performance and user engagement could be substantially improved. Improvements to the MAPT were based on the application of novel machine learning methods to predict the probability of belonging to a range of different epidemiological diagnoses of mastitis. This research project aimed to re-invigorate and enhance the use of the MPAT with in the NMCP by via establishing an automated data transfer pipeline between major milk recording organisations (QMMS, CIS and NMR) and a cloud-based analysis platform (REMEDY). Via this platform, automated analysis of mastitis epidemiological patterns is available to all milk recording farmers via a one-time sign-up process and the newly enhanced MPAT reports have been evaluated by farm animal veterinarians and incorporated into AHDB’s QuaterPRO mastitis control programme. 

Contact details:

Dr Luke O’Grady 

Senior Research Fellow

School of Veterinary Medicine and Science

University of Nottingham