It seems as if we hear something new about artificial intelligence (AI) almost daily. It is the hot topic of 2023 – in fact on the day I write this it has been confirmed that AI is Collins Dictionary's word of the year (BBC News, 2023)! So, it seems very apt that we have an article in this month's edition of Livestock on The future of AI for livestock veterinary practice (p254). In it, Robert Hyde and Charles Carslake discuss how AI could transform farm animal veterinary practice.
Technological advances are particularly interesting for the common diseases impacting livestock. Mastitis is one of the most economically important diseases of dairy cows across the industry, and of course it can have a big impact on animal welfare as well as profitability.
Data can play a big role in the prevention and detection of mastitis and has done for some time. However, this often looks at symptoms associated with the later stages of the disease. AI is now being trialled for the automatic diagnosis of early-stage dairy cow mastitis. If veterinarians can reliably detect mastitis at an early stage using automatic methods, big gains could be made in the reduction of antibiotic use and improvements in herd welfare.
Infrared thermography – the use of temperature measurement from a distance – has been shown to successfully detect early mastitis, but some suggest this is time consuming and requires a skilled examiner (Silva et al, 2021).
Sensors on automatic milking systems have also shown potential – these can measure electrical conductivity, the number of immune cells, and activity of enzymes in the milk. Farmers can then be alerted to cases of mastitis.
A recent study by researchers in China used an automatic detection method for dairy cow mastitis, using the fusion of udder temperature and size features based on deep learning (Chu et al, 2023). This showed promise for early diagnosis of mastitis.
Researchers at the University of Bristol have received funding to study how AI could be used in order to monitor social interactions of cattle, which could indicate developing mastitis or lameness. The research team have developed AI that can track the motion of cows, recognising each cow by its distinctive coat pattern, and alert farmers and veterinarians to changes in social exploration, grooming of others and receiving headbutts – all of which are indicators of early stage disease (Caplan and Held, 2021).
This is a rapidly developing area, and I look forward to seeing how this technology advances to improve welfare of animals on farm.