Machine learning to fight antibiotic resistance in farmed chickens
A new research project aims to improve the health of farmed chickens in China and reduce the risk of disease and antibiotic resistance transferring to human populations.
The FARMWATCH project will use machine learning to find new ways to identify and pinpoint disease in poultry farms, reducing the need for antibiotic treatment and lowering the risk of antibiotic resistance transferring to consumers.
The £1.5m project is a partnership between researchers from the University of Nottingham’s School of Veterinary Medicine and Science and the China National Center for Food Safety Risk Assessment. Funded by Innovate UK and the Chinese Ministry of Science and Technology (MoST), the researchers are also collaborating with commercial partners, Nimrod Veterinary Products in the UK and New Hope Liuhe in China.
The researchers in Nottingham will be working with colleagues in China to take thousands of samples from the animals, humans and environment of nine farms, in three Chinese provinces over three years. This complex ‘big’ data will be analysed for new diagnostic biomarkers that will predict and detect bacterial infection, insurgence of antibiotic resistance, and transfer to humans. This data will then allow early intervention and treatment, reducing spread and the need for antibiotics.
Dr Tania Dottorini, Assistant Professor in Bioinformatics at the University of Nottingham, said, “This is a hugely important project that has the potential to transform the ways farm animals are treated and looked after. It also has significant impact on the heath of consumers of poultry products, with future ramifications to other farmed animals. For the first time we are using large-scale collection of data, statistical modelling and data mining powered by machine learning and cloud computing to find answers to some big problems faced by the farming industry. This project will contribute to sustainable development in China through improved health and well-being of vulnerable populations. We can then apply these learnings to the UK as well.”
[SOURCE: University of Nottingham]