The application of machine learning to predict and prevent disease from the transition period of dairy cattle

Background:
The transition period (the time around each calving event) is a critical time for dairy cattle, and management factors at this time can have major impacts on future cow health and productivity. This is largely due to the significant physiological and hormonal changes during this period in order to meet the demands of lactation. The transition period therefore contributes to a large extent to health problems, the majority of which occur in early lactation. Careful management of cows during the transition period can minimize the likelihood of peri-parturient disease (digestive, metabolic and infectious). Identification and prediction of peri-parturient disease in high risk individuals or groups can be used to optimise prevention strategies resulting in the improved health, welfare and productivity of dairy cows during this time.

Project description:
The aim of this project is to utilise a unique dataset of cow- and farm-level data to make biological predictions and develop tools with the overall objective of supporting decision making and disease prevention in the transition period. Through collaboration with Premier Nutrition (part of the AB Agri group), anonymized data from approximately 150 dairy herds over a 12-month period will be made available for analysis. This project will focus on exploring which transition period cow- and farm-level factors are predictive of various health and production outcomes in the subsequent lactation. A variety of analytical approaches will be used, encompassing advanced statistical techniques and machine learning methods. By highlighting herd-level risk factors and developing methods for predicting disease risk at individual cow level, research will provide substantial benefits in terms of relevance to other herds and has the potential for substantial impact in the UK and beyond.



The successful applicant will develop skills in epidemiological and statistical techniques with a focus on the application of machine learning to data analysis. The student will be joining a dynamic and forward-thinking group of academic researchers within the Ruminant Population Health group at the University of Nottingham School of Veterinary Medicine and Science.
Research is central to the activities of the School of Veterinary Medicine and Science. In the 2014 Research Excellence Framework assessment, 97% of work submitted by the Schools of Veterinary Medicine and Science and Biosciences was judged to be of international quality, and 37% of work as world-leading (4-star). Research environment was ranked top of all institutions within our Unit of Assessment (Agriculture, Veterinary and Food Science).

Further information and Application
Applicants should have a first or 2.1 undergraduate degree (or a minimum of a 2.2 degree in addition to a Masters degree) in Animal Science, Veterinary Science, Applied Statistics, Veterinary Epidemiology or similar subjects, and should have a strong interest in quantitative analysis and epidemiology.
Informal enquiries may be addressed to [Email Address Removed]
Candidates should apply online at http://www.nottingham.ac.uk/pgstudy/apply/apply-online.aspx and include a CV. For any queries regarding the application process, please email: [Email Address Removed]

Start Date:
The expected start date is 1st October 2018. This is a 3-year studentship funded by Premier Nutrition and the School of Veterinary Medicine and Science, University of Nottingham.