About the Project
This PhD combines veterinary epidemiology, data science and artificial intelligence. It aims to develop innovative methods to extract symptoms and disease from electronic health clinical records and online equine communities/forums. The research will explore early warning systems for endemic and emerging infectious diseases, contributing to modern surveillance tools for equine health and disease outbreak preparedness.
About this opportunity
Infectious diseases remain a major challenge for equine health and welfare worldwide. Endemic diseases such as strangles, equine influenza, equine herpesvirus (EHV), and infectious gastrointestinal diseases can have significant impacts on horse populations, while emerging threats such as West Nile virus highlight the need for effective surveillance systems capable of identifying novel disease events rapidly. Early detection is critical for limiting disease spread, improving clinical outcomes, and supporting evidence-based disease control strategies.
Current surveillance approaches rely heavily on laboratory confirmation and structured clinical reporting, which can delay the recognition of emerging outbreaks. However, large volumes of valuable information are routinely recorded as unstructured free-text clinical notes within veterinary practice management systems. Similarly, horse owners frequently discuss clinical signs and health concerns on online forums before formal veterinary diagnoses are made. Advances in artificial intelligence (AI) and natural language processing (NLP) provide an opportunity to harness these previously underutilised data sources for disease surveillance.
The University of Liverpool’s Equine Veterinary Surveillance Network (EVSNET) provides access to a unique network of equine clinical data from veterinary practices across the UK. Building on the recently developed language model, this project will explore how modern NLP approaches can enhance equine disease surveillance by extracting clinically meaningful information from free-text records and informal online discussions.
Project Overview
This PhD project aims to develop innovative AI-driven methods for the early detection of equine infectious diseases through the analysis of unstructured textual data. The research will focus on advancing specialised language models trained on equine veterinary records and evaluating its application in syndromic surveillance.
The project will first develop and validate disease classifiers capable of identifying infectious disease syndromes from veterinary clinical narratives. Emphasis will be placed on syndromes associated with respiratory, neurological, gastrointestinal, reproductive, and pyrexic presentations that may indicate conditions such as equine influenza, strangles, equine herpesvirus infection, salmonellosis, clostridial disease, and emerging threats including West Nile virus. Model performance will be assessed using expert-annotated datasets and benchmarked against gold-standard classifications.
Building on these outputs, the project will investigate methods for syndromic surveillance and outbreak detection. Statistical and spatial approaches will be used to monitor trends in clinical syndromes, identify unusual disease activity, and evaluate the capacity of the models to detect emerging threats through simulated outbreak scenarios. Geographic visualisation techniques will be employed to explore spatial patterns of disease occurrence and support surveillance decision-making.
A further component of the project will examine the feasibility of web-based disease surveillance. NLP methods will be applied to publicly available equine owner forums and other online textual sources to determine whether informal discussions can provide earlier indications of disease activity than traditional surveillance systems.
Finally, the project will work closely with veterinary stakeholders to develop practical visualisation and reporting tools that translate model outputs into actionable surveillance insights. Opportunities also exist to collaborate with international partners, including Colorado State University, to evaluate the developed methods across different veterinary populations and disease contexts.
Relevance
This project sits at the intersection of veterinary epidemiology, artificial intelligence, and data science. By developing novel methods for extracting disease information from unstructured text, the research will contribute to modern surveillance systems. The outputs will support veterinarians and researchers in protecting equine health while advancing the application of AI within veterinary medicine.
Location
The student will be based full-time at the Leahurst Campus, University of Liverpool. They will join a multidisciplinary team of veterinary surgeons, epidemiologists, data scientists, computer scientists, parasitologists, and microbiologists, known for its collaborative and supportive research environment.
Applicant Requirements
Funding is only available for UK citizens or those with UK settled or other status which makes them eligible for UK student home fees. Ideal for a veterinary or science graduate with a strong interest in data science, quantitative epidemiology and/or computer science. An honours degree (or expected degree) in an appropriate subject (e.g., veterinary science, computer science, data science or a related field) is required; a relevant MSc/MRes is desirable.
Training
The student will receive comprehensive training in research methods, including data handling, advanced statistics (using R), natural language processing, and machine learning (using Python). Training will be delivered through formal postgraduate modules and close supervision by a highly experienced interdisciplinary team. In addition, the student will be able to access Master’s-level training through the University of Liverpool’s MSc programmes e.g., Data Science and AI for Health Innovation, equipping them with cutting-edge skills in AI, health informatics, and data-driven research.
To apply, please send a CV and cover letter to april.lawson@liverpool.ac.uk
For application enquiries, please contact Dr April Lawson, april.lawson@liverpool.ac.uk
This is a Preview Listing…
You must sign in to see the full job description, and to apply.
Manage / Upgrade this job to a Full Job Listing.
Find Your Best Opportunity
Tell them AcademicJobs.com sent you!
