Publication
Citations
H-index

Hi! đź‘‹

My name is Sean

I'm a PhD student in Natural Language Processing (NLP) at Durham University specialising in AI for public health research.


Natural Language Processing

Expert in transformer models, Retrieval Augmented Generation (RAG) systems, topic modelling, explainability, and multi-modal architectures using PyTorch and Huggingface. Specialised in low-resource training and domain adaptation.

Transformers RAG Explainability Multi-modal PyTorch Huggingface

Data Analysis and Statistical Modelling

Proficient in Python, R, SQL. Experienced in scalable pipeline design for low-resource environments, analysing datasets of 16M+ records, Git-based version control, and advanced statistical modeling.

Python R SQL Data Pipelines Big Data Git Statistical Modelling

Data Visualisation

Adept at creating clear, informative, and publication-quality visualisations. Skilled in website creation for serving models and presenting visualisations interactively.

Matplotlib Seaborn ggplot2 Plotly Dashboard Design

Teaching and Mentoring

Experienced in teaching NLP to master's-level students, adapting methods for varied skill levels. Mentoring a master’s student on an epidemiology-based project. Awarded with Associate Fellowship in Higher Education.

AFHEA Mentoring NLP Education Curriculum Design Student Engagement

Communication and Presentations

Experienced in delivering technical presentations to limited prior knowledge audiences. Capable of tailoring complex concepts to both expert and lay audiences, ensuring clarity and engagement. Won several best talk awards.

Public Speaking Science Communication Audience Engagement

Ethical and Scientific Writing

Published in peer-reviewed journals, skilled at structuring clear and concise papers, emphasising reproducibility and scientific rigor. Experience in writing ethics proposals.

Scientific Writing Ethics Proposals Reproducibility Research Integrity

Education

PhD Computer Science (Natural Language Processing)

October 2021 – October 2025

Durham University

Funded by the Biotechnology and Biological Sciences Research Council (BBSRC) to explore Natural Language Processing and deep learning methods for analysing over 16 million first-opinion veterinary electronic health records (EHRs) across the UK. The research addresses critical public health challenges by applying computational innovation to real-world data.

  • PetBERT: Developed a domain-specific foundation LLM for veterinary medicine trained on millions of clinical free-text records.
  • Public Health Research: Led studies on disease outbreak detection, socioeconomic inequalities in premature mortality, and antimicrobial usage trends aligned with national stewardship guidelines.
  • PetEVAL Benchmark: Created the first open benchmark dataset for veterinary free-text EHRs, promoting reproducibility in the field.
  • Multimodal & Explainable AI: Integrated structured data and unstructured text with explainable AI methods for transparency in model decisions.
  • EU ENOVAT Collaboration: Coordinated a multinational study on barriers to antimicrobial stewardship guideline adoption across Europe.
  • PetHarbor: Leading global initiatives defining protocols for anonymisation, sharing, and responsible use of veterinary free-text EHRs.

Thesis: Natural Language Processing for Early Detection and Mitigation of Critical Public Health Threats

Impact: Bridging computational innovation with real-world public health applications, advocating open science and standardised data sharing within veterinary research.

2:1 BSc (Hons) Biomedical Sciences

October 2018 – July 2021

University of Kent

Developed interdisciplinary expertise across biology and healthcare to address complex public health challenges. Experienced in laboratory methods spanning Genetics, Microbiology, Biochemistry, and Immunology.

Thesis: Antimicrobial Usage in Hospitalised SARS-CoV-2 Patients and Its Impact on the Gut Microbiome

Publications

First Authorships

Title Authors Venue Date Link Download
PetEVAL: A veterinary free text electronic health records benchmark. Farrell, S., Radford, A.D., Al Moubayed, N., Noble, P.-J.M. Proceedings of the 24th Workshop on Biomedical Language Processing 01/08/2025 Link pdf
Premature mortality analysis of 52,000 deceased cats and dogs exposes socioeconomic disparities. Farrell, S., Anderson, K., Noble, P.-J.M. and Al Moubayed, N. Scientific Reports 20/09/2024 Link pdf
Explainable text-tabular models for predicting mortality risk in companion animals. Farrell, S.*, Burton, J.*, Noble, P.-J.M. and Al Moubayed, N. Scientific Reports 20/06/2024 Link pdf
PetBERT: automated ICD-11 syndromic disease coding for outbreak detection in first opinion veterinary electronic health records. Farrell, S., Appleton, C., Noble, P.-J.M. and Al Moubayed, N. Scientific Reports 21/10/2023 Link pdf
A multinational survey of companion animal veterinary clinicians: How can antimicrobial stewardship guidelines be optimised for the target stakeholder? Farrell, S., Bagcigil, A.F., Chaintoutis, S.C., et al. The Veterinary Journal 23/09/2023 Link pdf
Seasonality and other risk factors for fleas infestations in domestic dogs and cats. Farrell, S., McGarry, J., Noble, P.-J.M., Pinchbeck, G.J., et al. Medical and Veterinary Entomology 09/01/2023 Link pdf
Seasonality and risk factors for myxomatosis in pet rabbits in Great Britain. Farrell, S., Noble, P.-J.M., Pinchbeck, G.L., et al. Preventive Veterinary Medicine 08/02/2020 Link pdf

Co-authorships

Title Authors Venue Date Link Download
Text mining for disease surveillance in veterinary clinical data: part two, training computers to identify features in clinical text. Davies, H., Nenadic, G., Alfattni, G., et al., Farrell, S., Radford, A.D. and Noble, P.-J.M. Frontiers in Veterinary Science 22/08/2024 Link pdf
Text mining for disease surveillance in veterinary clinical data: part one, rule-based extraction. Davies, H., Nenadic, G., Alfattni, G., et al., Farrell, S., Radford, A.D. and Noble, P.-J.M. Frontiers in Veterinary Science 23/01/2024 Link pdf
Evaluating ChatGPT text mining of clinical records for companion animal obesity monitoring. Fins, I.S., Davies, H., Farrell, S., Torres, J.R., Pinchbeck, G., et al. The Veterinary Record 06/12/2023 Link pdf
SARS-CoV-2 neutralising antibodies in dogs and cats in the United Kingdom. Smith, S.L., Anderson, E.R., Cansado-Utrilla, C., Farrell, S., et al. Current Research in Virological Science 04/08/2021 Link pdf

In Review

Title Authors Venue Date Link Download
In absence of vino, in machina discenti, veritas: Hierarchical semantic search in Ancient Greek texts. Farrell, S., Cannatella, P. In Review - - pdf
PetHarbor: A Standardised Framework for Sharing Veterinary Electronic Health Records. Farrell, S., Radford, A.D., Al Moubayed, N., Noble, P.-J.M. In Review - - pdf
Automated Disease Classification of Veterinary Clinical Narratives for Antimicrobial Stewardship Guideline Monitoring. Farrell, S., Singleton, D.A., Radford, A.D., Pinchbeck G., Noble, P.-J.M. & Al Moubayed, N. In Review - - pdf
Generalizable multilingual medical text de-identification using generative instruction tuning. Chenghao, X., Hudson, T., Jones, B., Watson, M., Farrell, S., Harmsworth-King, J., & Al Moubayed, N. In Review - - pdf
Comprehensive representation of health-related phenotypes in one million dogs using topic modelling of electronic health records. Noble, P.-J.M., Farrell, S., Al Moubayed, N. & Radford, A.D. In Review - - pdf
Quantifying and contextualising antimicrobial usage using automated disease classification tools. Lawson, A., Farrell, S., Noble, P.-J., Mair, T., Smith, J., Pinchbeck, G. In Review - - pdf

*Equal Contribution

Conferences and Presentations

Title Venue Location Date Type Link
🏆 Best Talk Award Democratising Veterinary EHRs: Balancing Privacy & Open Science for the future of LLM Research in Veterinary Science Symposium on Artificial Intelligence in Veterinary Medicine Cornell University, USA 17/05/2025 Oral pdf
Unravelling HPCIA prescription trends in veterinary healthcare: LLM approach towards antimicrobial stewardship surveillance in the UK  Association for Veterinary Informatics Talbot Veterinary Informatics Symposium Virginia-Tech University, USA 13/09/2024 Oral ppt
Can PetBERT help prevent the next apocalypse? Symposium on Artificial Intelligence in Veterinary Medicine Cornell University, USA 19/04/2024 Oral ppt
🏆 Best Talk Award Can CatGPT Help Prevent the Next Apocalypse? Annual BBSRC NLD DTP Conference Durham University, UK 22/07/2024 Oral ppt
Where are all the antimicrobials being used? LLM’s for monitoring adherence to antimicrobial stewardship guidelines in veterinary practices HealTAC Annual Conference Lancaster University, UK 13/06/2024 Poster pdf
Survey Results on what do clinicians want from their antimicrobial stewardship guidelines European Network for the Optimisation of Veterinary Antimicrobial Therapy (ENOVAT) Meeting University of Copenhagen, Netherlands 07/03/2024 Oral ppt
Syndromic Disease Classification of Veterinary EHR Notes for Disease Outbreak Detection HealTAC Annual Conference University of Manchester, UK 15/06/2023 Poster pdf
Syndromic Surveillance for Understanding Antimicrobial Usage in the veterinary community Medical Research Foundation National PhD Conference University of Bristol, UK 07/08/2022 Poster pdf
🏆 Best Talk Award Can AI tell you when your pet will die? Annual BBSRC NLD DTP Conference Durham University, UK 21/07/2022 Oral ppt
Current Status of multinational survey of companion animal veterinary clinicians: How can antimicrobial stewardship guidelines be optimised for the target stakeholder? European Network for the Optimisation of Veterinary Antimicrobial Therapy (ENOVAT) Meeting Aristotle University of Thessaloniki, Greece 13/05/2022 Oral ppt

Employment

Postdoctoral Researcher @ University of Liverpool

June 2025 – Present

  • Developed a automated syndromic classification system for Equine veterinary EHRs with EquineBERT foundation model
  • Created a veterinary NER model pipeline for automated disease coding and infectious disease survelliance
  • Continued work on the PetHarbor framework to expand across farm animal and equine dataset

Impact: Contextual antimicrobial usage in the UK equine population and automated disease coding in veterinary EHRs

Data Science Intern @ Evergreen Life

June 2024 – September 2024

  • Developed a RAG pipeline aligning model outputs with the Evergreen Life article repository for accuracy.
  • Built algorithmic recommendation systems to personalize healthcare insights.

Impact: Work integrated into a healthcare app serving over 1 million NHS patients.

NLP Demonstrator @ Durham University

January 2022 – April 2025

  • Taught foundational ML to advanced Transformer-based NLP to MSc CS and MBA cohorts.
  • Designed hands-on sessions demonstrating embeddings and text generation models.

Impact: Highest departmental module evaluations from students.

Undergraduate Researcher @ University of Liverpool

July 2020 – September 2021

  • Researched geospatial risk factors for fleas using EHR data from 34,000+ animals.

Impact: Published in the Journal of Medical and Veterinary Entomology.

Undergraduate Researcher @ University of Liverpool

June 2019 – January 2020

  • Applied multivariate logistic modelling to identify Myxomatosis risk factors.
  • Produced educational posters distributed to UK veterinary practices.

Impact: Published in the Journal of Preventive Veterinary Medicine.

Customer Experience Supervisor @ Sainsbury’s

October 2016 – September 2021

Teaching

Natural Language Processing @ Durham University

January 2021 – Present

  • Lead workshops spanning statistical NLP to large language model training.
  • Designed practical teaching materials, including detailed guides and Python notebooks.
  • Taught on the taught-Masters Computer Science programme.

Natural Language Analysis @ Durham University

January 2021 – Present

  • Delivered NLP workshops tailored to the MBA Business Analytics cohort.
  • Adapted teaching for students with limited Python experience, focusing on intuition and applied results before deep technical concepts.

Computational Thinking @ Durham University

December 2024 – January 2025

  • Assisted in marking undergraduate coursework and provided feedback on essay assessments.
  • Contributed to the development of detailed marking rubrics for consistent evaluation.

Introduction to Natural Language Processing @ NGSchool Machine Learning in Computational Biology

June 2021

  • Invited to deliver a lecture introducing NLP fundamentals to bioscience researchers.
  • Designed an interactive workshop on applying NLP techniques to biological datasets.
  • Focused on accessibility for participants with limited Python or ML experience.

Contact Me

Feel free to reach out for collaborations, job opportunities, or just a chat—I’d be happy to connect!

Email Me Linkedin Me
Email copied!