Mr Noel Kennedy
BA MPhil
Senior Research Fellow in Artificial Intelligence
Department: Professional Services
Campus: Camden
Research Centres: Veterinary Epidemiology, Economics and Public Health
Noel Kennedy is a Senior Research Fellow in Artificial Intelligence at the Royal Veterinary College (RVC). With over 25 years of experience as a developer, including two decades working in the veterinary domain, he has played a key role in advancing the intersection of veterinary informatics and epidemiology.
Noel Kennedy previously worked in finance in the City of London before joining the RVC. He completed a master’s degree in Advanced Computer Science at Cambridge. At the RVC, he helped develop the VeNom veterinary coding system and built the VetCompass application, which has supported more than 100 peer-reviewed publications in veterinary epidemiology.
Noel Kennedy now leads projects that apply large language models on one of the world’s largest veterinary datasets, with a focus on bridging artificial intelligence and veterinary science to improve animal health research.
-
Improved Stewardship to Protect Veterinary Antimicrobial Usage in UK Cats and Dogs
This study aims to identify and promote effective antimicrobial stewardship interventions in UK first-opinion companion animal practice. Our objectives are to benchmark current antimicrobial usage in dogs and cats, develop and implement a range of antimicrobial stewardship interventions, evaluate the impact of these interventions, and promote widespread adoption of the most effective interventions across the UK.
-
.jpg?v=638497413074474753)
Improved Stewardship to Protect Veterinary Antimicrobial Usage in UK Cats and Dogs (In Progress)
People: Stuart Becker, David Brodbelt, Dan O'Neill, Sian-Marie Frosini, Noel Kennedy, David Church
Vet Compass Project Type: Dog, Cat, Small Animal
Funded by the Petplan Charitable Trust, this project aims to identify and promote effective and practical antimicrobial stewardship interventions for widespread adoption in veterinary practice.
-
The VetCompass Causal Inference Research Programme (In Progress)
People: Camilla Pegram, Dan O'Neill, David Brodbelt, Noel Kennedy, David Church
Vet Compass Project Type: Dog, Cat, Small Animal
The VetCompass Causal Inference Research Programme builds on previous PhD research, applying target trial emulation to generate real-world evidence as an alternative when traditional RCTs are not feasible.
-
Using Veterinary Practice Data to Improve Understanding of Canine Chronic Kidney Disease (In Progress)
People: Dan O'Neill, Jonathan Elliott, Noel Kennedy, Camilla Pegram, David Brodbelt
Vet Compass Project Type: Dog
The aim of this study is to describe the frequency, features and clinical management of CKD in dogs attending primary care practice and evaluate factors associated with CKD survival.
-
VetCompass eClinical Trials (Complete)
People: Camilla Pegram, Dan O'Neill, David Brodbelt, Ruby Chang, Noel Kennedy
Vet Compass Project Type: Dog
The study aims to develop innovative statistical approaches to veterinary electronic patient records to evaluate the effectiveness of clinical interventions in dogs.
-
VetCompass eClinical Trials (VETs) – Generating Interventional Evidence from Observational Data
The study aims to develop innovative statistical approaches to veterinary electronic patient records to evaluate the effectiveness of clinical interventions in dogs.
This project aims to develop and apply novel causal inference methods that evaluate real world interventions via routinely collected veterinary EPRs. These methods will be applied to VetCompass data to provide real world inference for some key interventions.
-
VetCompass Project
VetCompass is a welfare-focussed epidemiological research project that shares anonymised clinical data from veterinary practices to investigate the frequency and nature of companion animal health problems.
Modern veterinary medicine has access to increasingly effective tools for diagnosis and treatment; yet many animals still continue to suffer from disorders that might be reduced or avoided if risks were better understood and measured.