MRC Epidemiology UnitSenior Data Scientist
Statistics and data science
Current work and interests
Tom is a Senior Data Scientist and manages the Unit’s Trusted Research Environment (TRE) which provides a secure way for collaborators to access and use study data (e.g. from EPIC Norfolk) without the data being removed from the Unit.
He also specialises in using machine learning and web scraping to acquire and enrich novel data sets. Examples of this include gathering publicly available data on the internet to build up a nutritional profile of takeaway food building a too to classify a takeaway outlet (e.g. as a pizza shop) from its name and limited other properties to understand the food environment.
Background and experience
Previously Tom has been a technical work package lead on the EUCAN-Connect project.
EUCAN-Connect brings together scientists and technologists from Europe and Canada to improve the quality of health care through a more efficient use of existing data. Large-scale integrated cohort data analysis for personalized and preventive healthcare will be made possible through an open, scalable data platform for cohorts, researchers and networks.
He is also responsible for the technical delivery of the InterConnect project. The InterConnect project aims to facilitate and coordinate research on the interaction between genetic and environmental factors in the aetiology of diabetes and obesity across different populations by creating a global diabetes research network.
Tom has a Master’s degree in mechanical engineering from Cambridge University. Before coming to the Unit, he has worked at Caterpillar, Thomson Reuters and Tesco.