A day in the life of...

a Data Science Lead

As the Data Science Lead for AXIS (Access Extract Integrate Safe Data) within the Clinical Informatics Research Unit (CIRU), I manage a multitude of projects at any given time. These projects span a wide range, from extracting and hosting data for international collaborations within our database, to performing data analysis using modern techniques like machine learning and specific bioinformatics analysis pipelines. Our projects not only vary in type but also focus on a broad spectrum of human diseases, from studying brain development in babies to lung diseases in the elderly. Beyond project management, a significant aspect of my role involves fostering collaboration between the University Hospital Southampton (UHS) and the University of Southampton. I work closely with the Research Data Science Unit at the UHS daily and AXIS (and CIRU) have become part of a major national governmental project with the UHS.

The primary objective of AXIS is to establish and uphold cutting-edge research pipelines that have a direct, tangible impact on patient health. A project that epitomizes this mission is a collaboration with UHS, where we are constructing a Secure Data Environment (SDE) as part of a national network of Sub National SDEs. This environment will offer a secure storage space for data and a platform for researchers to access and analyse data within CIRU’s secure infrastructure without the need to locally download datasets. Such an approach significantly enhances data security and minimizes the risk of data breaches. Another advantage of the SDE initiative is its potential to streamline data sharing across NHS sites, leveraging the benefits of a national healthcare service. This allows us to utilize larger datasets to gain insights into diseases, especially rare diseases with small numbers of patients, which would be challenging to study at individual sites.

Working as part of the AXIS team has enabled me to enjoy a multifaceted role. On any given day, I meet with collaborators from across the country, supervise my PhD and DM students, engage in coding for data transformations and analysis, or manage our database software that stores data for ongoing projects. Moving forward we look forward to facilitating ongoing projects and expanding our research capabilities transitioning from the pilot SDE project to a minimum viable product phase. We will also be building on award winning projects such as iDxLung (Cancer Research Horizons Innovation and Entrepreneurship ‘Further, Faster, Together’ award) by continuing to progress to iDxLung 2 where we will manage the data flows and storage.