Our statisticians used machine learning to predict emergency hospital admission risk of patients in Scotland

Experts from our Mathematical Sciences Department have contributed statistical analysis in the SPARRA project.

What is the SPARRA project?

The SPARRA (Scottish Patients at Risk of Re-admission) project is a machine-learning based tool to predict individualised risk of emergency hospital admission for essentially the entire population of Scotland.

The project was first developed by NHS Scotland’s Information Services Division and in a recent collaboration with The Alan Turing Institute the model has been updated and extended using state of the art machine learning and artificial intelligence methods.

Once deployed, this model will produce a score every month for 80% of the Scottish population (about 3.6 million patients), assessing their risk of emergency admission to hospital in the following 12-month period.

This score is delivered automatically direct to GP surgeries and can potentially be utilised when informing primary care intervention.

Advanced statistical analysis

Our statisticians are key members of the project, providing both academic leadership and statistical analysis to improve predictive performance of the next generation of SPARRA, whilst ensuring reproducibility and scalability of the entire analytical workflow.

This involves both a careful application of the latest machine learning and artificial intelligence methods, as well as production of a reproducible data science environment.

The new model provides substantial improvements to both precision and calibration, utilising a super learner of a collection of machine learning models.

This means both that more patients identified at risk are correctly flagged and that the judgement of the level of that risk is more accurate, potentially enabling better health outcomes through more accurately informed GPs.

This work was possible as a result of multiple funding sources secured by our faculty, including from the AI for Science and Government programme (Turing), Health Data Research UK, The Health Foundation and EPSRC.

Find out more

• Learn more about the work of Dr Louis Aslett and Dr James Liley.
• Find out more about the SPARRA project.

Our Department of Mathematical Sciences combines world-leading research with a dedication to the learning experience of our students. Ranked 4^th in the UK in The Complete University Guide 2023, we offer a unique blend of high-quality teaching and research across a wide range of disciplines and provide practical experience to support future careers and employment prospects.

Feeling inspired? Visit our Mathematical Sciences webpages to learn more about our postgraduate and undergraduate programmes.