Our mathematicians have helped harness the power of AI (artificial intelligence) to upgrade a tool that forecasts emergency hospital admissions across Scotland.
SPARRAv4 – Scottish Patients At Risk of Readmission and Admission version 4 – will inform healthcare providers in a more reliable and effective way about patients at high risk of requiring urgent hospital care within the next year.
This will help healthcare providers in Scotland anticipate and plan more effectively for emergency cases - and manage healthcare resources more efficiently.
Emergency hospital admissions routinely account for around half of all hospital stays in Scotland, placing tremendous strain on the healthcare system.
Researchers from our Department of Mathematical Sciences worked alongside experts at Public Health Scotland and the University of Edinburgh to develop an improved tool that can help combat this growing issue.
SPARRAv3 – the existing tool for helping Scottish healthcare providers manage patient care proactively – has been in use since 2012 and is calculated monthly for almost the entire Scottish population.
To build on SPARRAv3, the research team used health records from 4.8 million people living in Scotland, gathered between 2013 and 2018, and held by Public Health Scotland.
These records included information routinely collected by healthcare providers, such as patient history, prescription details, and previous hospital admissions.
Experts used machine learning techniques to analyse this dataset, developing SPARRAv4 as a tool to predict which patients might require emergency hospital care within a 12-month period.
Among those predicted to be at highest risk, SPARRAv4 correctly identified more emergency admissions than the previous version.
SPARRAv4 was also better calibrated, meaning that the predicted risk more closely matched observed emergency admission patterns.
Researchers highlight that while the tool will serve as a critical aid, it will not replace the essential clinical judgment of medical professionals.
Public Health Scotland will start promoting the updated model and engaging with healthcare professionals to encourage its widespread adoption in Scotland.
The research, supported by The Alan Turing Institute and Health Data Research UK, is published in npj Digital Medicine.
This research collaboration demonstrates how big datasets can be used to create tools to support medical professionals when identifying patients who might benefit from early intervention.
/prod01/prodbucket01/media/durham-university/central-news-and-events-images/83431-1920X290.jpg)