Scottish researchers develop AI-powered tool to break ground in predictive care

Scottish researchers have developed an AI-powered solution to help predict patients at high risk of urgent hospital care.

Experts from the University of Edinburgh and Durham University have partnered with Public Health Scotland (PHS) to develop an AI-powered update for a tool used to identify those at high risk of urgent hospital care within a 12-month period.

Experts claim the development, which marks the first update of the tool in more than a decade, will alleviate the pressure on the healthcare system by allowing professionals to better plan for emergency cases and manage resources more efficiently.

In tests, researchers found the new tool, named SPARRAv4 (Scottish Patients At Risk of Readmission and Admission version 4) was better able to identify emergency admissions than the previous version.

Catalina Vallejos, reader at the University of Edinburgh’s MRC Human Genetics Unit, said: “In an era where healthcare systems are under high stress, we hope that the availability of robust and reproducible risk prediction scores such as SPARRAv4 will contribute to the design of proactive interventions that reduce pressures on healthcare systems and improve healthy life expectancy.”

The announcement comes as statistics from the National Record of Scotland, show a slight increase in life expectancy north of the border, standing at 80.9 years for females and 76.9 years for males. These figures reflect a boost of almost seven weeks for females and around 14 weeks for males, compared to 2020-2022. However, they remain lower than the peak of 2012-2014.

PHS provided the health records from 4.8 million people living in Scotland, gathered between 2013 and 2018, to test the tool.

Experts then used machine learning techniques to analyse the dataset and developed SPARRAv4 to predict which patients might require emergency hospital care within a 12-month period.

Findings also showed SPARRAv4 was better at gauging individual patients’ level of risk of needing urgent hospital care.

It is understood that PHS will soon start promoting the updated model and engaging with healthcare professionals to encourage its widespread adoption in Scotland.

However, researchers warned that the tool will not replace the essential clinical judgement of medical professionals.

The research, supported by The Alan Turing Institute and Health Data Research UK, was published in the medical journal, npj Digital Medicine.

Jill Ireland, principal analyst at PHS, said: “The SPARRA model was developed to respond to a growing recognition of the need to shift from reactive healthcare to a more preventative and anticipatory approach. This has been a fruitful research collaboration between PHS and colleagues from the Alan Turing Institute, to harness the power of Scotland’s data through the use of innovative statistical and AI techniques to update our SPARRA model.”