Researchers from the University of Edinburgh have used machine learning to update a tool used by healthcare providers highlighting individuals at high risk of urgent hospital care within the next year.

By leveraging AI technology, SPARRAv4 (Scottish Patients At Risk of Readmission and Admission version 4) can more accurately predict which patients in Scotland will need emergency hospital admissions, outperforming the previous version.

The Edinburgh researchers, working alongside colleagues at the University of Durham, said that the AI-powered update will help healthcare providers in Scotland anticipate and plan more effectively for emergency cases, and manage healthcare resources more efficiently. 

The team used health records from 4.8 million people living in Scotland, gathered between 2013 and 2018, by Public Health Scotland, including information that is routinely collected by healthcare providers, such as patient history, prescription details and previous hospital admissions. 

They then used machine learning techniques to analyse the dataset and developed the new AI urgent care tool to predict which patients might require emergency hospital care within a 12-month period.  

“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,” said Dr Jill Ireland, principal analyst at Public Health Scotland.

“This has been a fruitful research collaboration between Public Health Scotland 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.”

As well as correctly identifying more emergency admissions, SPARRAv4 was also found to be better at gauging individual patients’ level of risk of needing urgent hospital care.  

With emergency hospital admissions routinely accounting for around half of all hospital stays in Scotland, it’s hoped the new AI urgent care tool will be able to reduce the enormous strain placed on the Scottish healthcare system.

However, while the tool will serve as a critical aid, it will not replace the essential clinical judgement of medical professionals, with Public Health Scotland engaging with healthcare workers to promote the updated model and encourage its widespread adoption in Scotland. 

“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,” said Dr Catalina Vallejos, Reader at the University of Edinburgh’s MRC Human Genetics Unit.

Recommended reading

• UK Gov Funds VR, AI Tech Projects For Reducing Drug Deaths
• One in Five GPs Use Generative AI
• How Many Lives Could Aberdeen Uni’s Skin Cancer App Potentially Save?

A recent wave of new healthcare technologies has followed from the swell in AI development. Last month, the University of Dundee discovered the potential for AI to transform care for heart failure patients, and Scottish scientists have been trialling AI to analyse data from CT and MRI scans in the hopes of identifying patterns that could indicate the likelihood of dementia.

Local healthcare has also been impacted by the growing utilisation of AI tools, with the Turing Institute today releasing research that shows nearly a third (29%) of doctors have already used some form of AI in their practice in the last 12 months.