Hospitals across Scotland will be able to more accurately anticipate when patients will need to be admitted to emergency departments thanks to Scottish researchers who have harnessed the power of artificial intelligence.

In AI model tests, researchers found that the ‘Scottish Patients At Risk of Readmission and Admission version 4’ (SPARRAv4) can more accurately identify emergency admissions than the previous version developed over a decade ago.

Emergency hospital admissions routinely account for around half of all hospital stays in Scotland, and there is rising concern for emergency departments this winter amid record delays in hospital discharge.

Public Health Scotland (PHS) has collaborated with Universities of Edinburgh and Durham researchers to employ machine learning to help manage the ‘growing issue’ of increased demand on emergency departments.

The AI-powered update will help healthcare providers in Scotland anticipate and plan more effectively for emergency cases and manage healthcare resources more efficiently, according to the researchers.

Dr Jill Ireland, Principal Analyst at Public Health Scotland, 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 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.” 

The update to this tool is the first in 12 years.

It will be used by healthcare providers to highlight individuals at high risk of urgent hospital care within the next year, drawing from the health records of 4.8 million people living in Scotland.

The records include information routinely collected by healthcare providers, such as patient history, prescription details and previous hospital admissions.

Dr 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.”

This comes as the Scottish government has announced a new method of capturing emergency care activity across Scotland to be rolled out next year as part of efforts to improve waiting times and patient care.

National Clinical Lead for Quality and Safety in NHS Scotland, Dr John Harden said as Scotland “strives to improve A&E performance”, it is vital that NHS Scotland has a “clear picture” of emergency care across the country.

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.

The research team has highlighted that while the tool will serve as a critical aid, it will not replace the essential clinical judgement of medical professionals.

Public Health Scotland is set to start promoting the updated model and engaging with healthcare professionals to encourage its widespread adoption in Scotland this year.

Dr Louis Aslett, Associate Professor of Statistics at Durham University, said the collaborative work also demonstrates the impact of health data collection:

“AI and machine learning depend on large amounts of high-quality data and secure platforms. Thanks to Public Health Scotland's exceptional data curation, this research collaboration has developed a model that could greatly benefit the public.

“This demonstrates how big data can create tools to support medical professionals when identifying patients who might benefit from early intervention.”

Read more: AI for early heart attack diagnosis; “Huge alarm” at hospital discharge delays; Pain assessments meet AI in care homes; ‘Unprecedented' crisis in community health and care; Health and care workforce to be bolstered over winter; NHS staff say data vital to improving care; Chief medic: Innovate to tackle health & planet crises