Researchers from our Computer Science Department have created new artificial intelligence (AI) tools that could help doctors and nurses spot very sick patients earlier and improve communication when people leave hospital.
Their work focuses on improving care in emergency and acute hospital settings, where staff often have to make fast decisions under pressure.
The research has been carried out with partners from the Northern Care Alliance NHS Foundation Trust and the University of Greater Manchester, and supported by the National Institute for Health and Care Research (NIHR) and the Medical Research Council (MRC).
Spotting sick patients early
In hospitals, it is vital to recognise when a patient's condition is starting to deteriorate.
At present, many hospitals use a system called NEWS2, which is based on paper-style charts and limited data.
Professor Noura Al Moubayed and Dr Matthew Watson have developed an AI model that looks at a patient's full electronic health record.
This includes vital signs as well as written notes made by clinicians when patients arrive at the Emergency Department.
By analysing all of this information, the system produces a more personalised risk score.
This helps staff identify which patients are most likely to become critically unwell within the next 24 hours and need urgent attention.
Tested on real hospital data
The AI model was created using data from more than 170,000 hospital admissions at Salford Royal Hospital.
It is one of the first studies to use written triage notes in this way, rather than relying only on structured data like numbers and tick boxes.
When tested, the AI system performed far better than NEWS2.
At the same level of false alarms, the AI correctly identified 92 percent of patients who later deteriorated, compared with just 13 percent using NEWS2.
This means the technology could help clinicians focus their time and resources on the patients who need them most.
The researchers' work won a Best Presentation Award at the Society for Acute Medicine's International Conference and was included in an NIHR policy briefing to the Department of Health and Social Care, highlighting the clinical importance of this research.
