An innovative artificial intelligence (AI) system is helping reduce avoidable visits to the emergency department at Tameside & Glossop Integrated Care NHS Foundation Trust, easing pressure on frontline NHS services while ensuring patients receive the right care sooner.
With emergency departments across the country facing rising demand, the Trust has developed a pioneering AI-powered tool capable of identifying patients who are most likely to return to A&E within 30 days of their initial visit.
Rather than simply analysing past activity, the system predicts which patients are at the greatest risk of reattendance, allowing healthcare professionals to intervene early with personalised support in the community before health problems escalate into emergencies.
Developed by the Trust’s Business Intelligence team, the model generates an individual risk score using information routinely collected during an emergency department visit. This includes demographic information, how the patient arrived at hospital, triage details, long-term health conditions and previous emergency department or hospital admissions.
Patients identified as high risk are reviewed by multidisciplinary teams made up of NHS staff and partners from health and social care organisations. Together, they assess each person’s needs and coordinate tailored follow-up care designed to reduce the likelihood of another emergency visit.
The AI system also continues to monitor patients after intervention, helping ensure agreed actions have been completed, and appropriate care has been delivered.
Early results have been highly encouraging, with emergency department reattendance among high-risk patients reduced by between 33 and 50 per cent, depending on the week.
The Trust says the model will continue to learn and improve over time, increasing its accuracy while introducing greater automation to reduce the administrative burden on clinical staff and further enhance patient safety.
Ease of use was a key priority during development. The AI tool has been designed as a single, user-friendly platform that can be accessed from multiple devices, enabling staff from across the health and care system to make consistent, informed decisions without having to switch between different computer systems.
Patient safety, accuracy and data security were also central to the project. Extensive testing was carried out before the system was introduced, with patient safety specialists helping to develop the clinical processes surrounding its use. Data security experts also ensured patient information remains protected and is only accessible to authorised staff.
Liam Brierley, Operational Intelligence Lead at the Trust, said: “The tool allows us to predict emergency department reattendance, rather than simply providing a retrospective analysis.
“Our ambition is ultimately to change how we anticipate patient need, moving from reactive care to intelligent, preventative intervention.
“This project is a strong example of how we can take advantage of new, advanced technologies like AI for the benefit of both our patients and staff. The AI tool doesn’t replace clinical judgement but rather empowers clinicians with the insight they need to deliver high-quality care before a crisis occurs.”
The project’s success has already gained national recognition. It has been shortlisted in the ‘Urgent and Emergency Care Safety Initiative of the Year’ category at the 2026 HSJ Patient Safety Awards, with winners due to be announced on September 28.