A pioneering research project is exploring how artificial intelligence (AI) could help healthcare teams identify patients at risk of developing hospital-acquired pressure ulcers.
Pressure ulcers remain a challenge for hospitals, affecting 700,000 people in the UK each year and costing the NHS £3.8 million everyday. Although up to 95% of pressure ulcers can be prevented through measures such as regular repositioning, specialist mattresses, and good nutritional support, healthcare providers still face a major challenge in identifying patients who are most at risk early enough to intervene effectively.
A new project led by Imperial College London is using testing a machine‑learning model designed to flag patients who may be at higher risk of developing a pressure ulcer during their hospital stay. Using routinely collected hospital data, including age, vital signs, blood test results, medications, and existing health conditions, to identify patterns that might otherwise be missed.
The current phase of the work focuses on externally validating the model using de‑identified patient data from hospitals across the East of England, covering admissions from 2017 to 2024. By comparing patients who developed pressure ulcers with those who didn’t, the team aims to understand how well the model performs in real‑world settings beyond where it was originally developed.
If the results are positive, this tool could help clinical teams identify at‑risk patients much earlier, allowing preventative steps to be taken sooner and reducing avoidable harm. Crucially, it would run quietly in the background, adding no extra tasks for busy staff.
This study will test whether the tool performs accurately when applied to patient data from hospitals in the East of England and will compare patients who developed pressure ulcers with those who did not, to verify that the tool correctly identifies high-risk individuals.
If the tool works well in East of England hospitals, it will drive the development of a tool that could be used in hospitals to help healthcare teams identify high-risk patients within hours of admission, allowing preventive care to begin immediately. This would hopefully reduce the number of patients who develop painful pressure ulcers, shorten hospital stays, and save NHS resources. The tool would work automatically in the background, using information already collected, without requiring extra work from busy nursing staff.
The project is sponsored and funded by Imperial College London and is now live with data in use.
Find out more, read the project page.