Long Stay Risk Score Algorithm
Benefits
The model successfully detects two-thirds of long stayers and stratifies risk effectively. It maintained performance accuracy within 1% when tested on unseen data before, during, and after the 2020 COVID waves. The tool has potential to decrease length of hospital stays overall, with corresponding reductions in patient deterioration, mortality during admission, and reduced readmission rates.
Details
- Tool name
- Long Stay Risk Score Algorithm
- Organisation
- Gloucestershire Hospitals NHS Foundation Trust
- Status
- pilot
- AI method (as recorded)
- Machine Learning, supervised, hybrid
- AI method (normalised tags)
- Machine Learning supervised hybrid
- Usecase
- Predictive Analytics
- Origin
- NHS AI Lab Skunkworks
- Owning team
- Business Intelligence team at Gloucestershire Hospital (GHFT)
- Date added
- Scrape date
- 23/03/2026
- Source note
- Long stayers at Gloucestershire Hospitals Trust occupy an average of 278 beds per day, around 4% of all admissions but account for 34% of bed use. These patients have an 11% mortality rate during their hospital stay (compared to 5% of all admissions), and 23% became unwell after being deemed medically fit for discharge (compared to 1% overall). [Source]