Refinement of an eFalls tool - a multivariable prediction model for the risk of ED attendance or in-hospital fall or fracture in individuals accessing mental health or learning disability services - eFalls
Chief Investigators: Dr Luis Marino, South West Yorkshire Partnership NHS Foundation Trust
Dr Stephen Lim, University of Southampton
Co-investigators: Professor Andrew Clegg, ARC Yorkshire & Humber, University of Leeds
Professor Sam Chamberlain, University of Southampton
Professor Chris Kipps, University Hospital Southampton
Start Date: 1st April 2025
End Date: 31st March 2026
Partners: University Hospital Southampton NHS Trust, South West Yorkshire Partnership NHS Foundation Trust, NIHR ARC Yorkshire & Humber, University of Leeds
Our Research
Falls have a significant impact on physical health with increased risk of morbidity including, dehydration, pain, chest infection and reduced ability to get on with daily activities of living. This may lead to reduced levels of activity, social isolation, depression and anxiety. Individuals with a mental health or learning disability diagnosis have an increased risk of falls.
Although several falls screening tools are available, they usually need a healthcare professional to manually screen electronic health records, which may not always be done. Falls have a big impact on health and social care systems and is a leading reason for admission to hospital. Treatment for fractures also costs the NHS an estimated £4.5billion a year.
This study aims to take an electronic tool (eFalls) which automatically predicts the risk of falls in older people (over the age of 65 years) and explore whether it accurately predicts the risk of falls in adults with a mental health or learning disability diagnosis.
We will use routinely collected data from two health services covering the regions of West Yorkshire and Hampshire and Isle of Wight for this study. Data for patients aged 18 years and above with a known mental health diagnosis will be included in this study. We want to know whether this tool can be used to predict the falls risk among people living with mental health disorders or learning disability and how effective the tool is in predicting falls. If shown to be successful, we will share our findings with healthcare commissioners and policymakers and the following steps will be to pilot this tool in the healthcare setting to explore its impact on patient outcomes.