Imperial College London

Academic Institute

Clare Leon-Villapalos

Unknown

No

NIBDAPC_2023_0025

Falls are the most frequently reported patient safety incident in hospitals in England. The impact of falls includes distress, pain, injury including head injuries and bone fractures, loss of confidence, loss of independence, and death. Patients who suffer a fall in hospital have longer stays and are more likely to fall at home after hospital discharge. This project will address two problems: 1. While we know much about falls risk factors in older people, comparatively less is known about why falls happen in specific under-represented groups including people with learning disabilities and those who do not speak English. 2. Investigation and monitoring of inpatient falls currently relies on manual review of medical notes and incident reports by clinical staff - a process that is labour intensive and leads to long time lags between fall events and safety improvement initiatives. The aims of this project are to better understand why specific specific under-represented patient groups fall in hospital and to develop and test an IT system that will provide automated, near-real-time reports to Imperial College Healthcare NHS Trust on the circumstances and mechanisms of all inpatient falls. These reports will support coordinated safety monitoring and improvement efforts by staff across the Trust. The project entails: • describing the characteristics of patients who have fallen in hospital (e.g. age, ethnicity, deprivation score, diagnosis, co-morbidities, clinical condition at the time of the fall) • analysis to identify falls risk factors and outcomes - with emphasis on under-represented groups (patients with learning disabilities, non-native english speakers: groups identified by the British Geriatrics Society and Care England for whom evidence and guidance is lacking around falls) • applying Natural Language Processing to patients’ medical notes. Natural Language Processing is a form of Artificial Intelligence that enables insights to be extracted from free-text information. Artificial Intelligence is a set of instructions which are written in a computer program. The instructions run a computer programme which performs mathematical tests on data. The instructions that allow the AI to work are called an ‘algorithm’. • We will semi-automate these algorithms to provide near-real-time insights into the circumstances and mechanisms of falls to clinical and safety leads. This work will be complemented by qualitative work (interviews) with patients and clinical staff to better understand the trends we are seeing in the data and the impacts of having near-real-time insights into why patients fall in hospital.

A significant proportion of the population will be affected by falls during their lives: around one third of people over the age of 65 and more than half of people over 80 fall at least once per year. The impact of falls includes distress, pain, head injuries, bone fractures, loss of confidence, loss of independence, and even death. Patients who suffer a fall in hospital have longer stays and are more likely to fall at home after hospital discharge. There is also a significant additional carer burden linked to falls. This work could lead to patient/public benefit in two ways: 1. Both the British Geriatrics Society and Care England (charity representing the adult social care sector) have identified a need for further evidence and guidance on identifying and managing falls risk factors in people with learning disabilities and in those who do not speak English. Ensuring that language barriers do not increase the risk of harm to patients is an important priority for Imperial College Healthcare NHS Trust; the North-West London population is diverse, with many patients attending the Trust who do not speak English or who have English as a second language. This work will benefit patients by helping Imperial College Healthcare NHS Trust to better falls in these under-represented groups. This will contribute to developing strategies to reduce the risk of harm from falls in these patient groups (for example, if our analysis were to show that there is a higher incidence of falls in non-English speaking patients, the Trust could look at further investing in interpreting and translation services to support non-English speaking patients to engage with clinical staff around safe mobility). 2. An IT system enabling near-real-time monitoring of why patients are falling in our hospitals will support the Trust to identify trends enabling them to better respond to falls and improve patient safety. Near-real-time monitoring will support coordinated falls prevention efforts across the Trust (for example, if our near-real-time reporting system was to showing an increasing number of falls linked to patients with delirium (a state of mental confusion that can be caused by being very unwell or by being given certain medications), the Trust could implement an improvement project to help clinical staff to better understand and manage the risk of falls in patients with delirium).

Public Health Research

06/09/2023

26/05/2023

De-Personalised

Not applicable

Not applicable

One-off

06/09/2023

TRE