Validation of AI models to measure physical activity after a stroke
Research type
Research Study
Full title
Validation and testing of artificial intelligence models to measure physical activity in patients admitted to hospital following a stroke
IRAS ID
298228
Contact name
Peter Hartley
Contact email
Sponsor organisation
Cambridge University Hospitals NHS Foundation Trust
Clinicaltrials.gov Identifier
Duration of Study in the UK
1 years, 11 months, 30 days
Research summary
How much people move around during the days in hospital after a stroke can affect their level of disability and quality of life long after they leave hospital. We are trying to develop ways to change how active people are in hospital to improve their rehabilitation outcomes. Before we do this, we need a way of measuring activity that is acceptable to patients and that can collect useful and accurate data for researchers.
We are developing algorithms using artificial intelligence that use information collected by small sensors to detect a person’s position, such as whether they are lying, sitting, or standing, and their movements, such as whether they are taking steps or standing up.
Sensor location will affect the accuracy of the model and acceptability of the method. We are therefore developing algorithms for four different locations:
1. clipped to clothing at chest level;
2. attached to a strap on the wrist;
3. attached to a strap on the ankle;
4. stuck to the thigh.
The purpose of the research is to continue the development of the algorithms and check whether they accurately recognise different positions and movements in people whose movement is affected by a stroke, and by being in a hospital environment (e.g. using a profiling bed).
We plan to recruit between 34 and 50 participants who are admitted to Cambridge University Hospital NHS Foundation Trust due to having a stroke. After providing informed consent, participants will be asked to complete a one-off assessment with a member of the research team and a ward physiotherapist. This should last no more than 45 minutes. Participants will be asked to wear the four sensors, and move through a series of postures, walk for up to six minutes, and stand as many times as they feel able in one minute.REC name
South Central - Oxford A Research Ethics Committee
REC reference
23/SC/0135
Date of REC Opinion
24 Apr 2023
REC opinion
Favourable Opinion