Understanding fall risk in real-world settings

  • Research type

    Research Study

  • Full title

    Understanding fall risk in real-world settings for people with Parkinson’s disease (U-Fall PD): Deep Learning Approach to Video Based Environmental Classification

  • IRAS ID

    324075

  • Contact name

    Alan Godfrey

  • Contact email

    alan.godfrey@northumbria.ac.uk

  • Sponsor organisation

    Northumbria University

  • Duration of Study in the UK

    2 years, 0 months, 0 days

  • Research summary

    Walking assessment is used by a healthcare professional (e.g., physiotherapist) to help them determine fall risk in those who may have poor mobility, such as people with Parkinson's disease (PwPD). Currently, walking assessment to inform fall risk is done under observation in a clinical setting e.g., the physiotherapist watches the person walk a short distance. At home, PwPD complete a falls diary. However, falls diaries are very subjective and very often they are not completed. Therefore, there is limited information for physiotherapists to better aid their patient. There is a need to develop electronic-based tools to help better inform walking assessment to provide better strategies to limit risk of falling.

    Modern approaches to measure walking include small electronic devices like accelerometers, the same technology often found in watches and mobile phones. However, use of an accelerometer only does not provide critical information as to where the person was walking (e.g., indoor or outdoor), which could greatly improve a physiotherapists understanding of walking and fall risk in PwPD. The aim of this project is to investigate the use of an accelerometer-based wearable (worn on the lower back) with camera-based glasses to provide more information on how a person walks in the clinic and at home. The use of camera-based glasses will help improve walking assessment and offer better clarity on fall risk in any environment/location. Specifically, the camera-based glasses will provide video data of (i) the environment and (ii) where the PwPD is looking. video imagery will be anonymised by the AI algorithms to protect participants anonymity.

  • REC name

    South West - Frenchay Research Ethics Committee

  • REC reference

    24/SW/0022

  • Date of REC Opinion

    26 Apr 2024

  • REC opinion

    Further Information Favourable Opinion