Multimodal Assessment of Falls Risk/ Movement Performance in Older Adults Using Wearable Sensor Technologies and Visual Computing Techniques

About the Project

Falls are a leading cause of severe injury and loss of functional independence among older adults. Performance measures derived from gait and postural assessments offer valuable insight into an individual’s movement quality (and hence their falls risk). Research indicates that these assessment outcomes provide strong discriminatory power in differentiating older adults with high and low falls risk. Gait analysis is commonly performed using a 3D multi-camera motion capture system and/or an instrumented walkway system to record movement. However, the high cost of these systems and the substantial space required for valid gait assessment restrict their use to specialised research settings. Alternatively, wearable Inertial Measurement Units (IMUs) or embedded smartphone accelerometers offer an accessible means of characterising movement quality during clinically relevant movement tasks. In addition, in recent years, advances in computer vision techniques have enabled contactless human motion tracking through 3D pose estimation from standard video recordings, providing a scalable and non-intrusive alternative to traditional methods.

The proposed PhD will investigate how movement data captured using three distinct measurement modalities: IMUs, smartphone accelerometers, and computer vision analysis, can be used to characterise movement quality and identify predictive indicators that inform the assessment of falls risk in older adults. This will involve cross-modal data fusion and machine learning methods to combine sensor- and computer-derived output measures, enabling a unified representation of movement quality. The physical functioning tasks to be evaluated will include: standing rise up-on-the-toes 30-second test (UTT-30), seated heel tapping 60-second test (HR-60), seated toe tapping 60-second test (ToeTap-60) and gait (3 minutes continuous walking, looping repeatedly over a 3.6 m pressure-sensitive walkway).

The validity of the developed analysis approaches will be assessed by comparing assessment outcomes determined using the three measurement modalities with benchmark data obtained from traditional measurement methods, including force platforms and instrumented walkways. Associations between the derived movement parameters and participants’ risk of falling, determined using the validated Falls Efficacy Scale (FES) ratings, will then be examined to evaluate each test’s potential as predictive markers of falls risk.

The PhD will be done as a collaboratively between Dr John Buckley at the Department of Biomedical Engineering (University of Bradford), Professor Rami Quhwaji at the Department of Computer Science (University of Bradford), and Professor Andre Rodacki from the School of Physical Education, University of Parana, Curitiba, Brazil.

How to apply

Formal applications can be submitted via the University of Bradford web site. Applicants should register an account, select 'Postgraduate Research' as the course type and use the keywords 'healthcare technology'. Please include the project title on the Research Proposal section; applicants are not required to supply a research proposal for this project.

Informal enquiries are also welcome.