Wear-axSpA
Research type
Research Study
Full title
Investigating computer vision and wearable-based monitoring of disease metrics in Axial Spondyloarthritis (axSpA)
IRAS ID
348963
Contact name
Gregory Knowles
Contact email
Sponsor organisation
University of Bath
Duration of Study in the UK
1 years, 0 months, 1 days
Research summary
Axial Spondyloarthritis (axSpA) is a chronic condition that principally affects the spine, causing painful inflammation and sometimes fusion of the vertebrae. The study will target three existing measurements of axSpA, the Bath Ankylosing Spondylitis Metrology Index (BASMI), the Bath Ankylosing Spondylitis Function Index (BASFI), and the Ankylosing Spondylitis Performance Index (ASPI).
The BASMI consists of 5 physical measures assess their spinal mobility. The disadvantage of this measurement is that it requires a trained person to administer the measurement, meaning it is mostly performed in a hospital setting on an infrequent basis. The BASFI measures function and level of disability. It is administered as a 10-item questionnaire, and asks patients to rate from 0 (easy) to 10 (impossible) how hard they find a set of every day activities. However, it suffers from recall bias and subjectivity. This has lead researchers to investigate asking patients to physically perform these activities, and measure how well they perform them. This lead to the development of the ASPI, which assesses the physically performs three of these activities. Whilst this improves the objectivity of the assessment, it is still harder to administer than the BASFI questionnaire as this also requires an external observer.
The aim of the study is to investigate the feasibility of measuring the BASMI, BASFI and ASPI using consumer grade wearable devices (without modification), and via computer vision techniques to overcome these shortcomings. During a 2-week rehabilitation for axSpA patients, patients will be measured at the beginning, middle, and end of the course. We will provide patients with wearable devices during these assessments, as well as capturing video, and then train machine learning models to map the data to the disease score.
REC name
Yorkshire & The Humber - Leeds West Research Ethics Committee
REC reference
26/YH/0076
Date of REC Opinion
11 May 2026
REC opinion
Further Information Favourable Opinion