Accuracy of a computer vision system for estimating biomechanical measures of body function in axial spondyloarthropathy patients and healthy subjects.

"The authors declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: NC developed the computer vision approach as a paid consultant of Good boost wellbeing but was not directly involved in data collection. All statistical comparisons between methods were performed independently in the Oxford Brookes lab. BW was a paid consultant, and EH was a paid employee of Good boost wellbeing during the project but were not involved in data analysis or interpretation."

"Funding: The authors disclosed receipt of the following financial support for the research, authorship, and/or publication of this article: This work was supported by a grant from Innovate UK, The IUK project number 79429, (CRN: 11495760). National Institute for Health and Care Research Exeter Biomedical Research Centre and National Institute for Health and Care Research Exeter Clinical Research Facility support the research of Professor Helen Dawes and Dr Maedeh Mansoubi. The views expressed are those of the authors and not necessarily those of the NIHR, NHS or the UK Department of Health and Social Care."

"This study was part of a larger clinical study that aimed to examine the validity of a computer vision system to assess movement in various functional tests (ClinicalTrials.gov Identifier: NCT04895826). The reader is referred to a protocol paper for additional details. Note that fewer tests are included in the present study than in the protocol paper because during pilot testing it became clear that some test variables could not reliably be estimated using computer vision (specifically: chest expansion, standing posture and the modified Schober test). The study was approved by the Oxford Brookes University institutional ethical committee (UREC Registration No: 201429) and was conducted in accordance with the Declaration of Helsinki. The test protocol included two stages presented in detail below. Firstly, the accuracy of the computer vision system was tested using different camera positions and objects with known dimensions. The second stage involved concurrent validity testing in two participant groups, whereby the results generated by our computer vision system were compared to those of a trained clinician."