Dataset Information

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

ABSTRACT:

Objective

Advances in computer vision make it possible to combine low-cost cameras with algorithms, enabling biomechanical measures of body function and rehabilitation programs to be performed anywhere. We evaluated a computer vision system's accuracy and concurrent validity for estimating clinically relevant biomechanical measures.

Design

Cross-sectional study.

Setting

Laboratory.

Participants

Thirty-one healthy participants and 31 patients with axial spondyloarthropathy.

Intervention

A series of clinical functional tests (including the gold standard Bath Ankylosing Spondylitis Metrology Index tests). Each test was performed twice: the first performance was recorded with a camera, and a computer vision algorithm was used to estimate variables. During the second performance, a clinician measured the same variables manually.

Main measures

Joint angles and inter-limb distances. Clinician measures were compared with computer vision estimates.

Results

For all tests, clinician and computer vision estimates were correlated (r² values: 0.360-0.768). There were no significant mean differences between methods for shoulder flexion (left: 2 ± 14° (mean ± standard deviation), t = 0.99, p < 0.33; right: 3 ± 15°, t = 1.57, p < 0.12), side flexion (left: - 0.5 ± 3.1 cm, t = -1.34, p = 0.19; right: 0.5 ± 3.4 cm, t = 1.05, p = 0.30) and lumbar flexion ( - 1.1 ± 8.2 cm, t = -1.05, p = 0.30). For all other movements, significant differences were observed, but could be corrected using a systematic offset.

Conclusion

We present a computer vision approach that estimates distances and angles from clinical movements recorded with a phone or webcam. In the future, this approach could be used to monitor functional capacity and support physical therapy management remotely.

SUBMITTER: Cronin NJ

PROVIDER: S-EPMC10291378 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Cronin Neil J NJ Mansoubi Maedeh M Hannink Erin E Waller Benjamin B Dawes Helen H

Clinical rehabilitation 20230113 8

<h4>Objective</h4>Advances in computer vision make it possible to combine low-cost cameras with algorithms, enabling biomechanical measures of body function and rehabilitation programs to be performed anywhere. We evaluated a computer vision system's accuracy and concurrent validity for estimating clinically relevant biomechanical measures.<h4>Design</h4>Cross-sectional study.<h4>Setting</h4>Laboratory.<h4>Participants</h4>Thirty-one healthy participants and 31 patients with axial spondyloarthro ...[more]

PMID: 36638533

Similar Datasets

Project description:Axial spondyloarthropathy (SpA) is a group of inflammatory diseases, with ankylosing spondylitis as the prototype. SpA affects the axial skeleton, entheses, joints and, at times, the eyes. This study tested the hypothesis that SpA is characterized by a distinct pattern of gene expression in peripheral blood of affected individuals compared with healthy controls.High-density, human GeneChip probe arrays were used to profile mRNA of peripheral blood cells from 18 subjects with SpA and 25 normal individuals. Samples were processed as two separate sets at different times (11 SpA + 12 control subjects in primary set (Set 1); 7 SpA+ 13 control subjects in the validation set (Set 2)). Blood samples were taken at a time when patients were not receiving systemic immunomodulatory therapy. Differential expression was defined as a 1.5-fold change with a q value < 5%. Gene ontology and pathway information were also studied.Signals from 134 probe sets (representing 95 known and 12 unknown gene transcripts) were consistently different from controls in both Sets 1 and 2. Included among these were transcripts for a group of 20 genes, such as interleukin-1 (IL-1) receptors 1 and 2, Nod-like receptor family, pyrin domain containing 2 (NLRP2), secretory leukocyte peptidase inhibitor (SLPI), secreted protein acidic and rich in cysteine (SPARC), and triggering receptor expressed on myeloid cells 1 (TREM-1) that are clearly related to the immune or inflammatory response and a group of 4 transcripts that have a strong role in bone remodeling.Our observations are the first to implicate SPARC, SLPI, and NLRP2, a component of the innate immune system, in the pathogenesis of SpA. Our results also indicate a possible role for IL-1 and its receptors in SpA. In accord with the bone pathology component of SpA, we also found that expression levels of transcripts reflecting bone remodeling factors are also distinguishable in peripheral blood from patients with SpA versus controls. These results confirm some previously identified biomarkers implicated in the pathogenesis of SpA and also point to novel mediators in this disease.

Dataset Information

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

Objective

Design

Setting

Participants

Intervention

Main measures

Results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets