Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Evaluation of the Ability of Machine Learning-Models to Assess Postural Orientation Errors During a Single-Leg Squat

Älmqvist Nae, Jenny LU orcid ; Banega, Mauri ; Kronström, Filip ; Jakobsson, Andreas LU orcid and Ageberg, Eva LU orcid (2025) In Journal of orthopedic and sports physical therapy methods 1(1). p.17-29
Abstract
OBJECTIVES: To reach agreement among experts on visual assessments of postural orientation errors (POEs) during the single-leg squat (SLS), and to use expert agreement assessments as ground truth for machine learning (ML) models to evaluate their ability to classify POEs.

DESIGN: Methodological study with mixed-methods design.

METHODS: POEs of the lower extremity and trunk were assessed from videos and scored as good, fair, or poor. Three experts visually assessed each repetition for each POE independently and then reached agreement. ML models, one for each POE, were trained to assess POEs, using supervised learning on a subset of videos from the agreement assessment (n = 48). The remaining 99 videos were used to compare... (More)
OBJECTIVES: To reach agreement among experts on visual assessments of postural orientation errors (POEs) during the single-leg squat (SLS), and to use expert agreement assessments as ground truth for machine learning (ML) models to evaluate their ability to classify POEs.

DESIGN: Methodological study with mixed-methods design.

METHODS: POEs of the lower extremity and trunk were assessed from videos and scored as good, fair, or poor. Three experts visually assessed each repetition for each POE independently and then reached agreement. ML models, one for each POE, were trained to assess POEs, using supervised learning on a subset of videos from the agreement assessment (n = 48). The remaining 99 videos were used to compare the prediction of ML models with the agreement scores (criterion validity), using quadratic weighted kappa (Ƙ), Spearman's correlation coefficient (rs), and accuracy.

RESULTS: Machine learning models for the POEs knee medial to foot position (KMFP), femur medial to shank, and femoral valgus showed strong association/substantial agreement with expert agreement scores (rs = 0.566-0.702, Ƙ = 0.58-0.7). Machine learning models for the POEs pelvis and trunk showed moderate association/fair agreement with expert agreement scores (Ƙ = 0.28-0.4, rs = 0.324-0.432), and the POE foot pronation showed no association/agreement (Ƙ = −0.042, rs = −0.05). ML models predicted the expert agreement score in 53% to 78% of the cases.

CONCLUSION: Using ML models as a fast and comprehensive assessment of POEs during the SLS shows promising results, the ML models for the POEs KMFP, femur medial to shank, and femoral valgus indicating good validity. Training on larger datasets and/or modifications to some ML models may lead to improvements in model performance. (Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
machine learning, Movement quality, Deep learning, Postural orientation errors, reliability, single-leg squat
in
Journal of orthopedic and sports physical therapy methods
volume
1
issue
1
pages
17 - 29
ISSN
3065-8195
DOI
10.2519/josptmethods.2024.0086
project
Streamlining the evaluation of postural orientation using artificial intelligence
language
English
LU publication?
yes
id
68e7e8c7-74a3-42c4-94ef-6e433cf01450
date added to LUP
2025-06-05 13:55:36
date last changed
2025-06-05 15:59:12
@article{68e7e8c7-74a3-42c4-94ef-6e433cf01450,
  abstract     = {{OBJECTIVES: To reach agreement among experts on visual assessments of postural orientation errors (POEs) during the single-leg squat (SLS), and to use expert agreement assessments as ground truth for machine learning (ML) models to evaluate their ability to classify POEs.<br/><br/>DESIGN: Methodological study with mixed-methods design.<br/><br/>METHODS: POEs of the lower extremity and trunk were assessed from videos and scored as good, fair, or poor. Three experts visually assessed each repetition for each POE independently and then reached agreement. ML models, one for each POE, were trained to assess POEs, using supervised learning on a subset of videos from the agreement assessment (n = 48). The remaining 99 videos were used to compare the prediction of ML models with the agreement scores (criterion validity), using quadratic weighted kappa (Ƙ), Spearman's correlation coefficient (rs), and accuracy.<br/><br/>RESULTS: Machine learning models for the POEs knee medial to foot position (KMFP), femur medial to shank, and femoral valgus showed strong association/substantial agreement with expert agreement scores (rs = 0.566-0.702, Ƙ = 0.58-0.7). Machine learning models for the POEs pelvis and trunk showed moderate association/fair agreement with expert agreement scores (Ƙ = 0.28-0.4, rs = 0.324-0.432), and the POE foot pronation showed no association/agreement (Ƙ = −0.042, rs = −0.05). ML models predicted the expert agreement score in 53% to 78% of the cases.<br/><br/>CONCLUSION: Using ML models as a fast and comprehensive assessment of POEs during the SLS shows promising results, the ML models for the POEs KMFP, femur medial to shank, and femoral valgus indicating good validity. Training on larger datasets and/or modifications to some ML models may lead to improvements in model performance.}},
  author       = {{Älmqvist Nae, Jenny and Banega, Mauri and Kronström, Filip and Jakobsson, Andreas and Ageberg, Eva}},
  issn         = {{3065-8195}},
  keywords     = {{machine learning; Movement quality; Deep learning; Postural orientation errors; reliability; single-leg squat}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{17--29}},
  series       = {{Journal of orthopedic and sports physical therapy methods}},
  title        = {{Evaluation of the Ability of Machine Learning-Models to Assess Postural Orientation Errors During a Single-Leg Squat}},
  url          = {{http://dx.doi.org/10.2519/josptmethods.2024.0086}},
  doi          = {{10.2519/josptmethods.2024.0086}},
  volume       = {{1}},
  year         = {{2025}},
}