Meta-analysis of AI posture recognition for work-related musculoskeletal disorders prevention in occupational activities: comparison between untransformed, logit and Freeman-Tukey transformed performance.
- 1University of Toulon, Toulon, France.
- 2International Institute of Biomechanics and Occupational Ergonomics, Hyères, France.
Abstract
Introduction
The objective of this systematic review and meta-analysis was to evaluate the performance of artificial intelligence (AI) posture recognition systems in preventing the occurrence of work-related musculoskeletal disorders (WMSDs) across all occupational activities, following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.Methods
During May 2026, six databases were screened without publication date restrictions. Selected studies had to evaluate the performance of a posture recognition system using a machine learning (ML) or deep learning (DL) approach to assess the risk level of WMSD development using at least one of the following metrics: accuracy, specificity, sensitivity, precision, and F1 score. Risk of bias, heterogeneity, sensitivity, publication bias, and certainty of evidence analyses were conducted in the meta-analysis. Logit and Freeman-Tukey transformations were applied to the data before pooling and results were compared to those obtained from the untransformed. A meta-analysis was performed by performance parameter and by transformation. Four subgroup analyses were performed: comparison of AI methods, sensor types, professional activities, and ergonomic tools used, using pairwise mixed-effects meta-regressions.Results
Among the 1,071 unique entries, 26 studies were included. The logit transformation most closely approximated a normal distribution for all performance metrics without affecting heterogeneity, which was high (I² > 90%) in all analyses. Overall performance ranged from 85 to 95% for the five performance metrics. DL significantly outperformed ML by 4 to 16% for specificity, sensitivity, and accuracy, regardless of the transformation (p ≤ 0.05). Hybrid solutions demonstrated higher sensitivity and accuracy (> 99%, p < 0.05) with low heterogeneity (I² < 30%) regardless of the transformation. Occupational activity had a limited influence on overall performance, and no assessment tool consistently outperformed all others across all five performance parameters.Conclusion
In conclusion, the logit transformation consistently improved the statistical properties of the data and AI approach, type of sensors, occupational activity, and ergonomic risk assessment tool all significantly influenced the reported performance metrics. However, findings should be interpreted with caution and prudence is required regarding the deployment of the systems under real-world conditions due to the very low level of evidence.Systematic review registration
https://www.crd.york.ac.uk/PROSPERO/home, PROSPERO, n°: CRD420261432405.
Related
- Official incidence and trends of occupational musculoskeletal disorders in Turkey in 2014-2024: implications of possible underreporting.
- Occupational Leptospirosis in Urban Sanitation: Lessons for Early Recognition and Worker Protection
- Early recognition of eosinophilic granulomatosis with polyangiitis in outpatient settings: musculoskeletal and gastrointestinal clues beyond respiratory disease
- Occupational Health Complaints Among Physical Education Teachers: A Scoping Review of Musculoskeletal, Vocal, Hearing, Respiratory, Injury-Related, Cardiometabolic, and Work-Limiting Outcomes
- Topical Application of Derris scandens Gel for Musculoskeletal Pain Relief and Enhanced Fitness Performance: A Randomized Trial
BibTeX
@article{gorce2026metaanalysis,
title = {{Meta-analysis of AI posture recognition for work-related musculoskeletal disorders prevention in occupational activities: comparison between untransformed, logit and Freeman-Tukey transformed performance.}},
author = {Philippe Gorce and Julien Jacquier-Bret},
journal = {Frontiers in artificial intelligence},
year = {2026},
month = oct,
doi = {10.3389/frai.2026.1933096},
url = {https://europepmc.org/article/MED/42909137},
note = {CC BY},
}
RIS
TY - JOUR
TI - Meta-analysis of AI posture recognition for work-related musculoskeletal disorders prevention in occupational activities: comparison between untransformed, logit and Freeman-Tukey transformed performance.
AU - Philippe Gorce
AU - Julien Jacquier-Bret
PY - 2026
DA - 2026/10/07
JO - Frontiers in artificial intelligence
DO - 10.3389/frai.2026.1933096
UR - https://europepmc.org/article/MED/42909137
AB - Introduction The objective of this systematic review and meta-analysis was to evaluate the performance of artificial intelligence (AI) posture recognition systems in preventing the occurrence of work-related musculoskeletal disorders (WMSDs) across all occupational activities, following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.Methods During May 2026, six databases were screened without publication date restrictions. Selected studies had to evaluate the performance of a posture recognition system using a machine learning (ML) or deep learning (DL) approach to assess the risk level of WMSD development using at least one of the following metrics: accuracy, specificity, sensitivity, precision, and F1 score. Risk of bias, heterogeneity, sensitivity, publication bias, and certainty of evidence analyses were conducted in the meta-analysis. Logit and Freeman-Tukey transformations were applied to the data before pooling and results were compared to those obtained from the untransformed. A meta-analysis was performed by performance parameter and by transformation. Four subgroup analyses were performed: comparison of AI methods, sensor types, professional activities, and ergonomic tools used, using pairwise mixed-effects meta-regressions.Results Among the 1,071 unique entries, 26 studies were included. The logit transformation most closely approximated a normal distribution for all performance metrics without affecting heterogeneity, which was high (I² > 90%) in all analyses. Overall performance ranged from 85 to 95% for the five performance metrics. DL significantly outperformed ML by 4 to 16% for specificity, sensitivity, and accuracy, regardless of the transformation (p ≤ 0.05). Hybrid solutions demonstrated higher sensitivity and accuracy (> 99%, p < 0.05) with low heterogeneity (I² < 30%) regardless of the transformation. Occupational activity had a limited influence on overall performance, and no assessment tool consistently outperformed all others across all five performance parameters.Conclusion In conclusion, the logit transformation consistently improved the statistical properties of the data and AI approach, type of sensors, occupational activity, and ergonomic risk assessment tool all significantly influenced the reported performance metrics. However, findings should be interpreted with caution and prudence is required regarding the deployment of the systems under real-world conditions due to the very low level of evidence.Systematic review registration https://www.crd.york.ac.uk/PROSPERO/home, PROSPERO, n°: CRD420261432405.
SN - 2624-8212
ER -