{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:56:05Z","timestamp":1791356165724,"version":"4.3.1"},"reference-count":114,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T00:00:00Z","timestamp":1791331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      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 (I\n                      <jats:sup>2<\/jats:sup>\n                      \u202f&amp;gt;\u202f90%) 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 (\n                      <jats:italic>p<\/jats:italic>\n                      \u202f\u2264\u202f0.05). Hybrid solutions demonstrated higher sensitivity and accuracy (&amp;gt; 99%,\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.05) with low heterogeneity (I\n                      <jats:sup>2<\/jats:sup>\n                      \u202f&amp;lt;\u202f30%) 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.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Systematic review registration<\/jats:title>\n                    <jats:p>\n                      <jats:uri>https:\/\/www.crd.york.ac.uk\/PROSPERO\/home<\/jats:uri>\n                      , PROSPERO, n\u00b0: CRD420261432405.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1933096","type":"journal-article","created":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:42:08Z","timestamp":1791355328000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"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"],"prefix":"10.3389","volume":"9","author":[{"given":"Philippe","family":"Gorce","sequence":"first","affiliation":[{"name":"University of Toulon","place":["Toulon, France"]},{"name":"International Institute of Biomechanics and Occupational Ergonomics","place":["Hy\u00e8res, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julien","family":"Jacquier-Bret","sequence":"additional","affiliation":[{"name":"University of Toulon","place":["Toulon, France"]},{"name":"International Institute of Biomechanics and Occupational Ergonomics","place":["Hy\u00e8res, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.apergo.2019.05.004","article-title":"RGB-D ergonomic assessment system of adopted working postures","volume":"80","author":"Abobak","year":"2019","journal-title":"Appl. Ergon."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1038\/s41467-020-20655-6","article-title":"Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning","volume":"12","author":"Abrol","year":"2021","journal-title":"Nat. Commun."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"796","DOI":"10.3390\/app11020796","article-title":"Impact of dataset size on classification performance: an empirical evaluation in the medical domain","volume":"11","author":"Althnian","year":"2021","journal-title":"Appl. Sci."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1093\/biomet\/43.3-4.461","article-title":"On estimating binomial response relations","volume":"43","author":"Anscombe","year":"1956","journal-title":"Biometrika"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"04020077","DOI":"10.1061\/(ASCE)CO.1943-7862.0001849","article-title":"Construction activity recognition and ergonomic risk assessment using a wearable insole pressure system","volume":"146","author":"Antwi-Afari","year":"2020","journal-title":"J. Constr. Eng. Manag."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1016\/j.autcon.2018.10.004","article-title":"Wearable insole pressure system for automated detection and classification of awkward working postures in construction workers","volume":"96","author":"Antwi-Afari","year":"2018","journal-title":"Autom. Constr."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"104181","DOI":"10.1016\/j.autcon.2022.104181","article-title":"Deep learning-based networks for automated recognition and classification of awkward working postures in construction using wearable insole sensor data","volume":"136","author":"Antwi-Afari","year":"2022","journal-title":"Autom. Constr."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"126178","DOI":"10.1016\/j.eswa.2024.126178","article-title":"Multi-subject human activities: a survey of recognition and evaluation methods based on a formal framework","volume":"267","author":"Arrotta","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"974","DOI":"10.1136\/jech-2013-203104","article-title":"Meta-analysis of prevalence","volume":"67","author":"Barendregt","year":"2013","journal-title":"J. Epidemiol. Community Health"},{"key":"ref10","volume-title":"Musculoskeletal Disorders and Workplace Factors: a Critical Review of Epidemiologic Evidence for Work-Related Musculoskeletal Disorders of the Neck, Upper Extremity, and Low Back","author":"Bernard","year":"1997"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"105804","DOI":"10.1016\/j.ssci.2022.105804","article-title":"Risk factors for work-related musculoskeletal disorders: a study in the inner regions of Alagoas and Bahia","volume":"153","author":"Bispo","year":"2022","journal-title":"Saf. Sci."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"2360","DOI":"10.3390\/s22062360","article-title":"How validation methodology influences human activity recognition Mobile systems","volume":"22","author":"Bragan\u00e7a","year":"2022","journal-title":"Sensors"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"115263","DOI":"10.1109\/ACCESS.2025.3585773","article-title":"Applications of machine learning in human factors and ergonomics: a comprehensive review of research from the past decade","volume":"13","author":"\u00c7akit","year":"2025","journal-title":"IEEE Access"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e0124414","DOI":"10.1371\/journal.pone.0124414","article-title":"Feature selection for wearable smartphone-based human activity recognition with able bodied, elderly, and stroke patients","volume":"10","author":"Capela","year":"2015","journal-title":"PLoS One"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.gaitpost.2021.06.017","article-title":"Machine-learning models for activity class prediction: a comparative study of feature selection and classification algorithms","volume":"89","author":"Chong","year":"2021","journal-title":"Gait Posture"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2006","DOI":"10.1016\/S0140-6736(20)32340-0","article-title":"Global estimates of the need for rehabilitation based on the global burden of disease study 2019: a systematic analysis for the global burden of disease study 2019","volume":"396","author":"Cieza","year":"2021","journal-title":"Lancet"},{"key":"ref17","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"55","DOI":"10.7326\/M14-0697","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"162","author":"Collins","year":"2015","journal-title":"Ann. Intern. Med."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1557","DOI":"10.3390\/s20061557","article-title":"Measuring biomechanical risk in lifting load tasks through wearable system and machine-learning approach","volume":"20","author":"Conforti","year":"2020","journal-title":"Sensors"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"4750","DOI":"10.3390\/s25154750","article-title":"Lightweight vision transformer for frame-level ergonomic posture classification in industrial workflows","volume":"25","author":"Cruciata","year":"2025","journal-title":"Sensors"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1002\/ajim.20750","article-title":"Risk factors for work-related musculoskeletal disorders: a systematic review of recent longitudinal studies","volume":"53","author":"da Costa","year":"2010","journal-title":"Am. J. Ind. Med."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"107561","DOI":"10.1016\/j.patcog.2020.107561","article-title":"Sensor-based and vision-based human activity recognition: a comprehensive survey","volume":"108","author":"Dang","year":"2020","journal-title":"Pattern Recogn."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1016\/j.jmpt.2017.03.012","article-title":"Prediction effects of personal, psychosocial, and occupational risk factors on low back pain severity using artificial neural networks approach in industrial workers","volume":"40","author":"Darvishi","year":"2017","journal-title":"J. Manip. Physiolog. Ther."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"84","DOI":"10.3390\/bios15020084","article-title":"Biomechanical risk classification in repetitive lifting using multi-sensor electromyography data, revised National Institute for Occupational Safety and Health lifting equation, and deep learning","volume":"15","author":"Davoudi Kakhki","year":"2025","journal-title":"Biosensors"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.3390\/s23041856","article-title":"Wearable sensors and smart devices to monitor rehabilitation parameters and sports performance: an overview","volume":"23","author":"De Fazio","year":"2023","journal-title":"Sensors"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"e25075","DOI":"10.1016\/j.heliyon.2024.e25075","article-title":"A systematic review of work-related musculoskeletal disorders and risk factors among computer users","volume":"10","author":"Demissie","year":"2024","journal-title":"Heliyon"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1289046","DOI":"10.3389\/fmed.2023.1289046","article-title":"Prevalence and risk factors of work-related musculoskeletal disorders among emerging manufacturing workers in Beijing, China","volume":"10","author":"Ding","year":"2023","journal-title":"Front. Med."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"2593","DOI":"10.3390\/s21082593","article-title":"Work-related risk assessment according to the revised NIOSH lifting equation: a preliminary study using a wearable inertial sensor and machine learning","volume":"21","author":"Donisi","year":"2021","journal-title":"Sensors"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.3390\/diagnostics12123048","article-title":"Wearable sensors and artificial intelligence for physical ergonomics: a systematic review of literature","volume":"12","author":"Donisi","year":"2022","journal-title":"Diagnostics"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1136\/bmj.315.7109.629","article-title":"Bias in meta-analysis detected by a simple, graphical test","volume":"315","author":"Egger","year":"1997","journal-title":"BMJ"},{"key":"ref31","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1214\/aoms\/1177729756","article-title":"Transformations related to the angular and the square root","volume":"21","author":"Freeman","year":"1950","journal-title":"Ann. Math. Stat."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"486","DOI":"10.5812\/ijem.3505","article-title":"Normality tests for statistical analysis: a guide for non-statisticians","volume":"10","author":"Ghasemi","year":"2012","journal-title":"Int J Endocrinol Metab."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"4354","DOI":"10.3390\/ijerph17124354","article-title":"Musculoskeletal risks: RULA bibliometric review","volume":"17","author":"G\u00f3mez-Gal\u00e1n","year":"2020","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref35","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1016\/j.jbmt.2024.01.025","article-title":"A systematic review of work-related musculoskeletal disorders among physical therapists and physiotherapists","volume":"38","author":"Gorce","year":"2024","journal-title":"J. Bodyw. Mov. Ther."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3390\/tae1010007","article-title":"Continental umbrella review and meta-analysis of work-related musculoskeletal disorders prevalence among healthcare professionals","volume":"1","author":"Gorce","year":"","journal-title":"Theor. Appl. Ergon."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"6540","DOI":"10.3390\/s25216540","article-title":"Fall detection in elderly people: a systematic review of ambient assisted living and smart home-related technology performance","volume":"25","author":"Gorce","year":"","journal-title":"Sensors"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"298","DOI":"10.3390\/bioengineering13030298","article-title":"Current trends in artificial intelligence for recognizing work postures to prevent work-related musculoskeletal disorders: systematic review and Meta-analysis by occupational activity","volume":"13","author":"Gorce","year":"","journal-title":"Bioengineering"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"1820","DOI":"10.3390\/healthcare14131820","article-title":"Current trends in AI gait analysis for the detection and assessment of Parkinson\u2019s disease severity: systematic review and Meta-analysis of performance using logit transformation","volume":"14","author":"Gorce","year":"","journal-title":"Healthcare"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1186\/s12891-021-04615-9","article-title":"Prevalence and incidence of work-related musculoskeletal disorders in secondary industries of 21st century Europe: a systematic review and meta-analysis","volume":"22","author":"Govaerts","year":"2021","journal-title":"BMC Musculoskelet. Disord."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/j.jclinepi.2010.04.026","article-title":"GRADE guidelines: 1. Introduction-GRADE evidence profiles and summary of findings tables","volume":"64","author":"Guyatt","year":"2011","journal-title":"J. Clin. Epidemiol."},{"key":"ref43","first-page":"133","article-title":"The mean and variance of the moments of w2, when used as a test of homogeneity, when expectations are small","volume":"29","author":"Haldane","year":"1940","journal-title":"Biometrika"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"127","DOI":"10.3390\/bioengineering11020127","article-title":"Compensation method for missing and misidentified skeletons in nursing care action assessment by improving spatial temporal graph convolutional networks","volume":"11","author":"Han","year":"2024","journal-title":"Bioengineering"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"2761","DOI":"10.1177\/0363546513497567","article-title":"How to write a systematic review","volume":"42","author":"Harris","year":"2014","journal-title":"Am. J. Sports Med."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"2042","DOI":"10.1186\/s12889-023-16896-x","article-title":"Prevalence of work-related musculoskeletal disorders among workers in the automobile manufacturing industry in China: a systematic review and meta-analysis","volume":"23","author":"He","year":"2023","journal-title":"BMC Public Health"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"1539","DOI":"10.1002\/sim.1186","article-title":"Quantifying heterogeneity in a meta-analysis","volume":"21","author":"Higgins","year":"2002","journal-title":"Stat. Med."},{"key":"ref48","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/s0003-6870(99)00039-3","article-title":"Rapid entire body assessment (REBA)","volume":"31","author":"Hignett","year":"2000","journal-title":"Appl. Ergon."},{"key":"ref49","doi-asserted-by":"publisher","first-page":"114497","DOI":"10.1109\/access.2023.3324659","article-title":"Ergonomic risk prediction for awkward postures from 3D keypoints using deep learning","volume":"11","author":"Hossain","year":"2023","journal-title":"IEEE Access"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"104176","DOI":"10.1016\/j.apergo.2023.104176","article-title":"Spatial relationship-aware rapid entire body fuzzy assessment method for prevention of work-related musculoskeletal disorders","volume":"115","author":"Huang","year":"2024","journal-title":"Appl. Ergon."},{"key":"ref51","doi-asserted-by":"publisher","first-page":"841","DOI":"10.3390\/ijerph20010841","article-title":"Prevalence of body area work-related musculoskeletal disorders among healthcare professionals: a systematic review","volume":"20","author":"Jacquier-Bret","year":"2023","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"118","DOI":"10.3390\/healthcare12010118","article-title":"Work-related musculoskeletal disorders risk assessment during manual lymphatic drainage with compressive bands among physiotherapists","volume":"12","author":"Jacquier-Bret","year":"2024","journal-title":"Healthcare"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"106970","DOI":"10.1016\/j.ssci.2025.106970","article-title":"Worldwide work-related musculoskeletal disorder prevalence among nurses: systematic review and meta-analysis","volume":"191","author":"Jacquier-Bret","year":"2025","journal-title":"Saf. Sci."},{"key":"ref54","doi-asserted-by":"publisher","first-page":"1356","DOI":"10.1080\/00140139.2024.2306315","article-title":"Improved REBA: deep learning based rapid entire body risk assessment for prevention of musculoskeletal disorders","volume":"67","author":"Jiao","year":"2024","journal-title":"Ergonomics"},{"key":"ref55","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1159\/000362720","article-title":"Sensitivity and false alarm rate of a fall sensor in long-term fall detection in the elderly","volume":"61","author":"Kangas","year":"2014","journal-title":"Gerontology"},{"key":"ref56","doi-asserted-by":"publisher","first-page":"525","DOI":"10.3390\/app14020525","article-title":"Addressing ergonomic challenges in agriculture through AI-enabled posture classification","volume":"14","author":"Kapse","year":"2024","journal-title":"Appl. Sci."},{"key":"ref57","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/0003-6870(77)90164-8","article-title":"Correcting working postures in industry: a practical method for analysis","volume":"8","author":"Karhu","year":"1977","journal-title":"Appl. Ergon."},{"key":"ref58","doi-asserted-by":"publisher","first-page":"52","DOI":"10.5395\/rde.2013.38.1.52","article-title":"Statistical notes for clinical researchers: assessing normal distribution (2) using skewness and kurtosis","volume":"38","author":"Kim","year":"2013","journal-title":"Restor Dent Endod."},{"key":"ref59","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref60","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1080\/15428119791012793","article-title":"Development and evaluation of an observational method for assessing repetition in hand tasks","volume":"58","author":"Latko","year":"1997","journal-title":"Am. Ind. Hyg. Assoc. J."},{"key":"ref61","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"103138","DOI":"10.1016\/j.apergo.2020.103138","article-title":"A novel vision-based real-time method for evaluating postural risk factors associated with musculoskeletal disorders","volume":"87","author":"Li","year":"2020","journal-title":"Appl. Ergonom."},{"key":"ref63","doi-asserted-by":"publisher","first-page":"2454","DOI":"10.1109\/JSEN.2020.3022326","article-title":"Vision and inertial sensing fusion for human action recognition: a review","volume":"21","author":"Majumder","year":"2021","journal-title":"IEEE Sensors J."},{"key":"ref64","doi-asserted-by":"publisher","first-page":"109353","DOI":"10.1016\/j.engappai.2024.109353","article-title":"Proactive prevention of work-related musculoskeletal disorders using a motion capture system and time series machine learning","volume":"138","author":"Matos","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref65","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/0003-6870(93)90080-s","article-title":"RULA: a survey method for the investigation of work-related upper limb disorders","volume":"24","author":"Mc Atamney","year":"1993","journal-title":"Appl. Ergon."},{"key":"ref66","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1002\/jrsm.1411","article-title":"Risk-of-bias VISualization (robvis): an R package and shiny web app for visualizing risk-of-bias assessments","volume":"12","author":"McGuinness","year":"2021","journal-title":"Res. Synth. Methods"},{"key":"ref67","doi-asserted-by":"publisher","first-page":"45425","DOI":"10.1038\/s41598-025-30155-6","article-title":"Musculoskeletal disorders among office workers: prevalence, ergonomic risk factors, and their interrelationships","volume":"15","author":"Mohammadian","year":"2025","journal-title":"Sci. Rep."},{"key":"ref68","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1016\/j.jclinepi.2009.06.005","article-title":"Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement","volume":"62","author":"Moher","year":"2009","journal-title":"PLoS Med."},{"key":"ref69","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1038\/s41597-024-03951-4","article-title":"A benchmark for domain adaptation and generalization in smartphone-based human activity recognition","volume":"11","author":"Napoli","year":"2024","journal-title":"Sci. Data"},{"key":"ref70","doi-asserted-by":"publisher","first-page":"1526","DOI":"10.3390\/s25051526","article-title":"Wearable sensors in industrial ergonomics: enhancing safety and productivity in industry 4.0","volume":"25","author":"Naranjo","year":"2025","journal-title":"Sensors"},{"key":"ref71","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1109\/MIS.2022.3159098","article-title":"Sensitivity of logic learning machine for reliability in safety-critical systems","volume":"37","author":"Narteni","year":"2022","journal-title":"IEEE Intell. Syst."},{"key":"ref72","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1016\/j.aei.2018.08.020","article-title":"Automated ergonomic risk monitoring using body-mounted sensors and machine learning","volume":"38","author":"Nath","year":"2018","journal-title":"Adv. Eng. Inform."},{"key":"ref73","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1613\/jair.1.12125","article-title":"Confident learning: estimating uncertainty in dataset labels","volume":"70","author":"Northcutt","year":"2021","journal-title":"J. Artif. Intell. Res."},{"key":"ref74","volume-title":"Ergonomics \u2013 Identify Problems","year":"2024"},{"key":"ref75","doi-asserted-by":"publisher","first-page":"n71","DOI":"10.1136\/bmj.n71","article-title":"The PRISMA 2020 statement: an updated guideline for reporting systematic reviews","volume":"372","author":"Page","year":"2021","journal-title":"BMJ"},{"key":"ref76","doi-asserted-by":"publisher","first-page":"6479","DOI":"10.3390\/s20226479","article-title":"Accelerometer-based fall detection using machine learning: training and testing on real-world falls","volume":"20","author":"Palmerini","year":"2020","journal-title":"Sensors"},{"key":"ref77","doi-asserted-by":"publisher","first-page":"45","DOI":"10.4103\/0301-4738.37595","article-title":"Understanding and using sensitivity, specificity and predictive values","volume":"56","author":"Parikh","year":"2008","journal-title":"Indian J. Ophthalmol."},{"key":"ref78","doi-asserted-by":"publisher","first-page":"576","DOI":"10.3390\/diagnostics14060576","article-title":"Capability of machine learning algorithms to classify safe and unsafe postures during weight lifting tasks using inertial sensors","volume":"14","author":"Prisco","year":"2024","journal-title":"Diagnostics"},{"key":"ref79","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.jelekin.2003.09.015","article-title":"Work-related musculoskeletal disorders: the epidemiologic evidence and the debate","volume":"14","author":"Punnett","year":"2004","journal-title":"J. Electromyogr. Kinesiol."},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2509.05913","article-title":"A fine-grained attention and geometric correspondence model for musculoskeletal risk classification in athletes using multimodal visual and skeletal features","author":"Rahman","year":"2025","journal-title":"arXiv"},{"key":"ref81","first-page":"21","article-title":"Power comparisons of Shapiro-Wilk, Kolmogorov-Smirnov, Lilliefors and Anderson-Darling tests","volume":"2","author":"Razali","year":"2011","journal-title":"J Stat Model Anal."},{"key":"ref82","doi-asserted-by":"publisher","first-page":"245","DOI":"10.3390\/info10080245","article-title":"Human activity recognition for production and logistics\u2014a systematic literature review","volume":"10","author":"Reining","year":"2019","journal-title":"Information"},{"key":"ref83","doi-asserted-by":"publisher","first-page":"1644","DOI":"10.3390\/s19071644","article-title":"Accelerometer-based human fall detection using convolutional neural networks","volume":"19","author":"Santos","year":"2019","journal-title":"Sensors"},{"key":"ref84","doi-asserted-by":"publisher","first-page":"1335174","DOI":"10.3389\/fmolb.2024.1335174","article-title":"Use of logit transformation within statistical analyses of experimental results obtained as proportions: example of method validation experiments and EQA in flow cytometry","volume":"11","author":"Seiffert","year":"2024","journal-title":"Front. Mol. Biosci."},{"key":"ref85","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.3390\/electronics12071509","article-title":"Machine learning and AI technologies for smart wearables","volume":"12","author":"Seng","year":"2023","journal-title":"Electronics"},{"key":"ref86","doi-asserted-by":"crossref","first-page":"109556","DOI":"10.1016\/j.cie.2023.109556","article-title":"Ergonomic risk level prediction framework for multiclass imbalanced data","volume":"184","author":"Senjaya","year":"2023","journal-title":"Comput. Ind. Eng."},{"key":"ref87","doi-asserted-by":"publisher","first-page":"103725","DOI":"10.1016\/j.autcon.2021.103725","article-title":"Automated postural ergonomic risk assessment using vision-based posture classification","volume":"128","author":"Seo","year":"2021","journal-title":"Autom. Constr."},{"key":"ref88","doi-asserted-by":"publisher","first-page":"214","DOI":"10.61882\/johe.14.3.214","article-title":"Risk management of work-related musculoskeletal disorders using an artificial intelligence approach (narrative review)","volume":"14","author":"Shakerian","year":"2025","journal-title":"J. Occup. Health Epidemiol."},{"key":"ref89","doi-asserted-by":"publisher","first-page":"591","DOI":"10.2307\/2333709","article-title":"An analysis of variance test for normality (complete samples)","volume":"52","author":"Shapiro","year":"1955","journal-title":"Biometrika"},{"key":"ref90","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1061\/(ASCE)CO.1943-7862.0001843","article-title":"Automated methods for activity recognition of construction workers and equipment: state-of-the-art review","volume":"1","author":"Sherafat","year":"2020","journal-title":"J. Constr. Eng. Manag."},{"key":"ref91","doi-asserted-by":"publisher","first-page":"8135","DOI":"10.1109\/TNNLS.2022.3152527","article-title":"Learning from Noisy labels with deep neural networks: a survey","volume":"34","author":"Song","year":"2023","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"ref92","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.jsr.2023.08.008","article-title":"Machine learning approach to determine the decision rules in ergonomic assessment of working posture in sewing machine operators","volume":"87","author":"Su","year":"2023","journal-title":"J. Saf. Res."},{"key":"ref93","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.ergon.2015.09.012","article-title":"Applying the K-nearest neighbor technique to the classification of workers according to their risk of suffering musculoskeletal disorders","volume":"52","author":"Su\u00e1rez S\u00e1nchez","year":"2016","journal-title":"Int. J. Ind. Ergon."},{"key":"ref94","doi-asserted-by":"publisher","first-page":"1399552","DOI":"10.3389\/fpubh.2024.1399552","article-title":"Musculoskeletal disorders among teachers: a systematic review and meta-analysis","volume":"12","author":"Tahernejad","year":"2024","journal-title":"Front. Public Health"},{"key":"ref95","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1136\/bmj.309.6965.1351","article-title":"Why sources of heterogeneity in meta-analysis should be investigated","volume":"309","author":"Thompson","year":"1994","journal-title":"BMJ"},{"key":"ref96","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1186\/s12891-025-08873-9","article-title":"Work-related musculoskeletal disorders and associated factors among hospital sanitary workers in public hospitals of eastern Ethiopia","volume":"26","author":"Tolera","year":"2025","journal-title":"BMC Musculoskelet. Disord."},{"key":"ref97","year":"2020"},{"key":"ref98","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1002\/jrsm.11","article-title":"Outlier and influence diagnostics for meta-analysis","volume":"1","author":"Viechtbauer","year":"2010","journal-title":"Res. Synth. Methods"},{"key":"ref99","doi-asserted-by":"publisher","first-page":"103556","DOI":"10.1016\/j.apergo.2021.103556","article-title":"Prediction of slaughterhouse workers\u2019 RULA scores and knife edge using low-cost inertial measurement sensor units and machine learning algorithms","volume":"98","author":"Villalobos","year":"2022","journal-title":"Appl. Ergon."},{"key":"ref100","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.patrec.2018.02.010","article-title":"Deep learning for sensor-based activity recognition: a survey","volume":"119","author":"Wang","year":"2019","journal-title":"Pattern Recogn. Lett."},{"key":"ref101","doi-asserted-by":"publisher","first-page":"103921","DOI":"10.1016\/j.autcon.2021.103921","article-title":"Risk assessment for musculoskeletal disorders based on the characteristics of work posture","volume":"131","author":"Wang","year":"2021","journal-title":"Autom. Constr."},{"key":"ref102","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1080\/00140139308967940","article-title":"Revised NIOSH equation for the design and evaluation of manual lifting tasks","volume":"36","author":"Waters","year":"1993","journal-title":"Ergonomics"},{"key":"ref103","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2307\/2334448","article-title":"Probability plotting methods for the analysis of data","volume":"55","author":"Wilk","year":"1968","journal-title":"Biometrika"},{"key":"ref104","doi-asserted-by":"publisher","first-page":"51","DOI":"10.7326\/M18-1376","article-title":"PROBAST: a tool to assess the risk of bias and applicability of prediction model studies","volume":"170","author":"Wolff","year":"2019","journal-title":"Ann. Intern. Med."},{"key":"ref105","doi-asserted-by":"publisher","first-page":"04023138","DOI":"10.1061\/JCEMD4.COENG-13795","article-title":"A feature-level fusion-based multimodal analysis of recognition and classification of awkward working postures in construction","volume":"149","author":"Xiahou","year":"2023","journal-title":"J. Constr. Eng. Manag."},{"key":"ref106","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.eswa.2019.04.057","article-title":"Survey on wearable sensor modality-centred human activity recognition in healthcare","volume":"137","author":"Yan","year":"2019","journal-title":"Expert Syst. Appl."},{"key":"ref107","doi-asserted-by":"publisher","first-page":"180481","DOI":"10.1109\/ACCESS.2024.3509447","article-title":"A systematic review: advancing ergonomic posture risk assessment through the integration of computer vision and machine learning techniques","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"ref108","doi-asserted-by":"publisher","first-page":"942","DOI":"10.3390\/s23020942","article-title":"Predicting wrist posture during 23","volume":"2","author":"Young","year":"2023","journal-title":"Sensors"},{"key":"ref109","doi-asserted-by":"publisher","first-page":"103538","DOI":"10.1016\/j.autcon.2020.103538","article-title":"Posture-related data collection methods for construction workers: a review","volume":"124","author":"Yu","year":"2021","journal-title":"Autom. Constr."},{"key":"ref110","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40747-024-01660-4","article-title":"Fall detection method based on spatio-temporal coordinate attention for high-resolution networks","volume":"11","author":"Zhang","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"ref111","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.autcon.2018.05.033","article-title":"Ergonomic posture recognition using 3D view-invariant features from single ordinary camera","volume":"94","author":"Zhang","year":"2018","journal-title":"Autom. Constr."},{"key":"ref112","doi-asserted-by":"publisher","first-page":"101177","DOI":"10.1016\/j.aei.2020.101177","article-title":"Convolutional long short-term memory model for recognizing construction workers\u2019 postures from wearable inertial measurement units","volume":"46","author":"Zhao","year":"2020","journal-title":"Adv. Eng. Inform."},{"key":"ref113","doi-asserted-by":"publisher","first-page":"101374","DOI":"10.1016\/j.aei.2021.101374","article-title":"Applying incremental deep neural networks-based posture recognition model for ergonomics risk assessment in construction","volume":"50","author":"Zhao","year":"2021","journal-title":"Adv. Eng. Inform."},{"key":"ref114","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1109\/THMS.2022.3148339","article-title":"A computer vision approach for estimating lifting load contributors to injury risk","volume":"52","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Hum.-Mach. Syst."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1933096\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T06:42:13Z","timestamp":1791355333000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1933096\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,7]]},"references-count":114,"alternative-id":["10.3389\/frai.2026.1933096"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1933096","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,7]]},"article-number":"1933096"}}