{"id":"W4409198662","doi":"10.1016/j.ergon.2025.103734","title":"Validation of markerless vision-based motion capture for ergonomics risk assessment","year":2025,"lang":"en","type":"article","venue":"International Journal of Industrial Ergonomics","topic":"Ergonomics and Musculoskeletal Disorders","field":"Psychology","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Glenrose Rehabilitation Hospital; Public Works and Government Services Canada; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Motion capture; Human factors and ergonomics; Motion (physics); Computer vision; Artificial intelligence; Computer science; Poison control; Physical medicine and rehabilitation; Engineering; Medicine; Medical emergency","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001169029,0.0001898321,0.000381012,0.0005571853,0.00005924976,0.00007776578,0.000611775,0.0003127952,0.0001340673],"category_scores_gemma":[0.0003621157,0.0001906642,0.0004551101,0.0001249939,0.00007670224,0.0002005197,0.0000529906,0.0004260904,0.000003192138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004595863,"about_ca_system_score_gemma":0.0006380606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001711438,"about_ca_topic_score_gemma":0.00002247039,"domain_scores_codex":[0.9980496,0.000148234,0.001190941,0.0002325067,0.0001957366,0.0001829577],"domain_scores_gemma":[0.9967737,0.0005442721,0.00158512,0.0002205937,0.0008044255,0.00007190692],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.03240206,0.002995319,0.1358971,0.0000719202,0.005400405,0.00001127171,0.0005564658,0.1766294,0.001947704,0.1101782,0.03804106,0.4958691],"study_design_scores_gemma":[0.1273488,0.00331601,0.5746214,0.002273574,0.003175105,0.00005685051,0.007636179,0.07494732,0.01489543,0.04095946,0.1475873,0.003182516],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8986437,0.00008650812,0.08526014,0.001182765,0.01130225,0.0004078035,0.00027773,0.00001027008,0.002828792],"genre_scores_gemma":[0.9953073,0.00005697539,0.003521843,0.0001833651,0.0006093746,0.00001871428,0.0000947683,0.00002341655,0.0001842173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4926866,"threshold_uncertainty_score":0.7775061,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02076572508009243,"score_gpt":0.3460149118525311,"score_spread":0.3252491867724387,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}