{"id":"W4401880856","doi":"10.2196/55476","title":"Recognition of Forward Head Posture Through 3D Human Pose Estimation With a Graph Convolutional Network: Development and Feasibility Study","year":2024,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Musculoskeletal pain and rehabilitation","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministry of Trade, Industry and Energy; Korea Medical Device Development Fund","keywords":"Computer science; Body posture; Graph; Key (lock); Pose; Artificial intelligence; Computer vision; Physical medicine and rehabilitation; Machine learning; Human–computer interaction; Medicine; Theoretical computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005658792,0.0008207776,0.0004429369,0.0004926221,0.0001338667,0.0003455362,0.001160809,0.0007841902,0.002242864],"category_scores_gemma":[0.001058915,0.0002861619,0.0004375734,0.0003642362,0.0002239613,0.000622393,0.0004464464,0.0004613844,0.0006628791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005657287,"about_ca_system_score_gemma":0.001177945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01865319,"about_ca_topic_score_gemma":0.01451323,"domain_scores_codex":[0.9997717,0.00003761613,0.000008226605,0.00006786037,0.00007120175,0.00004350874],"domain_scores_gemma":[0.9995907,0.0001344427,0.00002740119,0.00004999261,0.0001582729,0.00003925387],"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":[0.0008802116,0.0009959375,0.01676266,0.0003603727,0.000324415,0.0004765202,0.0000875335,0.2137341,0.07569968,0.001286779,0.005041956,0.6843498],"study_design_scores_gemma":[0.00002042845,0.0003440775,0.003713858,0.0000126374,0.00004182007,0.0001005371,0.00001540399,0.9860178,0.008806565,0.000226366,0.0006866308,0.00001398853],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4460353,0.001265194,0.5421219,0.0005622592,0.0002388677,0.0005318992,0.0007156468,0.00405667,0.004472303],"genre_scores_gemma":[0.8566189,0.0005329751,0.1386164,0.000145653,0.00003429926,0.0002434069,0.001122504,0.0000563057,0.002629553],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01865319,"threshold_uncertainty_score":0.03708923,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0885796709463452,"score_gpt":0.444288255643661,"score_spread":0.3557085846973158,"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."}}