{"id":"W3156454664","doi":"10.1016/j.jbiomech.2021.110414","title":"Assessment of spatiotemporal gait parameters using a deep learning algorithm-based markerless motion capture system","year":2021,"lang":"en","type":"article","venue":"Journal of Biomechanics","topic":"Balance, Gait, and Falls Prevention","field":"Health Professions","cited_by":167,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gait; Motion capture; Kinematics; Gait analysis; Treadmill; Artificial intelligence; Effect of gait parameters on energetic cost; Motion analysis; Motion (physics); Computer science; Physical medicine and rehabilitation; Computer vision; Medicine; Physical therapy; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003070681,0.0004992225,0.0004194,0.00089738,0.0001681773,0.0004073855,0.0003381707,0.0006474878,0.001127325],"category_scores_gemma":[0.0007240736,0.0001851428,0.0002430898,0.0005256377,0.0001246895,0.0003579381,0.0004603412,0.0002985582,0.0004238019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001916813,"about_ca_system_score_gemma":0.0003975794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003186278,"about_ca_topic_score_gemma":0.00604649,"domain_scores_codex":[0.9997877,0.0000228524,0.00001943418,0.00005958708,0.0000796493,0.00003072635],"domain_scores_gemma":[0.9997287,0.00003774338,0.00003879698,0.0000257737,0.0001444483,0.00002446909],"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":[0.001516939,0.001032282,0.0936339,0.0004778739,0.0003651875,0.0006421463,0.0002083589,0.05281324,0.2168802,0.001015423,0.006247612,0.6251669],"study_design_scores_gemma":[0.00007111528,0.0009720673,0.2035323,0.00007178517,0.0001557858,0.001116869,0.00009318333,0.744465,0.04671051,0.0006005198,0.002115835,0.00009494629],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6543645,0.0005834918,0.3379534,0.0002035539,0.0001420845,0.0002638792,0.002973615,0.001176283,0.002339151],"genre_scores_gemma":[0.9528658,0.0002366643,0.04330098,0.0001118364,0.00002695402,0.0001322564,0.00135855,0.00002655322,0.001940317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003186278,"threshold_uncertainty_score":0.006335497,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03134871610114701,"score_gpt":0.350807794831322,"score_spread":0.3194590787301749,"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."}}