{"id":"W4412463372","doi":"10.1055/s-0045-1810260","title":"Novel, Markerless, Kinematic Tool Utilising a Deep Neural Network for Analysis of Joint Range of Motion and Lameness In Dogs","year":2025,"lang":"en","type":"article","venue":"Veterinary and Comparative Orthopaedics and Traumatology","topic":"Veterinary Orthopedics and Neurology","field":"Veterinary","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medicine; Lameness; Kinematics; Range of motion; Joint (building); Range (aeronautics); Motion analysis; Physical medicine and rehabilitation; Motion (physics); Artificial intelligence; Physical therapy; Surgery; Computer science; Engineering; Structural engineering","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0004300557,0.0002492669,0.001188557,0.0004856756,0.0001096334,0.00001626866,0.00007964045,0.0001438103,0.0000118629],"category_scores_gemma":[0.00002536142,0.0002355652,0.0001345852,0.0005548967,0.0003874893,0.0001103894,0.0001646061,0.0001509651,6.164155e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006431858,"about_ca_system_score_gemma":0.00001461253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006070264,"about_ca_topic_score_gemma":0.0001200714,"domain_scores_codex":[0.9981843,0.0002446244,0.0007629792,0.0004431026,0.00007979736,0.0002851954],"domain_scores_gemma":[0.9989373,0.0004639225,0.0002798364,0.0001956592,0.00007164912,0.00005164447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01342579,0.0009353681,0.8890498,0.003531293,0.002119077,0.0003994406,0.003212901,0.001399295,0.01209821,0.04790618,0.00002134664,0.02590125],"study_design_scores_gemma":[0.002658719,0.002928152,0.7878029,0.0001165334,0.0005855233,0.0007837057,0.0003057661,0.2035744,0.00001183009,0.0007976688,0.0001938592,0.0002409019],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894376,0.001831836,0.007768213,0.0001441791,0.0001385741,0.0004642081,0.00005762642,0.00001315667,0.0001445991],"genre_scores_gemma":[0.9981259,0.0002588341,0.001402003,0.00008443685,0.00001238163,0.00007234948,0.00002917164,0.000009140575,0.000005750897],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2021752,"threshold_uncertainty_score":0.9606069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1339743121764988,"score_gpt":0.3509288183636399,"score_spread":0.216954506187141,"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."}}