{"id":"W4250452896","doi":"10.1016/j.joca.2008.06.009","title":"Comparative evaluation of three semi-quantitative radiographic grading techniques for hip osteoarthritis in terms of validity and reproducibility in 1404 radiographs: report of the OARSI-OMERACT Task Force","year":2008,"lang":"en","type":"article","venue":"Osteoarthritis and Cartilage","topic":"Osteoarthritis Treatment and Mechanisms","field":"Medicine","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"Women's College Hospital; University of Toronto","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; Medical Research Council; Canadian Institutes of Health Research; Centers for Disease Control and Prevention; Medical Research Council Canada; Pfizer","keywords":"Osteoarthritis; Medicine; Categorical variable; Kappa; Reproducibility; Intraclass correlation; Radiography; Logistic regression; Physical therapy; Cohort; Construct validity; Confidence interval; Cohen's kappa; Grading (engineering); Reliability (semiconductor); Surgery; Statistics; Internal medicine; Psychometrics; Mathematics; Pathology","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":[0.002835245,0.0002775899,0.001099877,0.0004334767,0.0001055762,0.000008725562,0.00009558076,0.000161417,0.000007340235],"category_scores_gemma":[0.0005008516,0.0002377607,0.0002742347,0.0007483188,0.00071664,0.0002390132,0.00006333869,0.0001884361,7.735839e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004904959,"about_ca_system_score_gemma":0.0001007481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009768066,"about_ca_topic_score_gemma":0.001508696,"domain_scores_codex":[0.9968894,0.0003196826,0.001085819,0.00085468,0.0005495741,0.0003008478],"domain_scores_gemma":[0.9978693,0.0002525582,0.0005850069,0.0008738778,0.0003329054,0.00008636358],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006248845,0.0002972196,0.579788,0.0002635914,0.00001631676,0.00007774909,0.002968474,0.000002774715,0.3955443,0.0002395897,0.00001604048,0.02016106],"study_design_scores_gemma":[0.01072429,0.007180295,0.1576283,0.002013167,0.0003072994,0.0008130611,0.0009136217,0.00004696302,0.8145445,0.005476983,0.00004980478,0.0003016984],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9897679,0.005593888,0.00001768743,0.00007276411,0.0001379402,0.003677918,0.0001530506,0.00001945002,0.0005593833],"genre_scores_gemma":[0.9981012,0.0006189363,0.0008047068,0.0000135627,0.00002393138,0.0003321948,0.00005912338,0.00002246711,0.00002384575],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4221597,"threshold_uncertainty_score":0.9695601,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05979089644537103,"score_gpt":0.3127556487770633,"score_spread":0.2529647523316922,"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."}}