{"id":"W2053691787","doi":"10.1016/j.joca.2008.02.021","title":"Comparative evaluation of three semi-quantitative radiographic grading techniques for knee osteoarthritis in terms of validity and reproducibility in 1759 X-rays: 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":135,"is_retracted":false,"has_abstract":false,"ca_institutions":"Women's College Hospital; University of Toronto","funders":"NIH Clinical Center; National Institute of Arthritis and Musculoskeletal and Skin Diseases; Medical Research Council; Canadian Institutes of Health Research; U.S. Public Health Service","keywords":"Osteoarthritis; Categorical variable; Kappa; Medicine; Reproducibility; Cohen's kappa; Cohort; Grading (engineering); Radiography; Reliability (semiconductor); Intraclass correlation; Physical therapy; Nuclear medicine; Orthodontics; Mathematics; Statistics; Surgery; Internal medicine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07563595,0.001255115,0.001578865,0.006005975,0.001034173,0.001975305,0.002544345,0.001721206,0.0008368727],"category_scores_gemma":[0.1251605,0.0009523178,0.003283834,0.003416849,0.002084995,0.001924402,0.002130534,0.0009196014,0.0004130181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001497621,"about_ca_system_score_gemma":0.001297847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003792794,"about_ca_topic_score_gemma":0.007012413,"domain_scores_codex":[0.9404355,0.02794624,0.01011221,0.00350229,0.01714092,0.0008627168],"domain_scores_gemma":[0.7658666,0.152414,0.02441048,0.01036455,0.04537951,0.001564942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.02110947,0.001402345,0.7775329,0.002418007,0.009629996,0.0001392384,0.008418194,0.00299878,0.01029839,0.0009272508,0.001939472,0.163186],"study_design_scores_gemma":[0.001580187,0.006172985,0.9703157,0.0003831459,0.002762554,0.0005476963,0.002091146,0.009127924,0.003892035,0.0007410256,0.002094238,0.0002914573],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9700799,0.006025407,0.01854374,0.0002319461,0.000302205,0.0008915822,0.001051371,0.0001441736,0.002729672],"genre_scores_gemma":[0.9800282,0.001147357,0.01644908,0.00008816842,0.00008889417,0.0005388928,0.001068669,0.00007688426,0.000513958],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07563595,"threshold_uncertainty_score":0.4000059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06035707866198371,"score_gpt":0.3121660901179353,"score_spread":0.2518090114559516,"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."}}