{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00294359,0.000250826,0.00100335,0.0002929473,0.00009518721,0.000007889353,0.00007827206,0.0001504247,0.000008177783],"category_scores_gemma":[0.0005728585,0.0002135811,0.0002039023,0.0005074134,0.0005781721,0.0002235065,0.00006790511,0.0001785615,1.108287e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005134347,"about_ca_system_score_gemma":0.0001073701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007172462,"about_ca_topic_score_gemma":0.001837387,"domain_scores_codex":[0.9971075,0.0003168962,0.001005129,0.0007831939,0.0005164457,0.0002708442],"domain_scores_gemma":[0.9980106,0.0002387358,0.0005336644,0.0008154965,0.0003268524,0.00007461233],"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":[0.0006065711,0.0003447263,0.4945472,0.0003046518,0.00001610338,0.00009021804,0.003838329,0.000004226744,0.4600806,0.000306677,0.00001348335,0.03984715],"study_design_scores_gemma":[0.01175395,0.01194019,0.1545837,0.002353598,0.0003081268,0.0007497834,0.001161593,0.00007087902,0.8110221,0.005660192,0.00007046415,0.0003253819],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917369,0.003664231,0.00002172956,0.00006262056,0.0001271976,0.003478669,0.0001420112,0.00001736232,0.0007492314],"genre_scores_gemma":[0.9984769,0.0002382587,0.000812534,0.00001278801,0.00002411625,0.0003204909,0.00005270329,0.00002041253,0.0000418606],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3509415,"threshold_uncertainty_score":0.8709582,"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."}}