{"id":"W2465767413","doi":"10.1093/ecco-jcc/jjw120","title":"Effect of Standardised Scoring Conventions on Inter-rater Reliability in the Endoscopic Evaluation of Crohn’s Disease","year":2016,"lang":"en","type":"article","venue":"Journal of Crohn s and Colitis","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital; Robarts Clinical Trials; Western University","funders":"","keywords":"Inter-rater reliability; Crohn's disease; Reliability (semiconductor); Disease; Medicine; Physical therapy; Internal medicine; Statistics; Mathematics; Physics; Rating scale","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":[0.001558289,0.00007345939,0.0001400559,0.00004651873,0.00002462656,0.000010593,0.00009300287,0.00003402595,0.0000378084],"category_scores_gemma":[0.0004574187,0.00004105096,0.0001113209,0.00002885754,0.000104316,0.00001004231,0.00002338596,0.00004577249,3.691981e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002933357,"about_ca_system_score_gemma":0.0001542972,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004141455,"about_ca_topic_score_gemma":0.0000104769,"domain_scores_codex":[0.9987446,0.0004827185,0.0003314991,0.00009362215,0.0002575465,0.00009000771],"domain_scores_gemma":[0.9992065,0.00006115314,0.0002202101,0.0001854266,0.0002664537,0.00006023413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.08677709,0.0009718559,0.7730911,0.001606776,0.0004058109,0.0005863069,0.000830362,0.0002718375,0.04227523,0.001137144,0.001337054,0.09070947],"study_design_scores_gemma":[0.002089413,0.0004706992,0.9791998,0.0002778862,0.00009312479,0.00000316227,0.00002863684,0.00001162388,0.01723962,0.0003563211,0.0001885878,0.00004111159],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990659,0.0001988715,0.00008674558,0.0001014294,0.00009780317,0.0002421657,0.00005527652,6.088872e-7,0.0001512133],"genre_scores_gemma":[0.9998094,0.00005819788,0.000007188673,0.00002407004,0.00006026942,0.00001416054,0.00000200077,0.0000047819,0.00001997066],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2061087,"threshold_uncertainty_score":0.167401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009860362704388687,"score_gpt":0.289036159677372,"score_spread":0.2791757969729833,"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."}}