{"id":"W1977593131","doi":"10.1016/j.bbmt.2012.05.005","title":"Poor Agreement between Clinician Response Ratings and Calculated Response Measures in Patients with Chronic Graft-versus-Host Disease","year":2012,"lang":"en","type":"article","venue":"Biology of Blood and Marrow Transplantation","topic":"Hematopoietic Stem Cell Transplantation","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute; National Institutes of Health","keywords":"Medicine; Kappa; Host response; Disease; Cohen's kappa; Complete response; Internal medicine; Statistics; Immunology; Immune system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08384794,0.000388614,0.0009832282,0.001479438,0.0005668646,0.001072038,0.0008215659,0.0006211057,0.0007541246],"category_scores_gemma":[0.1860124,0.0003413256,0.0008196642,0.000971802,0.001239955,0.0009976123,0.001860237,0.0006959795,0.0003421476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008392959,"about_ca_system_score_gemma":0.0005849997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001888342,"about_ca_topic_score_gemma":0.002970122,"domain_scores_codex":[0.8142087,0.1368989,0.02075205,0.008509409,0.01779189,0.00183891],"domain_scores_gemma":[0.7627676,0.1748249,0.02584668,0.01035295,0.02480169,0.001406122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002460949,0.0001574114,0.8774738,0.001222307,0.001131748,0.0003562525,0.01182747,0.002860623,0.003696883,0.0007883327,0.00257176,0.09545251],"study_design_scores_gemma":[0.0001687108,0.001992128,0.957495,0.0007589451,0.0003326665,0.001592688,0.007640953,0.01561772,0.005877338,0.002345442,0.006003573,0.0001748638],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.969283,0.001854317,0.02188009,0.000609931,0.0002106179,0.0003294466,0.0003356192,0.0001107245,0.005386261],"genre_scores_gemma":[0.995895,0.0001202559,0.003300329,0.0001776594,0.00002518675,0.00012313,0.0001213076,0.00002076911,0.0002164168],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08384794,"threshold_uncertainty_score":0.4434356,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01776219920482207,"score_gpt":0.2701865054525329,"score_spread":0.2524243062477108,"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."}}