{"id":"W2004500024","doi":"10.1007/s11606-012-2031-7","title":"Chapter 9: Options for Summarizing Medical Test Performance in the Absence of a “Gold Standard”","year":2012,"lang":"en","type":"article","venue":"Journal of General Internal Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Hamilton General Hospital","funders":"Agency for Healthcare Research and Quality; U.S. Department of Health and Human Services","keywords":"Gold standard (test); Test (biology); Medicine; Index (typography); Imperfect; Sensitivity (control systems); Statistics; Computer science; Mathematics; Internal medicine","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01220243,0.0001272996,0.0006531135,0.0001335476,0.00002537397,0.000006933716,0.0005015646,0.00009314797,0.0002918463],"category_scores_gemma":[0.08682265,0.00006615507,0.0001373105,0.000119418,0.0002786312,0.0001140313,0.0000492046,0.0005217342,0.000001124783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000437719,"about_ca_system_score_gemma":0.00004907159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001357251,"about_ca_topic_score_gemma":0.000006950658,"domain_scores_codex":[0.9968369,0.0002271453,0.00163285,0.00008561263,0.000962725,0.0002547777],"domain_scores_gemma":[0.9734318,0.02509158,0.000794995,0.0001784921,0.0003143678,0.0001887676],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.003583492,0.001930192,0.1451612,0.001253284,0.0005418776,0.0001636898,0.005988616,0.00002177418,0.0132407,0.6492342,0.06417985,0.1147011],"study_design_scores_gemma":[0.02059433,0.01792334,0.06451201,0.01605065,0.0008523992,0.00275223,0.001964839,0.007494668,0.009914286,0.8063748,0.05071104,0.0008553774],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5444979,0.001774232,0.4182865,0.01777295,0.007286034,0.0008848381,0.00007448674,0.00001618149,0.009406891],"genre_scores_gemma":[0.6944782,0.0004226532,0.3005889,0.0006568638,0.003461934,0.000008794502,2.592346e-7,0.0000173403,0.0003650057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1571406,"threshold_uncertainty_score":0.9208694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4348802255291279,"score_gpt":0.5528147674902757,"score_spread":0.1179345419611478,"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."}}