{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1780294,0.002685646,0.003284583,0.0136273,0.002172627,0.009343484,0.007708679,0.005248818,0.01845114],"category_scores_gemma":[0.4899772,0.001688968,0.005047756,0.01521822,0.007706662,0.01254428,0.006204922,0.007281173,0.005551551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003913271,"about_ca_system_score_gemma":0.004250595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00245503,"about_ca_topic_score_gemma":0.003338997,"domain_scores_codex":[0.733751,0.2015757,0.03116259,0.0066405,0.02586798,0.001002287],"domain_scores_gemma":[0.530454,0.4051914,0.01588973,0.01958519,0.02815999,0.0007197552],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006334817,0.00009823312,0.003040374,0.02034257,0.001977274,0.0003174067,0.005184822,0.003283969,0.001159794,0.4023483,0.236216,0.3253978],"study_design_scores_gemma":[0.0002408962,0.0003501754,0.003897212,0.02401511,0.00113167,0.0006731666,0.002328397,0.006550947,0.001908179,0.6077789,0.3507017,0.0004235862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0035305,0.05868002,0.8048216,0.06889506,0.01401415,0.00357879,0.007672932,0.001805283,0.03700164],"genre_scores_gemma":[0.04924183,0.02102519,0.882242,0.01849207,0.006834176,0.009567237,0.003085772,0.0009070907,0.00860462],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8219706,"threshold_uncertainty_score":0.9415208,"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."}}