{"id":"W2053630609","doi":"10.1097/ede.0b013e318207fc5c","title":"Adjusting for Differential-verification Bias in Diagnostic-accuracy Studies","year":2011,"lang":"en","type":"article","venue":"Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Test (biology); Computer science; Statistics; Bayesian probability; Reference values; Population; Data mining; Medicine; 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":[0.01959785,0.000143165,0.0006042516,0.0001558331,0.0001209699,0.0000107699,0.0005035346,0.0001011618,0.000279417],"category_scores_gemma":[0.5515234,0.00009557728,0.0001311069,0.0002523816,0.0001749181,0.0001445316,0.0001087786,0.0001271987,0.0001292896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005962525,"about_ca_system_score_gemma":0.00002640418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009449418,"about_ca_topic_score_gemma":0.0001486323,"domain_scores_codex":[0.9955817,0.001502382,0.001655339,0.0006008938,0.0002665063,0.0003931802],"domain_scores_gemma":[0.8709549,0.1269073,0.0008348433,0.0007697102,0.0004430387,0.00009024332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009680018,0.0002284795,0.8461317,0.0000371163,0.00004315366,0.00000204509,0.00297302,0.0002010463,0.0004105386,0.02328498,0.01758527,0.1090058],"study_design_scores_gemma":[0.0004092018,0.0001683544,0.6486715,0.00004745088,0.00001798596,0.000001024056,0.001715392,0.001346187,0.0004671252,0.3367754,0.01022199,0.0001583443],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9389172,0.001669553,0.0518718,0.004084632,0.00161851,0.0008651493,0.000009959593,0.00003886551,0.0009243716],"genre_scores_gemma":[0.9893702,0.0003911816,0.008990753,0.000678568,0.0001500379,0.00024794,0.000004986286,0.000006233373,0.0001601124],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5319256,"threshold_uncertainty_score":0.6792263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8295205122545626,"score_gpt":0.5205216194963798,"score_spread":0.3089988927581828,"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."}}