{"id":"W2111584093","doi":"10.1002/sim.4444","title":"Effect of dependent errors in the assessment of diagnostic or screening test accuracy when the reference standard is imperfect","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Hemodynamic Monitoring and Therapy","field":"Medicine","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"National Medical Research Council; National Health and Medical Research Council","keywords":"Computer science; Statistics; Imperfect; Test (biology); Diagnostic accuracy; 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":[0.004441423,0.0001769303,0.0005539405,0.0001200787,0.00004467225,0.000004022149,0.0002298326,0.00006409952,0.0001951181],"category_scores_gemma":[0.01384185,0.00007846056,0.00002528363,0.0002445962,0.0002427774,0.0000366458,0.00003692007,0.0005130132,0.00000106368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009578325,"about_ca_system_score_gemma":0.0001169273,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007190047,"about_ca_topic_score_gemma":0.0001159937,"domain_scores_codex":[0.9977454,0.0004291808,0.0005721089,0.0001547703,0.0007894041,0.0003091372],"domain_scores_gemma":[0.9716416,0.02753349,0.0002168724,0.0004452579,0.00008972498,0.00007303814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005157626,0.0002189328,0.8902133,0.0006868098,0.00007783807,0.00008102994,0.008182378,0.0000240682,0.001161543,0.001082104,0.00142971,0.09632658],"study_design_scores_gemma":[0.01119774,0.01239418,0.9563999,0.004776093,0.0005651599,0.0001028194,0.00406638,0.003693912,0.003724933,0.0009240981,0.001861212,0.0002936392],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9649546,0.0009283773,0.0293925,0.00151581,0.0003995179,0.001321389,0.0002521614,0.00001393624,0.001221679],"genre_scores_gemma":[0.994568,0.000695885,0.004253538,0.0001679607,0.0001692799,0.00005185703,0.00002888081,0.00001736968,0.0000472363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09603294,"threshold_uncertainty_score":0.994465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03475759916229025,"score_gpt":0.4109700804001137,"score_spread":0.3762124812378234,"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."}}