{"id":"W2178694734","doi":"10.1002/sim.6803","title":"Bias due to composite reference standards in diagnostic accuracy studies","year":2015,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Statistics; Computer science; Data mining; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"category_scores_codex":[0.3675564,0.002145658,0.004481113,0.006986781,0.001220841,0.008321824,0.006108151,0.005119082,0.003785102],"category_scores_gemma":[0.6510559,0.001693202,0.004238233,0.008336945,0.01162197,0.008457511,0.007573344,0.007863456,0.001345826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005210601,"about_ca_system_score_gemma":0.004673799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002830513,"about_ca_topic_score_gemma":0.0015885,"domain_scores_codex":[0.5832873,0.3407099,0.01807496,0.01913789,0.03703783,0.001752183],"domain_scores_gemma":[0.2912189,0.6240479,0.03149405,0.03852816,0.0139655,0.0007455833],"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":[0.0004685787,0.00005332281,0.0112525,0.002512561,0.00189206,0.0004167345,0.001254322,0.03468701,0.0004907755,0.8114863,0.005549075,0.1299367],"study_design_scores_gemma":[0.0001600987,0.000260212,0.002553917,0.001150512,0.0004667914,0.0005518842,0.0001186773,0.05598985,0.001260871,0.9265573,0.01081368,0.000116219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00538046,0.01206796,0.9714231,0.005064161,0.001021831,0.0004143949,0.0003005372,0.0003294343,0.003998045],"genre_scores_gemma":[0.3353403,0.01264792,0.6368372,0.005122907,0.002783213,0.0032002,0.0006947012,0.0004013797,0.002972065],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6324437,"threshold_uncertainty_score":0.7799156,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7570256031050993,"score_gpt":0.6499421358043234,"score_spread":0.1070834673007759,"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."}}