{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01374165,0.0003120929,0.001562236,0.0003121503,0.00003852756,0.00001877079,0.0004006384,0.0001311537,0.000172132],"category_scores_gemma":[0.8869722,0.0002420879,0.00002207597,0.000736583,0.0004676241,0.00005101199,0.0002454135,0.0006196013,0.00004655946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004985101,"about_ca_system_score_gemma":0.0002366773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001708585,"about_ca_topic_score_gemma":0.0007137581,"domain_scores_codex":[0.9942161,0.001399827,0.002015819,0.0005163001,0.001333681,0.0005182386],"domain_scores_gemma":[0.7136772,0.2842504,0.0003172001,0.0005464093,0.0008174087,0.0003913722],"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":[0.0007405202,0.0004797105,0.008545923,0.0007835199,0.0001266084,0.002725663,0.00924453,0.00008659883,0.00005597225,0.6948063,0.2154767,0.06692795],"study_design_scores_gemma":[0.003050093,0.0007318479,0.004153569,0.001465895,0.00007277916,0.00001096159,0.001426109,0.0001694743,0.00004359719,0.9858708,0.002730809,0.0002740715],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03802528,0.001145939,0.9425698,0.004766339,0.003086369,0.002131606,0.002361905,0.0001387176,0.005774039],"genre_scores_gemma":[0.06618645,0.0003964324,0.9319358,0.0008436503,0.0003338004,0.0001167428,0.00001303269,0.00004618796,0.0001279071],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8732306,"threshold_uncertainty_score":0.9872059,"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."}}