{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0705746,0.001283856,0.0009582388,0.002007433,0.0005653188,0.002365684,0.001826254,0.002378998,0.001805284],"category_scores_gemma":[0.3487698,0.0009111636,0.00169427,0.00150265,0.004048406,0.002810621,0.004131994,0.001989428,0.0004354058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001700714,"about_ca_system_score_gemma":0.001144543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003732412,"about_ca_topic_score_gemma":0.002835161,"domain_scores_codex":[0.9481884,0.03569598,0.002821686,0.004056488,0.008386401,0.0008512333],"domain_scores_gemma":[0.4844711,0.4477851,0.02421859,0.03458499,0.008109681,0.0008304535],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002321381,0.0005114478,0.3410267,0.000758682,0.002473596,0.002328135,0.001870355,0.4174204,0.009184026,0.09509277,0.002334537,0.124678],"study_design_scores_gemma":[0.0003744899,0.001455385,0.2258105,0.0008131862,0.001520835,0.003339381,0.0004827559,0.5971673,0.0308416,0.1335194,0.004186102,0.0004890766],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5277974,0.004438103,0.4435955,0.003065135,0.0002772286,0.0005331469,0.0007969809,0.000769363,0.01872724],"genre_scores_gemma":[0.9510181,0.00037513,0.046699,0.0003650345,0.00004583921,0.0001019513,0.0001451835,0.0001102011,0.001139602],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9294254,"threshold_uncertainty_score":0.3732386,"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."}}