{"id":"W2105385152","doi":"10.1002/sim.5676","title":"Comparing diagnostic tests: trials in people with discordant test results","year":2012,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Women's Health Research Institute","funders":"National Institutes of Health; Universiteit van Amsterdam; National Institute for Health and Care Research","keywords":"Statistics; Test (biology); Gold standard (test); Statistical hypothesis testing; Computer science; Medicine; Econometrics; Mathematics","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":["metaresearch"],"category_scores_codex":[0.3134172,0.002324735,0.007879863,0.004662482,0.001054425,0.006023927,0.004303317,0.01021514,0.005702175],"category_scores_gemma":[0.6904366,0.001372198,0.00640151,0.00469408,0.006992099,0.00963651,0.004707074,0.005073963,0.00113777],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002600948,"about_ca_system_score_gemma":0.003880645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002889247,"about_ca_topic_score_gemma":0.0002212041,"domain_scores_codex":[0.3872872,0.5572218,0.02894884,0.00972114,0.01601114,0.000809915],"domain_scores_gemma":[0.2883326,0.6501848,0.03172173,0.02294791,0.005231275,0.001581775],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.05556094,0.001442747,0.01464628,0.06922781,0.0440849,0.001287124,0.002974962,0.01597894,0.002461112,0.3544712,0.01324476,0.4246192],"study_design_scores_gemma":[0.03462104,0.01577806,0.005806413,0.02785411,0.02045895,0.002711385,0.0008652907,0.0500699,0.006624235,0.7821897,0.05239617,0.000624693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05268004,0.08198036,0.7960043,0.01336378,0.008108266,0.03228301,0.001517787,0.00087446,0.01318795],"genre_scores_gemma":[0.4241098,0.01469939,0.4907241,0.008703706,0.002215796,0.05660402,0.0008215012,0.0002875288,0.001834192],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6865828,"threshold_uncertainty_score":0.8466788,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5460293344991152,"score_gpt":0.5771006422312617,"score_spread":0.0310713077321465,"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."}}