{"id":"W2157472158","doi":"10.1136/bmj.d4770","title":"Verification problems in diagnostic accuracy studies: consequences and solutions","year":2011,"lang":"en","type":"article","venue":"BMJ","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"Royal Victoria Hospital","funders":"","keywords":"Receiver operating characteristic; Diagnostic accuracy; Diagnostic odds ratio; Gold standard (test); Statistics; Test (biology); Outcome (game theory); Diagnostic test; Sensitivity (control systems); Nominal level; Computer science; Medicine; Mathematics; Confidence interval; Radiology; Pediatrics","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":[0.4897068,0.003623682,0.007959833,0.01034162,0.005468862,0.01192358,0.009647256,0.02096142,0.003909012],"category_scores_gemma":[0.7714143,0.003859446,0.003679587,0.01433257,0.04329705,0.02360406,0.01629302,0.0207291,0.001015973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01519812,"about_ca_system_score_gemma":0.01070407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007379435,"about_ca_topic_score_gemma":0.003606938,"domain_scores_codex":[0.3830962,0.4587951,0.04834016,0.03943928,0.0672515,0.003077638],"domain_scores_gemma":[0.06050418,0.8689465,0.02446388,0.02276286,0.02218889,0.001133708],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007042854,0.0001767972,0.02159733,0.005446044,0.0016418,0.002483955,0.004598788,0.008452316,0.0003578675,0.6709399,0.05046598,0.233135],"study_design_scores_gemma":[0.0002758585,0.0001042457,0.002035452,0.003947999,0.0001940333,0.00170106,0.0008310424,0.01154769,0.0003786711,0.9589431,0.01978328,0.000257538],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.00953522,0.09748705,0.4326339,0.4408401,0.006709813,0.001078479,0.0007241279,0.0007461917,0.01024508],"genre_scores_gemma":[0.3046491,0.04461392,0.5299466,0.08256033,0.03000173,0.004036599,0.0005449944,0.0006712393,0.002975539],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5102932,"threshold_uncertainty_score":0.6292825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9023707166369184,"score_gpt":0.5668338398689057,"score_spread":0.3355368767680127,"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."}}