{"id":"W1518867746","doi":"10.1108/09526861311297325","title":"A comparison of two diagnostic performance measures","year":2013,"lang":"en","type":"article","venue":"International Journal of Health Care Quality Assurance","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Measure (data warehouse); Point (geometry); Receiver operating characteristic; Signal-to-noise ratio (imaging); Taguchi methods; Noise (video); Diagnostic accuracy; Computer science; Index (typography); Statistics; Mathematics; Artificial intelligence; Data mining; Medicine; Radiology","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":[],"consensus_categories":[],"category_scores_codex":[0.05701015,0.00171041,0.002002656,0.007796831,0.000502049,0.004117482,0.001571167,0.002022683,0.00168814],"category_scores_gemma":[0.1636581,0.0003591168,0.002016668,0.004700392,0.002582768,0.002775424,0.001637756,0.001302396,0.000791719],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001940485,"about_ca_system_score_gemma":0.001963961,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000633212,"about_ca_topic_score_gemma":0.0004027598,"domain_scores_codex":[0.9197831,0.04279786,0.00693347,0.006224895,0.02337923,0.0008814704],"domain_scores_gemma":[0.7835103,0.1769007,0.01778654,0.00562657,0.0151278,0.001047975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.004111847,0.001127562,0.2435846,0.008503393,0.00323315,0.0003641729,0.001816754,0.02235876,0.01646047,0.01617971,0.004193918,0.6780655],"study_design_scores_gemma":[0.00078436,0.02226559,0.4578569,0.008110264,0.007657724,0.007634365,0.00639868,0.263368,0.08750176,0.0697056,0.06755514,0.001161634],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3036394,0.04325384,0.6246321,0.002644514,0.001190865,0.001452719,0.002062174,0.001506016,0.01961843],"genre_scores_gemma":[0.8483333,0.003517373,0.1446058,0.0005702725,0.0002968612,0.0008542235,0.0007918378,0.0001219221,0.0009085464],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.05701015,"threshold_uncertainty_score":0.301502,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2317686654379214,"score_gpt":0.5212233067730002,"score_spread":0.2894546413350788,"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."}}