{"id":"W2618479513","doi":"10.1016/j.ejrad.2017.05.032","title":"Treatment of multiple test readers in diagnostic accuracy systematic reviews-meta-analyses of imaging studies","year":2017,"lang":"en","type":"review","venue":"European Journal of Radiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Medicine; Medical physics; Meta-analysis; Test (biology); Diagnostic accuracy; Nuclear medicine; Radiology; Pathology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"meta_analysis","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad"],"consensus_categories":["metaresearch","metaepi_broad"],"category_scores_codex":[0.1829357,0.0009878802,0.05900138,0.001953408,0.00009681678,0.0001605024,0.00411357,0.0000819379,0.0003987871],"category_scores_gemma":[0.6869249,0.0003578231,0.01728288,0.0008807809,0.0004038692,0.0002555272,0.0002032123,0.000348126,0.0004575984],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001556555,"about_ca_system_score_gemma":0.0002114152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005859575,"about_ca_topic_score_gemma":0.000006401777,"domain_scores_codex":[0.8096564,0.130246,0.05617767,0.001014289,0.002444629,0.0004609998],"domain_scores_gemma":[0.689861,0.1779084,0.124617,0.005405443,0.002019413,0.0001888038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001146514,0.0004950372,0.002381404,0.2033275,0.04805002,0.001710763,0.002498605,0.00007960912,0.000006441247,0.00002342569,0.0159792,0.7254365],"study_design_scores_gemma":[0.00064723,0.0006602788,0.0001455574,0.06595699,0.1205464,0.003293148,0.0009658392,0.00004165706,0.000001467435,0.00006326186,0.8072492,0.0004288747],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000033883,0.9962022,0.0005495698,0.00007971888,0.0004739716,0.002246591,0.000041689,0.000001310873,0.0003710801],"genre_scores_gemma":[0.002179834,0.9951563,0.001921579,0.00001338441,0.0001775239,0.00004830594,0.000005762302,0.00004240005,0.0004549117],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7912701,"threshold_uncertainty_score":0.9998873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9369164767241436,"score_gpt":0.6267886288958096,"score_spread":0.310127847828334,"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."}}