{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27501,0.006746386,0.03489328,0.01910427,0.002344118,0.00946051,0.008036285,0.0095935,0.00861216],"category_scores_gemma":[0.554379,0.006091265,0.07713564,0.0164476,0.004191628,0.007874397,0.007046732,0.007565575,0.0007963899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004676098,"about_ca_system_score_gemma":0.007814872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003761802,"about_ca_topic_score_gemma":0.008145162,"domain_scores_codex":[0.4310654,0.4131269,0.1098873,0.02160468,0.0225604,0.001755458],"domain_scores_gemma":[0.3813692,0.5616215,0.02935353,0.01862808,0.008076838,0.0009508014],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"systematic_review","study_design_scores_codex":[0.001878631,0.00003643979,0.005145485,0.1457177,0.8109341,0.0003366386,0.0004434822,0.0008359925,0.0002146073,0.001938297,0.002308623,0.03021003],"study_design_scores_gemma":[0.003284053,0.0004809469,0.003857191,0.03849084,0.9288598,0.0004332852,0.0002780117,0.003769511,0.0006369266,0.01199661,0.007694013,0.0002187074],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.006022042,0.8955894,0.08005619,0.003620384,0.005287034,0.005498241,0.002293855,0.0004968424,0.001136066],"genre_scores_gemma":[0.4466684,0.2698304,0.2108784,0.0117286,0.006679963,0.04770827,0.002639029,0.0009212474,0.00294563],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.72499,"threshold_uncertainty_score":0.8940417,"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."}}