{"id":"W2416590355","doi":"10.1186/s41073-016-0014-7","title":"Updating standards for reporting diagnostic accuracy: the development of STARD 2015","year":2016,"lang":"en","type":"article","venue":"Research Integrity and Peer Review","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Public Health; Ottawa Hospital; University of Ottawa","funders":"Medical Research Council","keywords":"Diagnostic accuracy; Medical physics; Computer science; Medicine; Internal medicine","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":["metaresearch"],"domain":"reporting","study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5893739,0.001834832,0.004122888,0.02467722,0.003414301,0.01139071,0.01174665,0.004815741,0.003881607],"category_scores_gemma":[0.744334,0.003546608,0.00884058,0.01758206,0.005916168,0.0107721,0.0190224,0.0135098,0.004087903],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01848975,"about_ca_system_score_gemma":0.07508777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008942961,"about_ca_topic_score_gemma":0.008568686,"domain_scores_codex":[0.2712913,0.3971967,0.229474,0.01132231,0.08683422,0.003881586],"domain_scores_gemma":[0.1661347,0.2624063,0.06459362,0.05849818,0.4414276,0.006939611],"domain_codex":"methods","domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006331484,0.000353012,0.02635831,0.03293827,0.001682676,0.0002390756,0.01244621,0.003390061,0.001574582,0.04918321,0.2102074,0.6609941],"study_design_scores_gemma":[0.0007847457,0.0009707529,0.03801459,0.0661817,0.001660054,0.001111363,0.007104788,0.008395576,0.006837255,0.05017417,0.8177469,0.001018152],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01630196,0.02741197,0.7646818,0.06755325,0.01823773,0.05689697,0.01368382,0.005972053,0.02926048],"genre_scores_gemma":[0.0326435,0.008005133,0.9043304,0.006693666,0.001106334,0.03496158,0.01004336,0.000701047,0.001514856],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4106261,"threshold_uncertainty_score":0.5063751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.921923900201108,"score_gpt":0.6904396986495264,"score_spread":0.2314842015515817,"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."}}