{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7030503,0.0001771525,0.002350253,0.0001515219,0.0004113115,0.0003869653,0.001340684,0.00006061136,0.003105818],"category_scores_gemma":[0.8594182,0.00005345941,0.0006952247,0.0008808497,0.0001786964,0.0002088626,0.0003470797,0.0004063577,0.000162091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007748703,"about_ca_system_score_gemma":0.0009292584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002027093,"about_ca_topic_score_gemma":0.00008255867,"domain_scores_codex":[0.9380088,0.01692302,0.02155951,0.001174835,0.02164701,0.000686777],"domain_scores_gemma":[0.4127584,0.405696,0.04783198,0.01553233,0.1168609,0.00132034],"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":[0.000005248071,0.00001820079,0.002403483,0.00226387,0.00009250893,0.000001399177,0.0003170558,6.131273e-8,0.00005933386,0.002608916,0.3710184,0.6212115],"study_design_scores_gemma":[0.00008311812,0.00003336536,0.001335169,0.005665701,0.00005539453,0.000007189746,0.0004254535,0.00002320726,0.0001649517,0.007002165,0.9851204,0.0000838566],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.03479385,0.4025634,0.1584483,0.3686638,0.0005632074,0.01490931,0.000753727,0.00001753511,0.01928686],"genre_scores_gemma":[0.7998797,0.08169883,0.07034227,0.00129729,0.0005597874,0.002213559,0.00005788506,0.00007153595,0.04387917],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7650858,"threshold_uncertainty_score":0.9978055,"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."}}