{"id":"W2089009990","doi":"10.1136/ebm.13.6.162-a","title":"GRADE: assessing the quality of evidence for diagnostic recommendations","year":2008,"lang":"en","type":"editorial","venue":"Evidence-Based Medicine","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":231,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"European Commission","keywords":"Grading (engineering); Diagnostic test; Medicine; Clinical Practice; Test (biology); Odds; Diagnostic odds ratio; Medical physics; MEDLINE; Diagnostic accuracy; Quality (philosophy); Intensive care medicine; Family medicine; Pediatrics; Logistic regression; 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":[{"model":"gemma","categories":["metaresearch"],"domain":"evaluation","study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3447122,0.0007666874,0.00797383,0.0007164038,0.0006000611,0.0004902062,0.005298715,0.0005323159,0.004471852],"category_scores_gemma":[0.9489586,0.0002785564,0.002933627,0.002664215,0.0008390037,0.0008205386,0.0001738369,0.0009462327,0.0002355375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002050328,"about_ca_system_score_gemma":0.00215249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003559905,"about_ca_topic_score_gemma":0.00009857502,"domain_scores_codex":[0.9050853,0.0390441,0.02757688,0.002557199,0.02505922,0.0006772756],"domain_scores_gemma":[0.174022,0.7838318,0.02424859,0.008075269,0.009514482,0.0003077709],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002101913,0.00004799015,0.00141524,0.000684919,0.000150614,0.00000269305,0.0002598228,0.00004977223,0.00002549088,0.00007524117,0.9869903,0.01027691],"study_design_scores_gemma":[0.0005108373,0.0002583057,0.00223973,0.01452877,0.001328594,0.000001835568,0.0004435392,0.000778003,0.00002228245,0.001473323,0.9780915,0.0003233264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.0002691732,0.05037844,0.1211176,0.1066342,0.716639,0.004479134,0.0002134534,0.00002162958,0.0002472715],"genre_scores_gemma":[0.01633399,0.01501575,0.01061205,0.001863546,0.9407024,0.001477458,0.0004313337,0.0001041725,0.01345933],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.7447878,"threshold_uncertainty_score":0.9999667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9476189088113064,"score_gpt":0.6841482826036769,"score_spread":0.2634706262076295,"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."}}