{"id":"W4311088172","doi":"10.1016/j.jclinepi.2022.11.019","title":"Controversy and debate: challenges with the need to improve the reference standard in diagnosis paper 1: two challenges: absence of a clear cut, easily replicable test for the reference standard; unethical/infeasible inclusion of an invasive procedure in the reference standard","year":2022,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Grading (engineering); Gold standard (test); Diagnostic accuracy; Test (biology); Quality of evidence; Reference values; Medical physics; Standard of care; Medicine; Diagnostic test; International standard; Computer science; Pathology; Meta-analysis; Pediatrics; Surgery; Engineering; 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":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7920349,0.002083575,0.01265672,0.01145312,0.008320935,0.02289018,0.02122687,0.04658507,0.004806465],"category_scores_gemma":[0.8842068,0.003767788,0.00641039,0.008695558,0.05037357,0.02955801,0.01620813,0.06363101,0.00291034],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01259771,"about_ca_system_score_gemma":0.03700477,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007337236,"about_ca_topic_score_gemma":0.006120619,"domain_scores_codex":[0.2285802,0.5377377,0.1127494,0.03073676,0.08675709,0.003438794],"domain_scores_gemma":[0.03672216,0.8429738,0.02058107,0.03115147,0.06394639,0.004625026],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.002485448,0.0004691946,0.009480279,0.01706855,0.005115805,0.0008179163,0.01975678,0.001502564,0.001238939,0.2717532,0.3420909,0.3282205],"study_design_scores_gemma":[0.002681741,0.0008743221,0.006853268,0.0432778,0.002507581,0.001628809,0.006093167,0.005502204,0.00196258,0.6239389,0.303384,0.001295608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.001408671,0.02187537,0.01751331,0.9396821,0.01797901,0.0001532856,0.0002059024,0.00009954898,0.001082791],"genre_scores_gemma":[0.07983376,0.01242108,0.1424952,0.6973157,0.06493752,0.0012913,0.0004383194,0.0004755331,0.0007915471],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.2079651,"threshold_uncertainty_score":0.256458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6980742085642876,"score_gpt":0.5652740455244651,"score_spread":0.1328001630398224,"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."}}