{"id":"W4417068344","doi":"10.1016/j.jclinepi.2026.112306","title":"When and how to establish a new reference standard for medical tests: a scoping review identifying methodological priorities","year":2025,"lang":"en","type":"review","venue":"Journal of Clinical Epidemiology","topic":"Clinical Laboratory Practices and Quality Control","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Reference data; Test (biology); Workflow; Gold standard (test); Guideline; Reference model; Reference values; Health care","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":[0.5813928,0.003203037,0.01205029,0.03935665,0.006765043,0.02643178,0.0114374,0.01114156,0.004167463],"category_scores_gemma":[0.800339,0.005209474,0.01546724,0.03474074,0.01088861,0.0352042,0.01377715,0.01239666,0.00154329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02983206,"about_ca_system_score_gemma":0.1388908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01881784,"about_ca_topic_score_gemma":0.02740319,"domain_scores_codex":[0.3519159,0.3783542,0.2031962,0.01412246,0.04849295,0.003918315],"domain_scores_gemma":[0.179417,0.6203388,0.05614739,0.02452369,0.1167455,0.002827621],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.0005021632,0.0001064298,0.005534681,0.6615455,0.005670235,0.0004165412,0.02079578,0.001080567,0.001012806,0.03079958,0.01661148,0.2559243],"study_design_scores_gemma":[0.0001846716,0.00008862417,0.001498367,0.9345541,0.005140733,0.0001453502,0.005980623,0.0006690191,0.0005670137,0.01474006,0.03630757,0.000123907],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.007147986,0.7604234,0.08206895,0.09931423,0.01010338,0.03131021,0.002372048,0.0002623732,0.006997542],"genre_scores_gemma":[0.08505629,0.4169313,0.3751831,0.02499452,0.002055334,0.09132057,0.003020158,0.0002985272,0.001140096],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.4186072,"threshold_uncertainty_score":0.5162172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8169739210829675,"score_gpt":0.6993830391793203,"score_spread":0.1175908819036472,"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."}}