{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","metaepi_broad","research_integrity"],"consensus_categories":["metaresearch","research_integrity"],"category_scores_codex":[0.1647331,0.0005753615,0.02468813,0.0002768819,0.00009101968,0.00006575404,0.0006861602,0.001998658,0.0002638545],"category_scores_gemma":[0.9160606,0.0003551945,0.002693877,0.0003563717,0.0003453331,0.0002236331,0.0003976327,0.004280959,0.000005352141],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001023649,"about_ca_system_score_gemma":0.01096122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001255209,"about_ca_topic_score_gemma":0.00004383931,"domain_scores_codex":[0.9617563,0.0228595,0.01296308,0.0009894765,0.0007444024,0.0006872059],"domain_scores_gemma":[0.1336432,0.8430714,0.01622459,0.001192809,0.002256499,0.003611471],"domain_codex":null,"domain_gemma":"methods","domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006590904,0.00006446634,0.0002476538,0.1589651,0.0005417798,0.00008643283,0.000006817291,3.010833e-8,2.03977e-8,0.001388327,0.03544659,0.8025937],"study_design_scores_gemma":[0.001215221,0.001749127,0.00005064888,0.4102182,0.003465346,0.000244966,0.000008699726,0.00000140742,8.49536e-9,0.001813376,0.5810611,0.0001719015],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.000003289111,0.8747188,0.0291815,0.09228139,0.001262462,0.002404462,0.00005737009,0.00002185801,0.00006887932],"genre_scores_gemma":[3.469311e-7,0.8474712,0.1159649,0.03333057,0.002727359,0.00005713185,0.00001437913,0.00002900156,0.0004050298],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8281131,"threshold_uncertainty_score":0.99989,"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."}}