{"id":"W4413930962","doi":"10.21203/rs.3.rs-7179076/v1","title":"Improving the active Crohn’s disease reference standard: Comparative evaluation of latent class modelling and expert panel consensus","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Inflammatory Bowel Disease","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University Health Centre","funders":"National Institute for Health and Care Research","keywords":"Crohn's disease; Class (philosophy); Consensus conference; Computer science; Medicine; Disease; Artificial intelligence; Internal medicine; Library science","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":[],"category_scores_codex":[0.2894442,0.001951822,0.004939077,0.005460388,0.002036172,0.006125988,0.006574927,0.006801393,0.007796152],"category_scores_gemma":[0.434455,0.001143661,0.007015664,0.002890775,0.001829591,0.004815734,0.005336947,0.005024388,0.002156803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002540396,"about_ca_system_score_gemma":0.004793481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0059277,"about_ca_topic_score_gemma":0.005974298,"domain_scores_codex":[0.7705494,0.1822048,0.01219739,0.01401343,0.01946181,0.001573169],"domain_scores_gemma":[0.4616166,0.4453053,0.01280671,0.02984124,0.04729604,0.003134116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.04015411,0.002195238,0.08514072,0.01669353,0.03582961,0.0005140508,0.008703029,0.1019714,0.003333402,0.02560039,0.07774946,0.602115],"study_design_scores_gemma":[0.01629474,0.006593212,0.1126872,0.01244768,0.03734489,0.001370413,0.006143018,0.5868197,0.01146673,0.1322182,0.07504768,0.001566619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3078595,0.03649267,0.5897322,0.01421751,0.004051641,0.005421498,0.01792951,0.003666212,0.02062932],"genre_scores_gemma":[0.729067,0.002708204,0.2428329,0.002597439,0.0005797102,0.002754608,0.0162872,0.000927122,0.002245897],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2894442,"threshold_uncertainty_score":0.8762418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1844493641307915,"score_gpt":0.4209172754060057,"score_spread":0.2364679112752142,"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."}}