{"id":"W4409559242","doi":"10.1007/s00261-025-04941-9","title":"Accuracy, repeatability, reproducibility and reference ranges of primary sclerosing cholangitis specific biomarkers from quantitative MRCP","year":2025,"lang":"en","type":"article","venue":"Abdominal Radiology","topic":"Gallbladder and Bile Duct Disorders","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Repeatability; Reproducibility; Medicine; Imaging phantom; Nuclear medicine; Scanner; Coefficient of variation; Limits of agreement; Radiology; Mathematics; Statistics; Computer science; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.001088959,0.0001838241,0.0006857663,0.0001504992,0.00007048977,0.00001169611,0.0001360654,0.0001521238,0.0001145016],"category_scores_gemma":[0.001962456,0.0001584163,0.00009260269,0.0002509374,0.0008171492,0.00009439515,0.0001185887,0.0002331944,0.000004809152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007772553,"about_ca_system_score_gemma":0.0001510776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008226798,"about_ca_topic_score_gemma":0.000078622,"domain_scores_codex":[0.9977748,0.0002662442,0.0004983365,0.001088417,0.000127647,0.0002445742],"domain_scores_gemma":[0.9973918,0.001105828,0.0001519516,0.001126529,0.0001513222,0.00007257498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.006122655,0.0003854758,0.3867628,0.0004693592,0.0005390632,0.00004191386,0.001189356,0.000001108724,0.4438705,0.0008793738,0.004789528,0.1549488],"study_design_scores_gemma":[0.001947487,0.0003821915,0.9801704,0.0001917909,0.0001547234,0.00005768061,0.001263298,0.00002040462,0.01169423,0.002273831,0.001702561,0.0001413942],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9800559,0.01144261,0.0002641648,0.001815141,0.0002018465,0.0004762257,0.00005588708,0.00003711955,0.005651067],"genre_scores_gemma":[0.9920669,0.002018798,0.005327325,0.0003439977,0.00004075278,0.00001533437,0.0001189824,0.00001023963,0.0000577258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5934076,"threshold_uncertainty_score":0.6460028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04698776009765573,"score_gpt":0.3125515638321729,"score_spread":0.2655638037345172,"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."}}