{"id":"W4412534866","doi":"10.1016/j.cgh.2025.06.034","title":"Artificial Intelligence and Endoscopist Diagnostic Agreement as a Framework for Colorectal Polyp Optical Diagnosis Implementation","year":2025,"lang":"en","type":"article","venue":"Clinical Gastroenterology and Hepatology","topic":"Radiomics and Machine Learning in Medical Imaging","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Fonds de Recherche du Québec - Santé","keywords":"Medicine; Colonoscopy; Colorectal Polyp; Colorectal cancer screening; General surgery; Gastroenterology; Radiology; Internal medicine; Medical physics; Colorectal cancer","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.009953329,0.0004665382,0.0007177995,0.001511139,0.0009316248,0.00298793,0.003265282,0.001725588,0.005855715],"category_scores_gemma":[0.02320709,0.0006399942,0.001029228,0.0006798993,0.001754564,0.002917042,0.003194842,0.002611205,0.0007465464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002182667,"about_ca_system_score_gemma":0.004381594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01196581,"about_ca_topic_score_gemma":0.01054707,"domain_scores_codex":[0.9944966,0.002638357,0.0003143339,0.000771714,0.001339818,0.0004391941],"domain_scores_gemma":[0.9875177,0.007695291,0.0007944637,0.001231731,0.002320476,0.0004402513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0007465869,0.000985936,0.01277679,0.0001555794,0.0002389327,0.0003558075,0.001024626,0.484244,0.006516546,0.2459607,0.003136506,0.2438581],"study_design_scores_gemma":[0.00001157306,0.00004433921,0.0003653819,0.000008536201,0.00001535369,0.00002315791,0.0000347697,0.9819531,0.001954713,0.01471678,0.0008606425,0.00001176699],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02854483,0.00005480914,0.9647217,0.0009222159,0.00003441015,0.0001638707,0.00007401194,0.001738377,0.003745797],"genre_scores_gemma":[0.552609,0.00003350467,0.4443255,0.0001738514,0.0000324901,0.0001599632,0.0001401175,0.000113847,0.002411844],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01196581,"threshold_uncertainty_score":0.05263889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03480557981211141,"score_gpt":0.4247259466775459,"score_spread":0.3899203668654345,"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."}}