{"id":"W4404734131","doi":"10.1016/j.gie.2024.11.042","title":"Creating a standardized tool for the evaluation and comparison of artificial intelligence–based computer-aided detection programs in colonoscopy: a modified Delphi approach","year":2024,"lang":"en","type":"article","venue":"Gastrointestinal Endoscopy","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Montreal General Hospital; Vancouver General Hospital; Vancouver Hospital and Health Sciences Centre","funders":"School of Medicine, Duke University","keywords":"Medicine; Colonoscopy; Delphi; Medical physics; Artificial intelligence; Delphi method; Machine learning; Internal medicine; Computer science; Programming language; Colorectal cancer","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":[0.001415357,0.0001646666,0.0003377557,0.0001906277,0.0001138742,0.0000860701,0.00005491648,0.00004673306,0.000004502327],"category_scores_gemma":[0.0006132167,0.0001287839,0.0001018145,0.0004542686,0.0001172525,0.0000652412,0.00002187744,0.0002527408,4.537827e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002027078,"about_ca_system_score_gemma":0.0002331213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002187124,"about_ca_topic_score_gemma":0.0001474925,"domain_scores_codex":[0.9984196,0.0001251926,0.0005093039,0.0003483333,0.0003666436,0.0002309594],"domain_scores_gemma":[0.9986352,0.0008026966,0.0001263609,0.0001424902,0.0002417295,0.00005148929],"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":[0.04161231,0.0003514095,0.003493847,0.0008137663,0.00006427139,0.000005156498,0.001575911,0.03179551,0.04948656,0.0001725897,0.0000079891,0.8706207],"study_design_scores_gemma":[0.0009043381,0.008292936,0.001526765,0.0008381798,0.0001898627,0.0001836086,0.000753414,0.9775343,0.009449465,0.0002311886,0.00000686532,0.00008906006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4024922,0.0001689776,0.5957561,0.00005823608,0.00009059749,0.001332302,0.000005037766,0.00007019118,0.00002632085],"genre_scores_gemma":[0.8078135,0.000001246011,0.1915254,0.000009325066,0.0001260811,0.0004840784,0.00002205596,0.00001633282,0.000002074723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9457388,"threshold_uncertainty_score":0.5251653,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1052220540758332,"score_gpt":0.3692039924978486,"score_spread":0.2639819384220154,"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."}}