{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2964573,0.001581394,0.002003576,0.01324148,0.002622296,0.004222433,0.003391548,0.001846578,0.003659074],"category_scores_gemma":[0.2735549,0.001339446,0.002866223,0.006472345,0.003217342,0.00497549,0.008643614,0.002271994,0.0007418399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007537476,"about_ca_system_score_gemma":0.01735913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001872083,"about_ca_topic_score_gemma":0.002769647,"domain_scores_codex":[0.6640119,0.2618524,0.04721247,0.003621172,0.02019616,0.003105869],"domain_scores_gemma":[0.6621976,0.2354101,0.01441473,0.01977086,0.06532236,0.002884358],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.003473234,0.005289185,0.03907946,0.00611913,0.001050327,0.0008105181,0.06454618,0.01026673,0.02138426,0.02936663,0.007111877,0.8115025],"study_design_scores_gemma":[0.006845927,0.03399261,0.2626604,0.0174658,0.003165354,0.003774394,0.2158028,0.1480007,0.08373687,0.07694626,0.1448385,0.002770513],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3249737,0.0007841191,0.5382724,0.001826492,0.0003711805,0.1185635,0.001167592,0.0009329164,0.0131082],"genre_scores_gemma":[0.1985163,0.0002973162,0.735302,0.0002721875,0.00004097648,0.06406506,0.0006577655,0.0001235019,0.0007248982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7035427,"threshold_uncertainty_score":0.8675934,"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."}}