{"id":"W2807187668","doi":"10.1016/j.gie.2018.04.2037","title":"Mo1679 REAL-TIME ARTIFICIAL INTELLIGENCE “FULL COLONOSCOPY WORKFLOW” FOR AUTOMATIC DETECTION FOLLOWED BY OPTICAL BIOPSY OF COLORECTAL POLYPS","year":2018,"lang":"en","type":"article","venue":"Gastrointestinal Endoscopy","topic":"Colorectal Cancer Screening and Detection","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vancouver General Hospital","funders":"","keywords":"Colonoscopy; Medicine; Workflow; Biopsy; Artificial intelligence; General surgery; Radiology; Gastroenterology; Internal medicine; Colorectal cancer; Computer science; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.0004639507,0.0006896767,0.0004459169,0.000719472,0.000337925,0.0005494506,0.0008170907,0.000591798,0.007331009],"category_scores_gemma":[0.0008373014,0.0003519078,0.0005074121,0.0003265236,0.0001408852,0.0003024989,0.0004823676,0.0003626848,0.002382165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004450131,"about_ca_system_score_gemma":0.001358606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007133452,"about_ca_topic_score_gemma":0.009077022,"domain_scores_codex":[0.9997171,0.0000403247,0.00002460565,0.0000817294,0.00008773964,0.0000486451],"domain_scores_gemma":[0.9997256,0.0000489969,0.00002017642,0.00004693588,0.000113172,0.00004506709],"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":[0.004296876,0.0005499482,0.01166048,0.000770974,0.0003152809,0.001157474,0.0002010251,0.03970809,0.2663061,0.002953766,0.05622332,0.6158568],"study_design_scores_gemma":[0.0003100493,0.0006814754,0.02399855,0.00005587275,0.000147652,0.0009109632,0.00008140803,0.7666754,0.1559532,0.002251209,0.04880083,0.0001335412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1969508,0.0008741454,0.6732239,0.0007340517,0.0004005769,0.0007473833,0.005425341,0.1078287,0.01381508],"genre_scores_gemma":[0.538992,0.0002640612,0.4426915,0.0004182798,0.00006806838,0.0002906278,0.007046352,0.0009805573,0.009248503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007331009,"threshold_uncertainty_score":0.02452469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01777725635948862,"score_gpt":0.2893149287567967,"score_spread":0.2715376723973081,"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."}}