{"id":"W4394765738","doi":"10.1055/a-2296-5696","title":"Influence of artificial intelligence on the diagnostic performance of endoscopists in the assessment of Barrett’s esophagus: a tandem randomized and video trial","year":2024,"lang":"en","type":"article","venue":"Endoscopy","topic":"Esophageal Cancer Research and Treatment","field":"Medicine","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vancouver General Hospital; University of British Columbia","funders":"","keywords":"Medicine; Confidence interval; Barrett's esophagus; Randomized controlled trial; Endoscopy; Esophagus; Biopsy; Esophageal disease; Diagnostic accuracy; Radiology; Surgery; Internal medicine; Adenocarcinoma; 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":[0.001593241,0.0001397931,0.0005311697,0.0001353606,0.00003395673,0.00001572876,0.0001611266,0.00004120089,0.00006263554],"category_scores_gemma":[0.001468249,0.0000691282,0.0001083411,0.0002963595,0.0004234291,0.00005754329,0.00003594858,0.0002828341,0.000002908418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005954355,"about_ca_system_score_gemma":0.0003221072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001687937,"about_ca_topic_score_gemma":0.00001585364,"domain_scores_codex":[0.9981237,0.0003374939,0.0005684597,0.0002043049,0.0005760998,0.0001899145],"domain_scores_gemma":[0.9931915,0.006290457,0.0001178249,0.0002906049,0.0000607267,0.00004890879],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"randomized_trial","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.6027035,0.003102992,0.2653413,0.004743787,0.001367984,0.0006599736,0.01442146,0.002980372,0.002891463,0.08225322,0.0002660867,0.0192679],"study_design_scores_gemma":[0.3108051,0.02201435,0.1516152,0.009741221,0.0008724402,0.00003264516,0.001229909,0.02161119,0.4733544,0.008320104,0.00002101366,0.0003824731],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9820054,0.01483156,0.00007509427,0.0007449572,0.00008964448,0.002105936,0.0000139978,0.000008361892,0.0001251174],"genre_scores_gemma":[0.9978826,0.001399426,0.0001890833,0.00006340179,0.00006104911,0.0003801565,0.000003216283,0.000009320474,0.00001176418],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4704629,"threshold_uncertainty_score":0.2818966,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02850510267176072,"score_gpt":0.3617251781385361,"score_spread":0.3332200754667753,"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."}}