{"id":"W4403344103","doi":"10.1016/j.gie.2024.10.010","title":"Development and usability of an endoscopist report card assessing ERCP quality","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":true,"ca_institutions":"University of Ottawa; Alberta Health; University of Calgary","funders":"University of Calgary; Alberta Health Services","keywords":"Medicine; Usability; Report card; Medical physics; Human–computer interaction","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07383977,0.001425164,0.001347755,0.003425343,0.0006878086,0.002605213,0.002035526,0.001151043,0.002475093],"category_scores_gemma":[0.1151622,0.0007659832,0.002139965,0.001384282,0.0009428298,0.002106259,0.002203661,0.00120279,0.0008929129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001630173,"about_ca_system_score_gemma":0.004071195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00103613,"about_ca_topic_score_gemma":0.00103038,"domain_scores_codex":[0.9439117,0.03360872,0.01109527,0.00202189,0.008094916,0.00126764],"domain_scores_gemma":[0.8148457,0.09899447,0.02045602,0.01566032,0.04657409,0.003469454],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00383748,0.005543984,0.1995928,0.004857273,0.0004222477,0.0006177339,0.01104185,0.003573242,0.01527505,0.001038477,0.01038994,0.7438099],"study_design_scores_gemma":[0.002794365,0.0455827,0.7471003,0.004864233,0.001337976,0.002452458,0.01597815,0.05355589,0.06118432,0.002034296,0.06194638,0.001168875],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7689745,0.0005160333,0.1588632,0.00116713,0.0004458413,0.05732279,0.003081912,0.003409798,0.006218858],"genre_scores_gemma":[0.4354428,0.0004898899,0.523267,0.0004653491,0.0001275445,0.03593114,0.002656622,0.0002179559,0.001401658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9261602,"threshold_uncertainty_score":0.3905067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04632563245415385,"score_gpt":0.363545132902963,"score_spread":0.3172195004488092,"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."}}