{"id":"W2948330616","doi":"10.1016/j.gie.2020.07.055","title":"Development and initial validation of an instrument for video-based assessment of technical skill in ERCP","year":2020,"lang":"en","type":"article","venue":"Gastrointestinal Endoscopy","topic":"Medical Device Sterilization and Disinfection","field":"Immunology and Microbiology","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"Hospital for Sick Children","funders":"National Institutes of Health; National Institute of Diabetes and Digestive and Kidney Diseases; Boston Scientific Corporation; Medtronic","keywords":"Generalizability theory; Reliability (semiconductor); Task (project management); Coaching; Medicine; Benchmark (surveying); Medical physics; Computer science; Statistics; Psychology","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":[0.0002264809,0.00008469235,0.0001910671,0.00006771566,0.00002638271,0.00000359154,0.00005486512,0.00003908163,0.0001003866],"category_scores_gemma":[0.0003933474,0.00007968674,0.00002369166,0.00009148205,0.00009189465,0.00005053221,0.00002583305,0.00008559791,0.000001596517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002748295,"about_ca_system_score_gemma":0.0001548251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001415911,"about_ca_topic_score_gemma":0.00001484505,"domain_scores_codex":[0.9991939,0.00009092484,0.0003862196,0.000165496,0.00004572709,0.0001177033],"domain_scores_gemma":[0.9995701,0.0001285411,0.0001405921,0.00006132892,0.00006151557,0.00003795023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007069354,0.0002805136,0.02471841,0.0001907067,0.00000782098,0.000001583325,0.0001378225,0.00009771609,0.9703704,0.0007123346,0.00002257817,0.00275317],"study_design_scores_gemma":[0.00886905,0.003708357,0.1072655,0.0005434044,0.00003869283,0.0001651929,0.0004573742,0.001971893,0.8758762,0.00009424958,0.0008062122,0.0002039073],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8643968,0.000008490691,0.1348384,0.0001641045,0.00005331261,0.0002805053,0.00001511861,0.00002108805,0.0002221954],"genre_scores_gemma":[0.8736814,4.126828e-7,0.1259672,0.00015743,0.000007528288,0.00002592914,0.0001534575,0.000005067341,0.000001602812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09449424,"threshold_uncertainty_score":0.3249531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03161883790412062,"score_gpt":0.3198404108561331,"score_spread":0.2882215729520125,"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."}}