{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01292057,0.001146204,0.0007717292,0.001523062,0.0005847276,0.00128671,0.001895647,0.002056088,0.001374068],"category_scores_gemma":[0.01440657,0.0004535572,0.0009265543,0.0005489097,0.0009387137,0.0009984133,0.001724907,0.001093916,0.0008299667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006663983,"about_ca_system_score_gemma":0.002168733,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001776618,"about_ca_topic_score_gemma":0.001807882,"domain_scores_codex":[0.9918606,0.003451328,0.0006893811,0.0008066279,0.00272878,0.0004632865],"domain_scores_gemma":[0.9892594,0.003860064,0.0004959813,0.0006550041,0.005265232,0.0004641949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002870428,0.01028727,0.2316031,0.001248114,0.0002685172,0.0005467819,0.004091491,0.004419891,0.3623888,0.001540952,0.003108742,0.3776259],"study_design_scores_gemma":[0.001117135,0.06571443,0.4933608,0.0009248964,0.0007387492,0.002986667,0.003994721,0.06882014,0.3325873,0.001415847,0.02793538,0.0004039905],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7528598,0.0006413964,0.2262048,0.0005429333,0.0003581814,0.01430807,0.00111774,0.0007962646,0.003170766],"genre_scores_gemma":[0.6133302,0.0006249631,0.3717871,0.0006537824,0.0001264849,0.008779957,0.00168329,0.0001456222,0.002868631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01292057,"threshold_uncertainty_score":0.06833136,"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."}}