{"id":"W2884971300","doi":"10.7759/cureus.3051","title":"Obstetrics and Gynecology Modified Delphi Survey for Entrustable Professional Activities: Quantification of Importance, Benchmark Levels, and Roles in Simulation-based Training and Assessment","year":2018,"lang":"en","type":"article","venue":"Cureus","topic":"Simulation-Based Education in Healthcare","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Obstetrics and gynaecology; Delphi method; Medical education; Benchmark (surveying); Medicine; Set (abstract data type); Psychology; Gynecology; Computer science; Biology; Pregnancy; Artificial intelligence","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":[0.0007694028,0.0001138104,0.0002719352,0.0001753726,0.0001218129,0.00001300406,0.00003318536,0.0001431876,0.00004369532],"category_scores_gemma":[0.002462712,0.0001123838,0.00001452993,0.0002180613,0.000140463,0.000112853,0.00001267549,0.000108239,7.435325e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001480116,"about_ca_system_score_gemma":0.000833213,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001398946,"about_ca_topic_score_gemma":0.0004344096,"domain_scores_codex":[0.9988372,0.0001172919,0.0004213874,0.0002847336,0.0001544481,0.0001848968],"domain_scores_gemma":[0.9886484,0.0104464,0.0002303586,0.0001701417,0.000410909,0.00009380881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001146104,0.0001258897,0.9905994,0.0002511102,0.00001667217,3.110089e-7,0.002743521,0.002018928,0.0002317001,0.0006142632,0.00003057486,0.003253003],"study_design_scores_gemma":[0.001330908,0.0001871281,0.7549595,0.00007069903,0.00001877307,4.807669e-7,0.002618669,0.2402067,0.0001318988,0.0003252433,0.0000698521,0.00008019914],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939572,0.0006380034,0.00365181,0.0003482228,0.0003583491,0.0008860903,0.0001047292,0.00001327049,0.00004237732],"genre_scores_gemma":[0.9963112,0.00001838764,0.003097787,0.0001202778,0.00005657206,0.00008806238,0.0002621796,0.0000149182,0.00003060857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2381877,"threshold_uncertainty_score":0.4582879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1598788737739449,"score_gpt":0.4320309874867345,"score_spread":0.2721521137127896,"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."}}