{"id":"W3080349182","doi":"10.1007/s10459-020-09987-6","title":"Augmenting physician examiner scoring in objective structured clinical examinations: including the standardized patient perspective","year":2020,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Medical Council of Canada","funders":"","keywords":"Empathy; Active listening; Reliability (semiconductor); Rating scale; Medicine; Psychology; Inter-rater reliability; Clinical psychology; Family medicine; Medical physics; Psychiatry","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":[0.01276386,0.0007151738,0.000814023,0.001517707,0.0003061275,0.002236874,0.0006040824,0.0006855897,0.002304267],"category_scores_gemma":[0.06324899,0.000445037,0.0005759848,0.001032547,0.0002928179,0.001636799,0.001966919,0.0007829927,0.0007677133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004036895,"about_ca_system_score_gemma":0.001886137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001565699,"about_ca_topic_score_gemma":0.008632519,"domain_scores_codex":[0.9862025,0.009078796,0.001106608,0.0005321348,0.00287342,0.0002064699],"domain_scores_gemma":[0.9521884,0.03038798,0.004703512,0.003766989,0.008208604,0.0007444564],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001031084,0.001116553,0.2420646,0.0006027152,0.0003481831,0.0003362072,0.001529338,0.004860149,0.01158599,0.0008178476,0.005834176,0.7298732],"study_design_scores_gemma":[0.0004845026,0.004065525,0.8677995,0.000821878,0.001074262,0.002388832,0.001934305,0.07482396,0.02399966,0.002934307,0.01936173,0.0003115495],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7723963,0.002781028,0.186868,0.00409677,0.0007253703,0.00108022,0.001115462,0.001637446,0.02929939],"genre_scores_gemma":[0.8158515,0.001779849,0.1783203,0.000715538,0.0005093176,0.0003688111,0.0004565038,0.000184783,0.001813351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01276386,"threshold_uncertainty_score":0.06750256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05042979373217132,"score_gpt":0.4640941036743465,"score_spread":0.4136643099421752,"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."}}