{"id":"W1562864973","doi":"10.1186/s12909-015-0387-1","title":"Making medical student course evaluations meaningful: implementation of an intensive course review protocol","year":2015,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Memorial University of Newfoundland","funders":"Memorial University of Newfoundland","keywords":"Protocol (science); Medical education; Educational measurement; Course evaluation; Course (navigation); Curriculum; Medicine; Psychology; Higher education; Pedagogy","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":["metaresearch"],"category_scores_codex":[0.4529309,0.002506417,0.003200297,0.007795171,0.004505458,0.005384394,0.006044908,0.00451054,0.01344243],"category_scores_gemma":[0.4966601,0.00257296,0.00260929,0.005961306,0.002573486,0.005315089,0.006873172,0.006628897,0.006667566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007341635,"about_ca_system_score_gemma":0.03437021,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001082813,"about_ca_topic_score_gemma":0.002490379,"domain_scores_codex":[0.5304517,0.3453971,0.07037099,0.01124447,0.03635058,0.006185052],"domain_scores_gemma":[0.339422,0.2797692,0.05396407,0.09967656,0.2122346,0.01493357],"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":[0.02210787,0.02108258,0.01887916,0.008633904,0.0005977366,0.000792711,0.01686786,0.004609067,0.01379228,0.005223508,0.07370069,0.8137127],"study_design_scores_gemma":[0.03889261,0.07230949,0.2571162,0.01521609,0.001498841,0.00100955,0.01406561,0.06198236,0.04576121,0.02238254,0.4671591,0.002606405],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"protocol","genre_gemma":"empirical","genre_scores_codex":[0.02491864,0.0001997777,0.06570394,0.002265312,0.0009880876,0.8997169,0.0006669448,0.001475578,0.004064759],"genre_scores_gemma":[0.03236909,0.000163,0.1148653,0.0009105165,0.000356069,0.8497408,0.0003365678,0.0001431809,0.001115476],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5470691,"threshold_uncertainty_score":0.6746336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1300517369979802,"score_gpt":0.6100737267329628,"score_spread":0.4800219897349826,"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."}}