{"id":"W2614587327","doi":"10.2196/games.7033","title":"Medical Student Evaluation With a Serious Game Compared to Multiple Choice Questions Assessment","year":2017,"lang":"en","type":"article","venue":"JMIR Serious Games","topic":"Educational Games and Gamification","field":"Psychology","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Multiple choice; Test (biology); Clinical endpoint; Medicine; Randomized controlled trial; Medical education; Medical school; Correlation; Variance (accounting); Psychology; Internal medicine; Significant difference; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00455203,0.0009065088,0.001856029,0.001030691,0.0002952123,0.0008163486,0.0005365381,0.0007176833,0.00455617],"category_scores_gemma":[0.01448417,0.0002369136,0.001496281,0.0004036362,0.0004561396,0.0007193969,0.001121501,0.0007755935,0.0005991646],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000541979,"about_ca_system_score_gemma":0.0006595803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005376019,"about_ca_topic_score_gemma":0.0006616722,"domain_scores_codex":[0.9948574,0.002515314,0.0007060227,0.0006402393,0.0009562669,0.0003247788],"domain_scores_gemma":[0.9881123,0.005618872,0.001770664,0.0004090997,0.001795408,0.002293701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.1592393,0.06559419,0.229854,0.002133627,0.00140298,0.0003589545,0.002739071,0.006878905,0.02081319,0.0006305524,0.002454381,0.507901],"study_design_scores_gemma":[0.008993366,0.4118268,0.5365271,0.0002970446,0.00083027,0.0004405876,0.001399277,0.02251261,0.01243251,0.0008003822,0.003712082,0.0002279499],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966433,0.000155813,0.001519451,0.00006124689,0.00006439434,0.000747058,0.0001063326,0.00003840961,0.000664017],"genre_scores_gemma":[0.9931566,0.0001760409,0.004134454,0.00006722186,0.00006524904,0.001195899,0.0001829538,0.00001073165,0.001010803],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00455617,"threshold_uncertainty_score":0.02407378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04195865251939022,"score_gpt":0.4608609860364374,"score_spread":0.4189023335170471,"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."}}