{"id":"W4405050704","doi":"10.2196/52068","title":"Evaluation of a Computer-Based Morphological Analysis Method for Free-Text Responses in the General Medicine In-Training Examination: Algorithm Validation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Simulation-Based Education in Healthcare","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Text messaging; Matching (statistics); Computer science; Natural language processing; Presentation (obstetrics); Artificial intelligence; Segmentation; Domain (mathematical analysis); Medical education; Medicine; Machine learning; Medical physics; Pathology; Radiology","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":[0.01691242,0.00135541,0.001027523,0.00283193,0.0005535067,0.001630497,0.001854867,0.001971063,0.002066979],"category_scores_gemma":[0.04175268,0.0004096573,0.0009222561,0.001409521,0.0004717026,0.001080949,0.001228369,0.0007764979,0.001019505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000920193,"about_ca_system_score_gemma":0.001199627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003967275,"about_ca_topic_score_gemma":0.003690782,"domain_scores_codex":[0.9927769,0.003478003,0.00103118,0.001295035,0.001226685,0.0001923174],"domain_scores_gemma":[0.9573886,0.02981224,0.001714088,0.001928906,0.008768917,0.0003872837],"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":[0.004164943,0.001393457,0.06925335,0.0007929319,0.0008585235,0.0003383037,0.0007119709,0.05480054,0.03531763,0.0009828038,0.002877889,0.8285077],"study_design_scores_gemma":[0.0004411588,0.001436634,0.03486756,0.0001114021,0.0002841428,0.0007578767,0.0002966382,0.9391051,0.02022734,0.0005239975,0.00187857,0.00006956814],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5356425,0.001164247,0.4546566,0.0001856888,0.0001689269,0.001847935,0.0005938967,0.004502014,0.00123803],"genre_scores_gemma":[0.4774664,0.0002751341,0.5184865,0.0001155912,0.00003177209,0.001223896,0.001197309,0.0002187198,0.0009846403],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01691242,"threshold_uncertainty_score":0.08944249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1522816462793468,"score_gpt":0.5287105663652942,"score_spread":0.3764289200859474,"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."}}