{"id":"W4416965115","doi":"10.2196/77580","title":"Feasibility of a Specialized Large Language Model for Postgraduate Medical Examination Preparation: Single-Center Proof-Of-Concept Study","year":2025,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Innovations in Medical Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Educational measurement; Medical history; Physical examination; Objective structured clinical examination; Language assessment","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":[0.01857517,0.00100554,0.0006882177,0.0006485349,0.0004525968,0.001328954,0.001676649,0.001034824,0.003586582],"category_scores_gemma":[0.01977216,0.0004295979,0.0008331691,0.0001965702,0.0007218049,0.001248856,0.001405058,0.001070778,0.0009939555],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007349055,"about_ca_system_score_gemma":0.002451123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006004522,"about_ca_topic_score_gemma":0.0007080188,"domain_scores_codex":[0.9939495,0.0031828,0.0003522833,0.0004992872,0.001555377,0.0004607737],"domain_scores_gemma":[0.9858022,0.00479723,0.001457778,0.001619641,0.004091279,0.002231844],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.02173698,0.06649591,0.04733879,0.005245789,0.0008605814,0.002204464,0.007464877,0.01524368,0.4463076,0.001696181,0.007427447,0.3779776],"study_design_scores_gemma":[0.009236612,0.5570399,0.07088967,0.0008224686,0.001400256,0.002390378,0.004502847,0.0409661,0.2674741,0.0008211535,0.04407287,0.0003836856],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9564906,0.0002140961,0.03077922,0.0003030071,0.00009465341,0.009824239,0.0002794263,0.0004986617,0.00151613],"genre_scores_gemma":[0.8671532,0.0003802984,0.119818,0.0003817067,0.00006884302,0.009615436,0.0005063501,0.0001078203,0.001968439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01857517,"threshold_uncertainty_score":0.09823608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1222072542841215,"score_gpt":0.5186528880953443,"score_spread":0.3964456338112228,"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."}}