{"id":"W4396680020","doi":"10.2196/56342","title":"Assessing the Ability of a Large Language Model to Score Free-Text Medical Student Clinical Notes: Quantitative Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Natural language processing; Psychology; Medical education; Medicine; World Wide Web","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":[0.02292199,0.0004416342,0.000463675,0.001624312,0.0003659434,0.001097151,0.0006803231,0.0004952495,0.00127892],"category_scores_gemma":[0.09068587,0.0002559051,0.0006960436,0.0008192312,0.0009587529,0.00143929,0.001536412,0.0005922689,0.0004879685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006997252,"about_ca_system_score_gemma":0.0006827866,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005486005,"about_ca_topic_score_gemma":0.0008167618,"domain_scores_codex":[0.9820637,0.008882541,0.002060037,0.001340521,0.005196932,0.0004563773],"domain_scores_gemma":[0.8581287,0.1031215,0.0135684,0.004504351,0.01870337,0.001973804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001016159,0.00158349,0.9160661,0.000217829,0.0002007041,0.0001394324,0.01104589,0.0009155546,0.002583521,0.0001103013,0.0006933371,0.06542765],"study_design_scores_gemma":[0.0001767878,0.00831317,0.957375,0.0001456138,0.0001906287,0.001021589,0.01084699,0.01375288,0.005725064,0.0002939056,0.002044418,0.0001140166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9969757,0.00004054878,0.002105241,0.0000246894,0.000006745342,0.0001825995,0.00007177706,0.00002169445,0.0005709823],"genre_scores_gemma":[0.996831,0.00003085297,0.002572986,0.00002252188,0.00000688161,0.0002067198,0.000108048,0.00001161788,0.0002092689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02292199,"threshold_uncertainty_score":0.1212245,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2698714885083644,"score_gpt":0.6452357604818295,"score_spread":0.3753642719734651,"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."}}