{"id":"W3048489732","doi":"10.1111/medu.14347","title":"Machine learning to extract communication and history‐taking skills in OSCE transcripts","year":2020,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Hamilton Medical Research Group","funders":"","keywords":"Transferability; Sentence; F1 score; Computer science; Natural language processing; Artificial intelligence; Utterance; Context (archaeology); Machine learning; Objective structured clinical examination; Support vector machine; Medicine; Medical education; Biology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007210615,0.0001262726,0.0002238496,0.0002155975,0.00006715507,0.00001278378,0.0001468431,0.0001550661,0.001330402],"category_scores_gemma":[0.01129888,0.0001263883,0.00002673325,0.0005384743,0.00009729876,0.0001225858,0.00003184259,0.0008030837,0.00004512814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004278726,"about_ca_system_score_gemma":0.0010341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002789074,"about_ca_topic_score_gemma":0.0000351084,"domain_scores_codex":[0.9984156,0.0001246573,0.00044624,0.0002885011,0.0005317489,0.0001932187],"domain_scores_gemma":[0.9992333,0.00007442338,0.0001172432,0.0002159493,0.0001330919,0.0002260163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008336375,0.001124897,0.04286133,0.0002624406,0.00001431446,0.000005436109,0.02405606,0.000008857141,0.001000376,0.0008649587,0.04768537,0.8820326],"study_design_scores_gemma":[0.001209053,0.0002331221,0.1382104,0.0007895685,0.00004407739,0.00005352492,0.001731278,0.01309721,0.0001059886,0.00006918827,0.8442246,0.0002320025],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7438278,0.003866707,0.00261616,0.2422766,0.0007553039,0.0007188059,7.016472e-7,0.0001290875,0.00580882],"genre_scores_gemma":[0.9345759,0.0002795308,0.00697499,0.05719949,0.0002587746,0.00008775857,0.0001421769,0.00002453992,0.0004569079],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8818006,"threshold_uncertainty_score":0.9995825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02168354091414416,"score_gpt":0.3381810623154852,"score_spread":0.3164975214013411,"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."}}