{"id":"W4390988578","doi":"10.1097/acm.0000000000005634","title":"Using Natural Language Processing to Evaluate the Quality of Supervisor Narrative Comments in Competency-Based Medical Education","year":2024,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Saskatchewan; Royal College of Physicians and Surgeons of Canada; McMaster University Medical Centre","funders":"","keywords":"Supervisor; Narrative; Quality (philosophy); Medical education; Natural (archaeology); Psychology; Computer science; Natural language processing; Medicine; Linguistics; Political science; History","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004239096,0.0001661197,0.0003988849,0.0004348303,0.00007707987,0.000005793198,0.0002669136,0.0001944108,0.0004836776],"category_scores_gemma":[0.008232344,0.0001011053,0.00003519597,0.001712725,0.0003393404,0.00009678681,0.00004436744,0.001336374,0.000008583426],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003209341,"about_ca_system_score_gemma":0.00506643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004096977,"about_ca_topic_score_gemma":0.00003836373,"domain_scores_codex":[0.9968277,0.0002701767,0.0009839544,0.0002985403,0.001373608,0.0002459845],"domain_scores_gemma":[0.998862,0.0003060968,0.000104344,0.0002737551,0.0003308772,0.000122973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005198889,0.0004260156,0.02755249,0.004812894,0.0001568471,0.00003173031,0.3594753,0.00005196011,0.07180054,0.01599325,0.04439932,0.4747798],"study_design_scores_gemma":[0.008743213,0.0008494246,0.07609604,0.05478971,0.0006413427,0.000269094,0.3080429,0.5320664,0.005275431,0.005530239,0.00677542,0.0009208431],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8255404,0.005748111,0.001151729,0.1653566,0.001116016,0.0006749271,0.000001309983,0.00004255639,0.0003683202],"genre_scores_gemma":[0.9746682,0.00002583619,0.001997204,0.02229589,0.0006768795,0.00006440421,0.00009372656,0.00002109236,0.0001567342],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5320144,"threshold_uncertainty_score":0.985548,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08285630765382505,"score_gpt":0.5130708602996962,"score_spread":0.4302145526458711,"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."}}