{"id":"W4412817474","doi":"10.3389/fmed.2025.1631565","title":"Leveraging LLM to identify missed information in patient-physician communication: improving healthcare service quality","year":2025,"lang":"en","type":"article","venue":"Frontiers in Medicine","topic":"Patient-Provider Communication in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Algorithm; Logistic regression; Computer science; Ordered logit; Machine learning; Medical record; Health care; Artificial intelligence; Medicine; Internal medicine","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01122087,0.0006294498,0.0005346691,0.002180762,0.0007007616,0.001982659,0.0007936108,0.0006901835,0.002520738],"category_scores_gemma":[0.05329884,0.0002840431,0.0007722898,0.00140992,0.0003965918,0.001937096,0.001896382,0.001186984,0.0008223692],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001635213,"about_ca_system_score_gemma":0.003223455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007439564,"about_ca_topic_score_gemma":0.009476626,"domain_scores_codex":[0.9913578,0.006069333,0.0005276141,0.0006762067,0.001046441,0.0003224724],"domain_scores_gemma":[0.9526435,0.03316477,0.007719282,0.002125574,0.003657355,0.0006895419],"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":[0.0003069801,0.0005715797,0.7218369,0.0006846141,0.0001574677,0.0001415279,0.003940735,0.007545982,0.002845354,0.0009761037,0.002929175,0.2580634],"study_design_scores_gemma":[0.00007345498,0.001013977,0.5012541,0.0005700524,0.0002345628,0.0003254771,0.007197134,0.46832,0.007988667,0.006488206,0.006386961,0.0001473907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8120434,0.0006011768,0.1722583,0.0050692,0.00007941906,0.0006503484,0.00170699,0.001913991,0.005677131],"genre_scores_gemma":[0.9300837,0.0001201869,0.06798633,0.000253674,0.00003217162,0.0002242606,0.0006752207,0.00003529263,0.0005891689],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01122087,"threshold_uncertainty_score":0.05934232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.133722209730895,"score_gpt":0.4478135238208978,"score_spread":0.3140913140900028,"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."}}