{"id":"W4410203956","doi":"10.1371/journal.pdig.0000800","title":"Clinical insights: A comprehensive review of language models in medicine","year":2025,"lang":"en","type":"review","venue":"PLOS Digital Health","topic":"Topic Modeling","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; Saint Mary's University","funders":"","keywords":"Computer science; Context (archaeology); Key (lock); Autonomy; Data science; Resource (disambiguation); Health care; Management science; Knowledge management; Artificial intelligence; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004544385,0.0003485124,0.003911641,0.0003420843,0.00002321967,0.00002674747,0.001322088,0.0001688219,0.000003895771],"category_scores_gemma":[0.000351038,0.0002550619,0.0003378341,0.0009355271,0.00007566964,0.0003905236,0.0005584017,0.0005839916,0.0000138171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001659264,"about_ca_system_score_gemma":0.001691319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005542473,"about_ca_topic_score_gemma":0.000006443431,"domain_scores_codex":[0.9954472,0.0003968143,0.002622816,0.0007326955,0.0004634011,0.0003371082],"domain_scores_gemma":[0.9965184,0.001092223,0.0008453315,0.00122988,0.0001289841,0.0001851356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[3.443981e-7,0.00007275266,4.517769e-7,0.2802604,0.00002038552,0.00001139972,0.0001383733,8.546851e-7,5.759804e-10,0.003810763,0.0003646006,0.7153198],"study_design_scores_gemma":[0.0001770488,0.0001218894,4.805632e-7,0.6535438,0.00003840883,0.000008463902,0.00001590992,0.001896887,7.742516e-9,0.001256163,0.3427494,0.0001914328],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[5.843545e-7,0.9809248,0.01303264,0.0004598555,0.0002303351,0.001277309,0.00003014493,0.00007404136,0.003970272],"genre_scores_gemma":[0.000007169185,0.995201,0.002257607,0.002212374,0.00009437538,0.00004562023,0.00006400239,0.0000159409,0.0001019439],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7151283,"threshold_uncertainty_score":0.9999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2057323525799405,"score_gpt":0.4502191212996913,"score_spread":0.2444867687197507,"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."}}