{"id":"W4406015091","doi":"10.2196/58457","title":"The Transformative Potential of Large Language Models in Mining Electronic Health Records Data: Content Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Servicio Andaluz de Salud","keywords":"McNemar's test; Computer science; Medicine; Machine learning; Medical physics; Artificial intelligence; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002143087,0.00009621333,0.0003822996,0.0002741158,0.0001169164,0.00001555567,0.000284551,0.0001209478,0.00004631334],"category_scores_gemma":[0.0002516313,0.00006473831,0.00008439118,0.0009526129,0.00009306562,0.0002611784,0.0000596664,0.0004297894,0.000003868194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001729706,"about_ca_system_score_gemma":0.001520694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000793458,"about_ca_topic_score_gemma":0.00319143,"domain_scores_codex":[0.9975823,0.00008271092,0.001330334,0.00008901817,0.0004890272,0.0004266312],"domain_scores_gemma":[0.9988514,0.000233511,0.0002219578,0.000428206,0.0001219467,0.0001429715],"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":[0.0005318968,0.0007223378,0.006432697,0.001528059,0.0009461658,0.000006852897,0.1839132,0.0002779901,0.000009206971,0.009120067,0.006579172,0.7899323],"study_design_scores_gemma":[0.0003899003,0.0002795967,0.002182367,0.0005017304,0.0001844019,0.000006615453,0.2455314,0.7475741,0.0002378984,0.0006110914,0.00239533,0.0001056077],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9196065,0.001185142,0.06418347,0.01217514,0.0002762301,0.0008649733,0.00004069742,0.00003199859,0.001635828],"genre_scores_gemma":[0.9956301,0.001200444,0.0003592305,0.002327761,0.0000455192,0.00003754242,0.0002526152,0.000004055782,0.0001427431],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7898267,"threshold_uncertainty_score":0.2697645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1100382858948128,"score_gpt":0.4558892266026876,"score_spread":0.3458509407078748,"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."}}