{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01065527,0.001191356,0.0006911462,0.004304087,0.0004139588,0.002342287,0.001445507,0.0007828907,0.001243431],"category_scores_gemma":[0.04571258,0.00041259,0.001771124,0.002303242,0.0008577209,0.003042272,0.001376821,0.001297841,0.0007902341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001925816,"about_ca_system_score_gemma":0.001930718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005034728,"about_ca_topic_score_gemma":0.005755985,"domain_scores_codex":[0.9940269,0.00371531,0.0004091515,0.0009704691,0.0007378717,0.0001402787],"domain_scores_gemma":[0.9378566,0.05421463,0.002168859,0.002777109,0.002724,0.0002588099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001348288,0.001140373,0.07455769,0.001184767,0.0008267566,0.0007300226,0.002376343,0.2233033,0.01282677,0.007966328,0.00723105,0.6665083],"study_design_scores_gemma":[0.00004336625,0.000147503,0.004670054,0.00008144869,0.0001453722,0.0001705525,0.0003191748,0.9756421,0.005907334,0.01035872,0.002481547,0.00003284382],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3013164,0.001000642,0.6833585,0.002064346,0.0001093835,0.0009059526,0.003042056,0.005750831,0.002452021],"genre_scores_gemma":[0.6630709,0.0005007013,0.3300362,0.0003313546,0.0001141929,0.0006150491,0.00424002,0.0002447936,0.0008469177],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01065527,"threshold_uncertainty_score":0.05635113,"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."}}