{"id":"W4385709848","doi":"10.1093/jamiaopen/ooad062","title":"Automated identification of unstandardized medication data: a scalable and flexible data standardization pipeline using RxNorm on GEMINI multicenter hospital data","year":2023,"lang":"en","type":"article","venue":"JAMIA Open","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; St. Michael's Hospital","funders":"Alliance de recherche numérique du Canada","keywords":"Standardization; Computer science; Identifier; Pharmacy; Coding (social sciences); Data mining; Information retrieval; Medicine; Statistics; Mathematics; Family medicine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001736698,0.0001242061,0.0002135243,0.00006667255,0.0001133829,0.00011389,0.001869973,0.0001575169,0.00001122358],"category_scores_gemma":[0.001385154,0.0001088348,0.00001106353,0.0002541161,0.0001744372,0.00006334262,0.003736582,0.00007217971,0.00000780639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001749969,"about_ca_system_score_gemma":0.000173159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001236588,"about_ca_topic_score_gemma":0.00003593473,"domain_scores_codex":[0.9982848,0.00008498203,0.0004136821,0.000751606,0.0002843458,0.0001805596],"domain_scores_gemma":[0.9970621,0.00004539598,0.0002495293,0.002468911,0.0001090531,0.00006504742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001159601,0.0004864129,0.005753432,0.0003176958,0.0004154845,0.00001158868,0.0003709846,0.0002770025,0.2982412,0.00006178457,0.536998,0.1559067],"study_design_scores_gemma":[0.004241485,0.0002910907,0.01103768,0.0002530025,0.0001858747,0.000006303767,0.0006998756,0.7488163,0.04124334,0.00005417472,0.1927484,0.0004224917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7591041,0.00141721,0.2004468,0.004399488,0.001638369,0.002710586,0.0287836,0.0006025617,0.0008973519],"genre_scores_gemma":[0.9232706,0.0007728291,0.00986771,0.0001039576,0.0001710808,0.00001078971,0.06534158,0.00003091586,0.000430543],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7485393,"threshold_uncertainty_score":0.4657382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09741173152302603,"score_gpt":0.4051766285713367,"score_spread":0.3077648970483107,"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."}}