{"id":"W2995134651","doi":"10.2196/14777","title":"Optimizing Antihypertensive Medication Classification in Electronic Health Record-Based Data: Classification System Development and Methodological Comparison","year":2019,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Electronic Health Records Systems","field":"Health Professions","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health; Clinical and Translational Science Institute, University of Florida; National Center for Advancing Translational Sciences; University of Florida; Florida Department of Health; Patient-Centered Outcomes Research Institute","keywords":"DrugBank; Medicine; Medical prescription; Terminology; Pairwise comparison; Data mining; Drug; Computer science; Artificial intelligence; Pharmacology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01286269,0.0003017927,0.001062794,0.0003641833,0.0004299826,0.00002395513,0.0006730745,0.0007636386,0.00008563908],"category_scores_gemma":[0.0008467914,0.0002491023,0.00003273929,0.0005548512,0.00009824877,0.0004247163,0.0002086322,0.002214463,0.000370027],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002557132,"about_ca_system_score_gemma":0.007204528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002103701,"about_ca_topic_score_gemma":0.0005805466,"domain_scores_codex":[0.9910356,0.002315139,0.003656838,0.0004823585,0.00120115,0.001308912],"domain_scores_gemma":[0.9942057,0.002199134,0.001818263,0.0009723675,0.0002289526,0.0005756369],"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":[0.0005361715,0.0008950072,0.316372,0.03374212,0.0001957234,0.000005767079,0.06966758,0.00006484838,0.0002003543,0.04699477,0.0251049,0.5062208],"study_design_scores_gemma":[0.002739585,0.0003044959,0.04014731,0.002799052,0.00001306565,0.00001349202,0.05501127,0.8003246,0.0000101473,0.0000224573,0.09824815,0.0003663845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8596092,0.00118984,0.1112526,0.01199963,0.001884466,0.009122588,0.00002260081,0.0006567395,0.004262331],"genre_scores_gemma":[0.9644589,0.0003069924,0.02957889,0.003696186,0.0001891618,0.0006968048,0.0009720418,0.00003846805,0.00006255251],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8002598,"threshold_uncertainty_score":0.9999961,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2787064707669388,"score_gpt":0.495084101649321,"score_spread":0.2163776308823822,"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."}}