{"id":"W2791458756","doi":"10.2196/medinform.8960","title":"Characterizing and Managing Missing Structured Data in Electronic Health Records: Data Analysis","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Statistical Methods and Bayesian Inference","field":"Mathematics","cited_by":174,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine; National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Human Genome Research Institute; University of Pennsylvania; National Institutes of Health; Pennsylvania Department of Health","keywords":"Missing data; Imputation (statistics); Health records; Computer science; Data science; Electronic health record; Data mining; Health care; Machine learning","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":[0.003003762,0.0001791736,0.0005578861,0.0002496297,0.0001280447,0.0001286018,0.001092804,0.0001242004,0.000307475],"category_scores_gemma":[0.002248151,0.0001465887,0.00001929797,0.0007025594,0.0002070679,0.0005718438,0.0009949419,0.0004946358,0.000006599061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006598208,"about_ca_system_score_gemma":0.0002903678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006948588,"about_ca_topic_score_gemma":0.0004598227,"domain_scores_codex":[0.9973879,0.0001676557,0.001035693,0.0002822892,0.0005649219,0.000561522],"domain_scores_gemma":[0.9970308,0.0007620195,0.0003523854,0.001515546,0.00003874646,0.0003005067],"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":[0.00002254849,0.00005224134,0.001702011,0.0006350051,0.000181626,0.000007894357,0.003868597,1.443559e-8,0.000004908723,0.04932584,0.001740091,0.9424592],"study_design_scores_gemma":[0.000823977,0.0001861368,0.008353455,0.00069359,0.0002208136,0.00004722894,0.001864535,0.6203794,0.00001412577,0.361256,0.005674283,0.0004864906],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0144456,0.00007652992,0.9822434,0.00183154,0.0001066844,0.0002802384,0.0001696598,0.00006744883,0.0007789119],"genre_scores_gemma":[0.09233689,0.0002667306,0.9045528,0.002107236,0.0002148677,0.000007023798,0.0004837643,0.00001975283,0.0000109418],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9419727,"threshold_uncertainty_score":0.5977713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08677746776859628,"score_gpt":0.4334871571936644,"score_spread":0.3467096894250681,"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."}}