{"id":"W2899011686","doi":"10.2196/10788","title":"Detection of Bleeding Events in Electronic Health Record Notes Using Convolutional Neural Network Models Enhanced With Recurrent Neural Network Autoencoders: Deep Learning Approach","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Heart, Lung, and Blood Institute; National Institutes of Health","keywords":"Pharmacovigilance; Medicine; Health records; Electronic health record; Convolutional neural network; Deep learning; Major bleeding; Artificial neural network; Intensive care medicine; Artificial intelligence; Adverse effect; Medical emergency; Computer science; Internal medicine; Health care","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":[0.0007826393,0.0008333403,0.0003254349,0.0009007633,0.0001968234,0.0004715034,0.0006347547,0.0006155631,0.000901643],"category_scores_gemma":[0.002187453,0.0003165066,0.0005803746,0.000455067,0.0001737784,0.0006797113,0.0004202692,0.0009257367,0.0004566351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008154658,"about_ca_system_score_gemma":0.0007825483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01545629,"about_ca_topic_score_gemma":0.02013391,"domain_scores_codex":[0.9997391,0.00005700666,0.00002712232,0.00008551538,0.00005177089,0.00003945845],"domain_scores_gemma":[0.9991263,0.0004417808,0.0001207922,0.00005877369,0.0002248782,0.00002756828],"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":[0.0007113754,0.00079258,0.02849938,0.0003615276,0.0003585692,0.0009411924,0.0002938302,0.2812603,0.03616778,0.001758378,0.01280055,0.6360546],"study_design_scores_gemma":[0.000006922269,0.00004037067,0.002009429,0.00001047999,0.00002751264,0.00003577923,0.00001540519,0.9935464,0.003409941,0.0005238066,0.0003666558,0.000007328267],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4574365,0.002022632,0.5270098,0.001183377,0.0001821325,0.0002313941,0.003038361,0.005629954,0.003265887],"genre_scores_gemma":[0.8748649,0.0006449313,0.1158973,0.0002827882,0.0000791204,0.0001147406,0.004149839,0.00005822111,0.003908087],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01545629,"threshold_uncertainty_score":0.03073263,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08366403244212085,"score_gpt":0.4086108924995199,"score_spread":0.3249468600573991,"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."}}