{"id":"W3024228313","doi":"10.2196/18417","title":"Extraction of Information Related to Drug Safety Surveillance From Electronic Health Record Notes: Joint Modeling of Entities and Relations Using Knowledge-Aware Neural Attentive Models","year":2020,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Documentation; Computer science; Medical prescription; Information extraction; Sentence; Medical record; Artificial intelligence; Medicine; Medical emergency; Information retrieval; Data mining; Natural language processing","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":[0.001149491,0.001185709,0.0005665479,0.002092423,0.0004517438,0.001403849,0.001405453,0.001430658,0.001016726],"category_scores_gemma":[0.004669152,0.0006047088,0.001794198,0.001399953,0.0004124899,0.001785579,0.001038129,0.001938362,0.0005521099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001864239,"about_ca_system_score_gemma":0.001557318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03063351,"about_ca_topic_score_gemma":0.02942431,"domain_scores_codex":[0.9994695,0.0001084859,0.00006158373,0.0002344252,0.00007581933,0.00005024367],"domain_scores_gemma":[0.997402,0.001853747,0.0002888628,0.0001268083,0.0002724685,0.0000562463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005552126,0.0009142226,0.02828232,0.0005746282,0.0004637311,0.001635709,0.0007216305,0.5426437,0.008351859,0.006554927,0.01013058,0.3991714],"study_design_scores_gemma":[0.000007637454,0.00002523651,0.001592347,0.00002690161,0.00005361951,0.00004174263,0.00003502263,0.993082,0.001100916,0.003083684,0.0009412896,0.000009736625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2185754,0.00295702,0.7557774,0.003592906,0.0002222999,0.0005886782,0.007305246,0.004836487,0.006144636],"genre_scores_gemma":[0.7755918,0.001236716,0.2091811,0.0006794682,0.0001497708,0.0004188233,0.00847041,0.00008580703,0.004186104],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03063351,"threshold_uncertainty_score":0.0609104,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03801965279698179,"score_gpt":0.2973762146673368,"score_spread":0.2593565618703551,"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."}}