{"id":"W2772514355","doi":"10.2196/medinform.9170","title":"Adverse Drug Event Discovery Using Biomedical Literature: A Big Data Neural Network Adventure","year":2017,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; National Center for Advancing Translational Sciences; Institute for Clinical and Translational Research, University of Wisconsin, Madison; Marshfield Clinic Research Institute","keywords":"Big data; Computer science; Social media; SPARK (programming language); Data science; Scalability; Knowledge extraction; Analytics; World Wide Web; Social media analytics; Artificial intelligence; Machine learning; Data mining; Database","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":[0.002094295,0.000977688,0.0007043265,0.006499468,0.0008876138,0.002275047,0.001271171,0.001356944,0.001172473],"category_scores_gemma":[0.006403503,0.0003856783,0.00103958,0.00399486,0.0004658138,0.002127478,0.001181056,0.001298615,0.0005083621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001082995,"about_ca_system_score_gemma":0.00136767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009095694,"about_ca_topic_score_gemma":0.01457568,"domain_scores_codex":[0.9989935,0.0002719568,0.0001262523,0.0002652875,0.0002795492,0.00006353398],"domain_scores_gemma":[0.9964095,0.001888031,0.0004019271,0.0004092976,0.0006530279,0.0002382056],"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":[0.001096591,0.001622258,0.0930094,0.00147457,0.001113793,0.002486354,0.0006426146,0.0422524,0.007312897,0.004151529,0.04516658,0.7996711],"study_design_scores_gemma":[0.00008093844,0.0003417738,0.02798875,0.0003169841,0.0003792512,0.0007995937,0.000651623,0.918868,0.006908576,0.01769494,0.02589504,0.00007446059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6643854,0.04703921,0.1892852,0.04519746,0.002680354,0.001021613,0.02452841,0.006079237,0.01978317],"genre_scores_gemma":[0.7453778,0.0108375,0.2195599,0.00264611,0.00158589,0.0003057683,0.01496124,0.0000808098,0.004645024],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009095694,"threshold_uncertainty_score":0.01808554,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1348998625086512,"score_gpt":0.4625458255001619,"score_spread":0.3276459629915108,"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."}}