{"id":"W2807150748","doi":"","title":"Adverse Reaction Extraction from Drug Labels Using LSTM Networks.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Adverse drug reaction; Extraction (chemistry); Computer science; Drug reaction; Drug; Artificial intelligence; Natural language processing; Chemistry; Pharmacology; Medicine; Chromatography","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":[0.0009974374,0.000754199,0.0004706164,0.002082812,0.0003076712,0.0007511764,0.0007297453,0.0008641655,0.003523618],"category_scores_gemma":[0.004875883,0.0001599133,0.0007897373,0.001482789,0.0001855853,0.0009060692,0.000799274,0.00100525,0.002191451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007714373,"about_ca_system_score_gemma":0.001106519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004520619,"about_ca_topic_score_gemma":0.009504126,"domain_scores_codex":[0.9994484,0.0001479165,0.0000531505,0.0001418339,0.0001409484,0.00006780124],"domain_scores_gemma":[0.9982842,0.0009492936,0.0002143608,0.0001321183,0.0003762563,0.00004381975],"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":[0.000815173,0.0003538106,0.01962306,0.001143056,0.0002865306,0.0005422868,0.000167588,0.03484914,0.01316205,0.004102567,0.046195,0.8787596],"study_design_scores_gemma":[0.00007696891,0.0003501664,0.01706919,0.0003269546,0.0003929334,0.0006271325,0.0002425153,0.8882858,0.02697605,0.03147981,0.03410656,0.00006587883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1882504,0.007907101,0.7283694,0.004076456,0.00154142,0.0009349365,0.03019895,0.01390864,0.02481283],"genre_scores_gemma":[0.7915313,0.002047513,0.1764376,0.0006201685,0.0003460897,0.0005234913,0.02004406,0.0001548545,0.008294882],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004520619,"threshold_uncertainty_score":0.01178765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02061288158274141,"score_gpt":0.3213272460412929,"score_spread":0.3007143644585515,"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."}}