{"id":"W2806165888","doi":"","title":"Extracting Adverse Drug Reactions using Deep Learning and Dictionary Based Approaches.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Drug reaction; Artificial intelligence; Dictionary learning; Natural language processing; Drug; Pharmacology; Medicine; Sparse approximation","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":[0.0008555219,0.0006001196,0.0008772856,0.005737559,0.0004159468,0.001031841,0.0008008643,0.0008685329,0.002462433],"category_scores_gemma":[0.00550253,0.0001892199,0.001004132,0.003779343,0.0002736168,0.001368977,0.001380384,0.0008976544,0.001500925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006506872,"about_ca_system_score_gemma":0.001633425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004717498,"about_ca_topic_score_gemma":0.008980292,"domain_scores_codex":[0.9987407,0.0002410926,0.0002473628,0.0002269327,0.0004288544,0.0001150118],"domain_scores_gemma":[0.9965013,0.001641928,0.0005952682,0.0003156158,0.0008236963,0.0001221593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005359047,0.0004754532,0.03040616,0.002021466,0.0004296094,0.001115699,0.0002264986,0.009876679,0.01341256,0.006936942,0.03982737,0.8947357],"study_design_scores_gemma":[0.0002850144,0.0009849101,0.07133677,0.001471558,0.001395808,0.005140274,0.001982037,0.5644564,0.04541536,0.1308341,0.1764823,0.0002153364],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2223532,0.02019391,0.6626781,0.004152291,0.001135979,0.001554646,0.0562247,0.006827688,0.02487956],"genre_scores_gemma":[0.607464,0.006604707,0.3187553,0.0008458945,0.00033693,0.0005776327,0.05862877,0.0001839859,0.006602862],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005737559,"threshold_uncertainty_score":0.009380102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02359633721303129,"score_gpt":0.2853442128436758,"score_spread":0.2617478756306446,"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."}}