{"id":"W2805155289","doi":"","title":"Extracting Positive Mentions of Adverse Drug Reactions from Product Labels using a Machine Learning Centric Approach.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Product (mathematics); Artificial intelligence; Machine learning; Drug reaction; Natural language processing; Drug; Pharmacology; Mathematics; Medicine","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":[0.002375766,0.0009800886,0.0009483501,0.01354103,0.001113966,0.001780917,0.001621407,0.002086362,0.002493144],"category_scores_gemma":[0.01463494,0.0003700005,0.001221636,0.00711973,0.0005038274,0.001873723,0.001818071,0.001154445,0.002102728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001050777,"about_ca_system_score_gemma":0.002683242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006866817,"about_ca_topic_score_gemma":0.01508961,"domain_scores_codex":[0.9964006,0.0007520275,0.0005116223,0.0007954041,0.001299699,0.0002406337],"domain_scores_gemma":[0.985359,0.007934126,0.00179271,0.001162282,0.003399624,0.0003522905],"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":[0.001120938,0.0008693833,0.1055429,0.003584475,0.000708851,0.003732849,0.001116884,0.007524629,0.03210589,0.01314676,0.08542941,0.7451171],"study_design_scores_gemma":[0.0003077991,0.000962091,0.2049798,0.001872133,0.002230331,0.01070423,0.003090004,0.3236022,0.06720652,0.1079521,0.2766342,0.0004585087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3116679,0.02235116,0.5217113,0.006107315,0.002111936,0.001875263,0.08598756,0.01266287,0.03552459],"genre_scores_gemma":[0.6405184,0.00247327,0.2813053,0.001254849,0.0006561659,0.0006679835,0.06617242,0.0002584518,0.006693147],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01354103,"threshold_uncertainty_score":0.0136537,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05997973488236706,"score_gpt":0.3983670202963445,"score_spread":0.3383872854139774,"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."}}