{"id":"W2897647360","doi":"10.1002/cpt.1255","title":"Innovation in Pharmacovigilance: Use of Artificial Intelligence in Adverse Event Case Processing","year":2018,"lang":"en","type":"article","venue":"Clinical Pharmacology & Therapeutics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":86,"is_retracted":false,"has_abstract":true,"ca_institutions":"Pfizer (Canada); Artificial Intelligence in Medicine (Canada)","funders":"Pfizer","keywords":"Pharmacovigilance; Adverse effect; Event (particle physics); Complex event processing; Adverse Event Reporting System; Artificial intelligence; Computer science; Medicine; Pharmacology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0238436,0.000871237,0.0006003541,0.004857072,0.0006467236,0.004149988,0.001652237,0.001065956,0.001298392],"category_scores_gemma":[0.05569172,0.0004186143,0.0007804575,0.002801909,0.001578551,0.00284629,0.002394442,0.001446969,0.0004800191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001948586,"about_ca_system_score_gemma":0.002201849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00223562,"about_ca_topic_score_gemma":0.002080092,"domain_scores_codex":[0.9773166,0.01279818,0.001947213,0.001651163,0.005892199,0.0003946231],"domain_scores_gemma":[0.9263064,0.05282145,0.00563796,0.006167106,0.008390008,0.0006771481],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001205575,0.001271178,0.05237516,0.001058252,0.0005224211,0.0007635986,0.002786552,0.03658264,0.03401413,0.01657891,0.003214754,0.8496268],"study_design_scores_gemma":[0.0005417393,0.003143721,0.08557843,0.000840673,0.0005365775,0.002502964,0.002285249,0.7169073,0.08624762,0.07235815,0.02847435,0.0005832103],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2773281,0.0008935601,0.6939349,0.003634211,0.0001191617,0.002627405,0.0003861132,0.003451976,0.01762458],"genre_scores_gemma":[0.422613,0.0002404309,0.5754886,0.000334342,0.00004579041,0.0003094868,0.0002548905,0.00007340533,0.0006401376],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0238436,"threshold_uncertainty_score":0.1260985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4092247310207464,"score_gpt":0.5705374598262889,"score_spread":0.1613127288055425,"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."}}