{"id":"W4207070465","doi":"10.2196/31063","title":"Development of a Pipeline for Adverse Drug Reaction Identification in Clinical Notes: Word Embedding Models and String Matching","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Punctuation; Computer science; Identification (biology); Natural language processing; Word (group theory); Matching (statistics); Artificial intelligence; Set (abstract data type); Medicine; Pathology; Mathematics","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":[0.00281144,0.002093258,0.001142045,0.003687026,0.0004835489,0.001836064,0.001829075,0.001980979,0.007001243],"category_scores_gemma":[0.008884345,0.0007035349,0.002014782,0.002515357,0.0003483272,0.003202302,0.001556961,0.001959149,0.008820197],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001027986,"about_ca_system_score_gemma":0.001989825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006682999,"about_ca_topic_score_gemma":0.006385388,"domain_scores_codex":[0.9985887,0.0003758713,0.0001964562,0.0004622454,0.0002926624,0.00008407932],"domain_scores_gemma":[0.995676,0.00239043,0.0003283116,0.0005253013,0.000939658,0.0001403159],"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":[0.0004143421,0.0002996475,0.003247256,0.0005827244,0.000211195,0.0002877897,0.0001927351,0.01325406,0.01601386,0.00157031,0.01475313,0.9491729],"study_design_scores_gemma":[0.0001089618,0.0003575436,0.003737252,0.0001360053,0.0001536055,0.0004448098,0.0002959431,0.940925,0.03319072,0.008398313,0.01217456,0.00007727475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02051231,0.0006925489,0.9387293,0.0004612309,0.0001837304,0.0008006138,0.004078079,0.03348141,0.001060773],"genre_scores_gemma":[0.07424672,0.0005163718,0.9113463,0.0002036932,0.00006993893,0.0006706845,0.009658023,0.000581082,0.002707128],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007001243,"threshold_uncertainty_score":0.02342153,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.148014929724732,"score_gpt":0.4922374196700689,"score_spread":0.3442224899453369,"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."}}