{"id":"W3129597052","doi":"10.2196/24678","title":"Extracting Drug Names and Associated Attributes From Discharge Summaries: Text Mining Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Topic Modeling","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; King's College London; Saudi Arabian Cultural Bureau","keywords":"CRFS; Computer science; Conditional random field; Named-entity recognition; Natural language processing; Artificial intelligence; Word embedding; Context (archaeology); Biomedical text mining; Relationship extraction; Task (project management); Information extraction; Deep learning; Word (group theory); F1 score; Machine learning; Embedding; Text mining","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007336596,0.0001554777,0.0002950893,0.00004910601,0.000201016,0.0003932388,0.0005267066,0.000115249,0.0000890822],"category_scores_gemma":[0.00140898,0.0001349699,0.00004096067,0.0002676779,0.00004823233,0.0009493039,0.0007912812,0.0003886035,0.00001791355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004223355,"about_ca_system_score_gemma":0.0002041648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004201611,"about_ca_topic_score_gemma":0.00007325396,"domain_scores_codex":[0.9978005,0.00009671683,0.0006893183,0.0001920755,0.0008895168,0.0003318341],"domain_scores_gemma":[0.9980841,0.0009359734,0.0002190185,0.0003999522,0.0001086927,0.0002523063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008314878,0.001121465,0.2675488,0.0001842328,0.0004091288,0.0003070385,0.425265,0.00005102434,0.00004239099,0.0040377,0.009559164,0.2914657],"study_design_scores_gemma":[0.001737008,0.000062981,0.019263,0.000403688,0.00003080334,0.00002437646,0.06269224,0.909363,0.0001527794,0.0007422714,0.005030987,0.0004968271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9395444,0.0001671121,0.05780067,0.001264095,0.0003152357,0.0001717295,0.00001169209,0.0001736481,0.0005514317],"genre_scores_gemma":[0.973091,0.00002390624,0.02569557,0.0008307107,0.000104676,0.00002276134,0.00003368739,0.000008347727,0.0001893064],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.909312,"threshold_uncertainty_score":0.5503914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02615739534699034,"score_gpt":0.2886754367506368,"score_spread":0.2625180414036464,"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."}}