{"id":"W2104381725","doi":"10.1136/amiajnl-2011-000150","title":"Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010","year":2011,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":240,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"U.S. National Library of Medicine","keywords":"Narrative; Benchmark (surveying); Process (computing); Computer science; State (computer science); Data science; Health care; Artificial intelligence; Natural language processing; Political science; Art; Cartography; Literature; Geography; Law","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003558089,0.00008340988,0.0002759108,0.000031335,0.0001453896,0.000009938619,0.0005321678,0.0001240806,0.00001662486],"category_scores_gemma":[0.005891096,0.00003923466,0.0003344423,0.0001522037,0.0004779773,0.00002444393,0.0002003546,0.0003473044,0.000002288961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004521082,"about_ca_system_score_gemma":0.0002705289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003119299,"about_ca_topic_score_gemma":0.00008497143,"domain_scores_codex":[0.9976616,0.0001742248,0.001279964,0.00003693867,0.000674483,0.0001728244],"domain_scores_gemma":[0.9945642,0.0003434077,0.004389491,0.0002459562,0.0003876244,0.0000692795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001329793,0.0005185343,0.1906929,0.0001757639,0.001624735,4.440452e-7,0.004694991,0.0004302751,0.001880987,0.0002973498,0.1816364,0.6167179],"study_design_scores_gemma":[0.003483944,0.002663083,0.7625557,0.0002324712,0.0005000082,0.00007681899,0.002834769,0.01307383,0.009153448,0.002681174,0.2023977,0.0003471271],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9592066,0.0001517301,0.0313124,0.006696429,0.001548084,0.0003153675,0.00008776933,0.000006338635,0.0006752214],"genre_scores_gemma":[0.9943545,0.000618034,0.003090716,0.001274925,0.0001981634,0.000006786244,0.00001325542,0.000007410983,0.0004361946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6163707,"threshold_uncertainty_score":0.7052618,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04653909334875948,"score_gpt":0.340871690572667,"score_spread":0.2943325972239075,"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."}}